CN108648061A

CN108648061A - image generating method and device

Info

Publication number: CN108648061A
Application number: CN201810479980.6A
Authority: CN
Inventors: 刘斌; 张开涛; 崔菁; 张弛; 费程; 杨嗦
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Priority date: 2018-05-18
Filing date: 2018-05-18
Publication date: 2018-10-12

Abstract

The embodiment of the present application discloses image generating method and device.One specific implementation mode of this method includes：Obtain the user images and depth information of target user；Based on user images, at least one candidate dress ornament image is determined；In at least one candidate dress ornament image, determine that the candidate dress ornament image that user chooses is used as selected dress ornament image；Based on depth information and selected dress ornament image, the fitting image of user is generated.The embodiment enriches the flexibility of image formation mode, helps to improve the flexibility of user's fitting mode.

Description

Image generating method and device

Technical field

The invention relates to field of computer technology, and in particular to image generating method, device and system.

Background technology

Currently, the flow that user buys dress ornament in boutique is generally as follows：First, the style for selecting dress ornament, it is suitable to find Close oneself color and size；Then, it is tried on before taking fitting room or fitting mirror, checks practical fitting effects.

However, often up to tens of kinds or more of the dress ornament style of boutique.User may need to select and try on more Dress ornament.

Invention content

The embodiment of the present application proposes image generating method and device.

In a first aspect, the embodiment of the present application provides a kind of image generating method, this method includes：Take the use of target user Family image and depth information；Based on user images, at least one candidate dress ornament image is determined；In at least one candidate dress ornament image In, determine that the candidate dress ornament image that user chooses is used as selected dress ornament image；Based on depth information and selected dress ornament image, generate The fitting image of user.

In some embodiments, the above method further includes：Depth information is sent to destination service end；Receive destination service The threedimensional model for the user that end group is built in depth information；And it is based on depth information and selected dress ornament image, generate user's Fitting image, including：Based on threedimensional model and selected dress ornament image, the three-dimensional fitting image of user is generated.

In some embodiments, user images are based on, determine at least one candidate dress ornament image, including：By user images It is sent to destination service end；The matched at least one candidate dress ornament image of destination service end returns and user images is received, with Determine at least one candidate dress ornament image.

In some embodiments, the above method further includes：It is sent to target indicator at least one of following：Fitting image, At least one candidate's dress ornament image.

In some embodiments, target indicator is touch display；And the above method further includes：Believed based on control Breath, controls at least one of following controlled device：Target speaker, target hair-dryer, target aromitizer, target illumination lamp, In, control information includes at least one of following：The control signal that destination client is sent, the control sound that target microphone obtains Frequently, the touching instruction that touch display detects, the user gesture image that camera group is got.

In some embodiments, the above method further includes：In response to determining that user images meet default storage condition, store User images.

In some embodiments, user images are based on, determine at least one candidate dress ornament image, including：Schemed based on user Picture determines at least one following user information of target user：Age information, Skin Color Information, hair style information, body-shape information；Base In at least one user information, at least one candidate dress ornament image is determined.

In some embodiments, user images include the direct picture of user, back side image and left and right sides image；And Fitting image includes the front fitting image of user, back side fitting image and left and right sides fitting image.

In some embodiments, user images include facial image；And the above method further includes：Receive destination service end The face recognition result of return, wherein face recognition result be destination server based on Face image synthesis, for characterize be The no result existed with the associated account of target user；It is associated with target user in response to determining that face recognition result characterization exists Account, store instruction is sent to destination service end, so that at least one of following be associated with account is deposited at destination service end Storage：At least one candidate's dress ornament image, at least one user information, front fitting image, back side fitting image, left and right sides examination Clothing image.

Second aspect, the embodiment of the present application provide a kind of video generation device, which includes：Acquiring unit, by with It is set to the user images and depth information for obtaining target user；First determination unit is configured to be based on user images, determine extremely A few candidate dress ornament image；Second determination unit is configured at least one candidate dress ornament image, determines that user chooses Candidate dress ornament image as selecting dress ornament image；Generation unit is configured to be based on depth information and selected dress ornament image, raw At the fitting image of user.

In some embodiments, above-mentioned apparatus further includes：First transmission unit is configured to depth information being sent to mesh Mark server-side；First receiving unit is configured to receive the threedimensional model for the user that destination service end group is built in depth information； And generation unit is further configured to be based on threedimensional model and selected dress ornament image, generates the three-dimensional fitting image of user.

In some embodiments, the first determination unit is further configured to：User images are sent to destination service end； The matched at least one candidate dress ornament image of destination service end returns and user images is received, to determine at least one time Select dress ornament image.

In some embodiments, above-mentioned apparatus further includes：First transmission unit, be configured to target indicator send with It is at least one of lower：Fitting image, at least one candidate dress ornament image.

In some embodiments, target indicator is touch display；And above-mentioned apparatus further includes：Control unit, quilt It is configured to, based on control information, control at least one of following controlled device：Target speaker, target hair-dryer, target fragrance Device, target illumination lamp, wherein control information includes at least one of following：The control signal that destination client is sent, target Mike The control audio that wind obtains, the touching instruction that touch display detects, the user gesture image that camera group is got.

In some embodiments, above-mentioned apparatus further includes：Storage unit is configured in response to determine that user images meet Default storage condition, stores user images.

In some embodiments, the first determination unit is further configured to：Based on user images, determine target user's At least one user information below：Age information, Skin Color Information, hair style information, body-shape information；Believed based at least one user Breath determines at least one candidate dress ornament image.

In some embodiments, user images include facial image；And above-mentioned apparatus further includes：Second receiving unit, It is configured to receive the face recognition result that destination service end returns, wherein face recognition result is that destination server is based on people Result that face image generates, for characterize with the presence or absence of with the associated account of target user；Second transmission unit, is configured to In response to determination face recognition result characterization presence and the associated account of target user, store instruction is sent to destination service end, So that destination service end is associated storage by least one of following with account：At least one candidate's dress ornament image, at least one User information, front fitting image, back side fitting image, left and right sides fitting image.

The third aspect, the embodiment of the present application provide a kind of image generation system, which includes：Control device and with control The camera group of control equipment communication connection, wherein：Camera group is configured to obtain the user images of target user and depth letter Breath；Control device is configured to obtain user images and depth information from camera group；Based on user images, at least one is determined A candidate's dress ornament image；In at least one candidate dress ornament image, determine that the candidate dress ornament image that user chooses takes as selected Adorn image；Based on depth information and selected dress ornament image, the fitting image of user is generated.

In some embodiments, above system further includes the server-side communicated to connect with control device.

In some embodiments, above-mentioned server-side is configured to obtain user images from control device；Schemed based on user Picture determines the user information of target user；User information is input to dress ornament recommended models trained in advance, is obtained at least one Candidate dress ornament image, wherein dress ornament recommended models are used to characterize the correspondence of user information and candidate dress ornament image；It will at least One candidate dress ornament image is sent to control device.

In some embodiments, above-mentioned server-side is further configured to obtain depth information from control device；Based on depth Information is spent, the threedimensional model of user is built；Threedimensional model is sent to control device.

In some embodiments, control device is further configured in response to determining that user images meet preset mark Condition marks user images；Labeled user images are sent to server-side；Server-side is configured to the use that will be labeled Family image is stored.

In some embodiments, above system further includes the display communicated to connect with control device；And display, quilt It is configured to receive at least one of following from control device and show：Fitting image, at least one candidate dress ornament image, three-dimensional mould Type.

In some embodiments, above system further includes that at least one the following control communicated to connect with control device fills It sets：Client, microphone, touch display；Above system further include with control device communicate to connect it is at least one of following by Control device：Speaker, hair-dryer, aromitizer, headlamp；And control device, it is further configured to according at least one control The control information that device is sent, at least one of control controlled device.

In some embodiments, camera group include at least four colour imagery shots, at least four colour imagery shots by with It is set to the direct picture for obtaining user, back side image and left and right sides image；And fitting image includes the front fitting of user Image, back side fitting image and left and right sides fitting image.

In some embodiments, server-side is further configured to obtain the facial image of target user；To facial image Carry out recognition of face, it is determined whether exist and the associated account of target user；If so, being carried out at least one of following with account Associated storage：At least one candidate's dress ornament image, fitting image, labeled user images.

Fourth aspect, the embodiment of the present application provide a kind of control device generated for image, including：It is one or more Processor；Storage device is stored thereon with one or more programs, when said one or multiple programs are by said one or multiple Processor executes so that the one or more processors realize the method such as any embodiment in above-mentioned image generating method.

5th aspect, the embodiment of the present application provide a kind of computer-readable medium that image generates, are stored thereon with meter Calculation machine program realizes the method such as any embodiment in above-mentioned image generating method when the program is executed by processor.

Image generating method and device provided by the embodiments of the present application are determined at least by the user images based on acquisition One candidate dress ornament image determines selected dress ornament image then at least one candidate dress ornament image, is finally based on acquired Depth information and selected dress ornament image, the fitting image for generating user have to enrich the flexibility of image formation mode Help improve the flexibility of user's fitting mode.

Description of the drawings

By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other Feature, objects and advantages will become more apparent upon：

Fig. 1 is that the embodiment of the present application can be applied to exemplary system architecture figure therein；

Fig. 2 is the flow chart according to one embodiment of the image generating method of the application；

Fig. 3 A- Fig. 3 C are the schematic diagrames according to the application scenarios of the image generating method of the application；

Fig. 4 is the flow chart according to another embodiment of the image generating method of the application；

Fig. 5 is the flow chart fitted according to the schematical user of one embodiment of the image generating method of the application；

Fig. 6 is the structural schematic diagram according to one embodiment of the video generation device of the application；

Fig. 7 is the interactive process schematic diagram of camera group and control device in the image generation system according to the application；

Fig. 8 is adapted for the structural schematic diagram of the computer system of the control device for realizing the embodiment of the present application.

Specific implementation mode

The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to Convenient for description, is illustrated only in attached drawing and invent relevant part with related.

It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

Fig. 1 shows that the image generating method, video generation device or image that can apply the embodiment of the present application generate system The exemplary system architecture 100 of system.

It is set as shown in Figure 1, system architecture 100 may include control device 101, server 102, camera 103 and terminal Standby 104.Network 105 between control device 101, server 102, camera 103 and terminal device 104 providing communication chain The medium on road.Network 105 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..

Control device 101 can control controlled device (not shown) or camera 103, to achieve phase The function of answering.Wherein, above-mentioned controlled device can include but is not limited at least one of following：Speaker, hair-dryer, aromitizer, photograph Bright lamp.As an example, above-mentioned control device 101 can control unlatching, closing or brightness regulation of headlamp etc..Control is set Standby 101 can be hardware, can also be software.Can be there is image generative capacity each when control device 101 is hardware Kind electronic equipment, including but not limited to micro-chip processor, pocket computer on knee and desktop computer etc..Work as control device 101 when being software, may be mounted in above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into it, It can also be implemented as single software or software module.It is not specifically limited herein.

It should be noted that the image generating method that the embodiment of the present application is provided generally is executed by control device 101, phase Ying Di, video generation device are generally positioned in control device 101.However, when terminal device 104 or server 102 are integrated When having control device 101 or having the function that control device 101 is provided, image generating method that the embodiment of the present application is provided It can also be executed by terminal device 104 or server 102, correspondingly, video generation device can also be set to terminal device 104 Or in server 102.

Server 102 can be to provide the server of various services, such as provide the rear number of units supported to control device 101 According to processing server.Back-end data processing server can be handled the depth information acquired in control device 101, with structure The threedimensional model of user is built out, and handling result (such as threedimensional model) is fed back into control device 101.

It should be noted that server can be hardware, can also be software.When server is hardware, may be implemented At the distributed server cluster that multiple servers form, individual server can also be implemented as.It, can when server is software To be implemented as multiple softwares or software module (such as providing the software or software module of Distributed Services), can also realize At single software or software module.It is not specifically limited herein.

Terminal device 104 can be hardware, can also be software.Can have to show when terminal device 104 is hardware Display screen and the various electronic equipments for supporting information to transmit, including but not limited to smart mobile phone, tablet computer, portable meter on knee Calculation machine and desktop computer etc..When terminal device 104 is software, may be mounted in above-mentioned cited electronic equipment. Multiple softwares or software module (such as providing the software or software module of Distributed Services) may be implemented into it, can also It is implemented as single software or software module.It is not specifically limited herein.

It should be understood that the number of the control device, camera, terminal device, network and server in Fig. 1 is only to illustrate Property.According to needs are realized, can have any number of terminal device, network and server.

With continued reference to Fig. 2, the flow 200 of one embodiment of the image generating method according to the application is shown.The figure As generation method, include the following steps：

Step 201, the user images and depth information of target user are obtained.

In the present embodiment, the executive agent (such as control device shown in FIG. 1) of image generating method can be by having Line connection type or radio connection obtain the use of target user from other electronic equipments (such as camera shown in FIG. 1) Family image and depth information.Wherein, target user can be the user being located in a certain area of space.For example, in certain boutique Fitting room user.Above-mentioned depth information (depth information) can be that depth camera acquires, comprising above-mentioned Information of each position of the body of target user at a distance from depth camera.Above-mentioned depth camera can use infrared light The depth camera of structure；Can also be to be based on flight time telemetry (Time of flight, TOF) and Binocular Vision Principle Depth camera.Above-mentioned user images can be the image of the user of picture or visual form.Above-mentioned depth information may include But it is not limited at least one of following：Age information, Skin Color Information, hair style information, height information, body-shape information etc..

Step 202, user images are based on, determine at least one candidate dress ornament image.

In the present embodiment, above-mentioned executive agent can be determined at least one based on the user images obtained in step 201 Candidate dress ornament image.Wherein, above-mentioned candidate dress ornament image can meet certain conditions in dress ornament included in the boutique Dress ornament image.Wherein, above-mentioned condition can be the clothes that style and/or size and/or price etc. are suitble to above-mentioned target user Decorations.

As an example, above-mentioned executive agent can be based on the letter of the dress of above-mentioned target user included in user images It ceases (such as dress ornament style information, apparel size information, dress ornament pricing information), determines at least one candidate dress ornament image.Example Such as, if the dress ornament that user is worn in user images is " one-piece dress ", above-mentioned executive agent can be by institute in the boutique Including the images of all one-piece dresses be determined as candidate dress ornament image；If the dress ornament that user is worn in user images is " XX brands ", the dress ornament price of the brand is between 500 yuan to 1000 yuan, then above-mentioned executive agent can be by institute in the boutique There is the image of dress ornament of the price between 500 yuan to 1000 yuan to be determined as candidate dress ornament image.

Step 203, at least one candidate dress ornament image, determine that the candidate dress ornament image that user chooses takes as selected Adorn image.

In the present embodiment, above-mentioned executive agent can determine that user selects in above-mentioned at least one candidate dress ornament image In candidate dress ornament image as selecting dress ornament image.

In practice, above-mentioned executive agent may be used various ways and determine the candidate dress ornament image that user chooses.For example, After above-mentioned at least one candidate dress ornament image display, above-mentioned executive agent can acquire the figure of above-mentioned user by camera Picture, to determine that user watches the candidate dress ornament image chosen attentively, wherein above-mentioned executive agent user can be watched attentively 3 seconds and Above candidate dress ornament image is determined as user and watches the candidate dress ornament image chosen attentively.Optionally, when above-mentioned at least one time When the color of dress ornament image being selected to be respectively red, yellow, and green, then above-mentioned executive agent can be by voice by above-mentioned at least one candidate The distinctive information of each of dress ornament image candidate's dress ornament image plays out, to inform user.For example, above-mentioned executive agent can " may I ask you by voice and like the dress ornament of red yellow or green" inform the difference of each candidate dress ornament image of user Information, then, by acquiring the return information (such as red) of user, to determine candidate dress ornament image that user chooses.

Step 204, it is based on depth information and selected dress ornament image, generates the fitting image of user.

In the present embodiment, above-mentioned executive agent can based on acquired in step 201 depth information and step 203 institute really Fixed selected dress ornament image, generates the fitting image of user.Wherein, above-mentioned fitting image can be two dimensional image, can also be Threedimensional model.Image of fitting can be an image, can also be multiple images；It can be picture, can also be video；May be used also To be direct picture, back side image, the side image etc. of user.Fitting image can be half body image, whole body images, can also It is the image etc. at each visual angle.

In practice, above-mentioned executive agent can construct the threedimensional model of above-mentioned target user first by depth information, Then threedimensional model and above-mentioned selected dress ornament image are subjected to image co-registration, to obtain the fitting image of threedimensional model characterization.It can Choosing, above-mentioned executive agent can also be overlapped above-mentioned user images and selected dress ornament image, then be based on depth information pair It is superimposed obtained image to be adjusted, to obtain the fitting image of threedimensional model characterization.

In some optional realization methods of the present embodiment, depth information can also be sent to mesh by above-mentioned executive agent Mark server-side；Receive the threedimensional model for the user that destination service end group is built in depth information.Then, above-mentioned executive agent base again In threedimensional model and selected dress ornament image, the three-dimensional fitting image of user is generated.Wherein, above-mentioned destination service end can be with it is upper State the server of executive agent communication connection.Above-mentioned destination server can be after receiving depth information, using above-mentioned side Formula constructs the threedimensional model of user.Then, above-mentioned executive agent can be based on threedimensional model and selected dress ornament image, using figure As modes such as superpositions, the three-dimensional fitting image of user is generated.Optionally, above-mentioned executive agent can also be based on Unity3D, The softwares such as 3DMAX (3D Studio Max), three-dimensional modeling and animation software (MAYA) are based on threedimensional model and selected dress ornament figure Picture generates the three-dimensional fitting image of user.

In some optional realization methods of the present embodiment, user images are based on, determine at least one candidate dress ornament figure Picture, including：User images are sent to destination service end；It receives that destination service end returns, matched at least with user images One candidate dress ornament image, to determine at least one candidate dress ornament image.Wherein, destination server can be and above-mentioned execution The server of main body communication connection.The destination service end can be with the server-side of the above-mentioned threedimensional model for building user Same server-side can also be different server-side.

Herein, above-mentioned destination server can be based on the technologies such as machine learning algorithm, big data, determine to scheme with user As matched at least one candidate dress ornament image.Above-mentioned candidate dress ornament image matched with user images, can be price it is consistent, Style (such as American-European style, Feminine Style, hip-hop style, commuting style, institute's style etc.) is consistent etc..

In some optional realization methods of the present embodiment, above-mentioned executive agent may also respond to determine user images Meet default storage condition, stores user images.Wherein, above-mentioned default storage condition can be that the user in user images is in Particular state.The state etc. that above-mentioned particular state can be smile state, face camera.Above-mentioned default storage condition also may be used To be the presence of account associated with the facial image included by above-mentioned user images.Herein, above-mentioned executive agent or and its The server of communication connection can have the function of recognition of face, receive the facial image included by above-mentioned user images it Afterwards, above-mentioned executive agent or communicate with connection server can to facial image carry out recognition of face, to determine whether to deposit In account associated with the facial image.If being not present, above-mentioned executive agent or the server for communicating with connection can refer to Show that user carries out registration operation, to establish the incidence relation of the facial image and account.If in the presence of, above-mentioned executive agent or with Its server communicated to connect can be by data of the user in fitting process (such as selected dress ornament image, browsing record, user Captured photo or video etc.) with the account be associated storage, so that user checks at any time.In addition, when exist and the people When the associated account of face image, above-mentioned executive agent or server may call upon the historical record of user (such as history are clear The dress ornament information etc. that dress ornament information, the history of the dress ornament information, history purchase look at are tried on), more accurately to determine candidate Dress ornament image.

Illustratively, above-mentioned default storage condition can be that clear (such as resolution ratio is more than preset resolution to user images Rate threshold value) and user images in reflected portrait position, posture, expression be suitable for take pictures (such as portrait position be user The centre of image, posture be do not block face, expression is smile).User is during trying on as a result, above-mentioned executive agent After the unlatching of camera group image can be read in real time, the image acquired in camera group includes the image of people, and is obtained When image clearly, portrait position, posture, the expression taken is suitable for taking pictures, take pictures, to store certain fitting images.Optionally, Above-mentioned default storage condition can also be that the time of trying on of user is more than preset duration threshold value (such as 1 minute).Herein, on Right moment for camera can be determined based on artificial intelligence (Artificial Intelligence, AI) algorithm by stating executive agent, to carry out The candid photograph of photo and small video.

It is above-mentioned to be based on user images in some optional realization methods of the present embodiment, determine at least one candidate clothes Image is adornd, including：Based on user images, at least one following user information of target user is determined：Age information, colour of skin letter Breath, hair style information, body-shape information；Based at least one user information, at least one candidate dress ornament image is determined.It is appreciated that Above-mentioned executive agent can according to one or more in the age information of user, Skin Color Information, hair style information, body-shape information, Determine the image at least one candidate dress ornament for being suitble to user.

In some optional realization methods of the present embodiment, user images include the direct picture of user, back side image With left and right sides image；And fitting image includes the front fitting image of user, back side fitting image and left and right sides fitting Image.It is appreciated that working as the front fitting image that fitting image includes user, back side fitting image and left and right sides fitting image When, contribute to the front of the selected dress ornament image that above-mentioned target user can be clearly seen that it is chosen, the back side and the left and right sides Fitting effects, without turning round.Thus, it is possible to which more comprehensively, easily understanding this selectes the corresponding selected dress ornament of dress ornament image Effect.

In some optional realization methods of the present embodiment, user images include facial image；And the above method is also Including：Receive the face recognition result that destination service end returns, wherein face recognition result is that destination server is based on face figure As result generate, for characterize with the presence or absence of with the associated account of target user；In response to determining face recognition result table Sign exist and the associated account of target user, to destination service end send store instruction so that destination service end by it is following at least One is associated storage with account：At least one candidate's dress ornament image, at least one user information, front fitting image, the back of the body Interview clothing image, left and right sides fitting image.Wherein, destination server can be the service communicated to connect with above-mentioned executive agent Device.After receiving the facial image included by above-mentioned user images, above-mentioned destination server can carry out facial image Recognition of face, to determine whether there is account associated with the facial image.The destination service end can be used for structure with above-mentioned The server-side for building the threedimensional model of user is same server-side, can also be different server-side；It can be with above-mentioned return candidate The server-side of dress ornament image is same server-side, can also be different server-side.

In practice, above-mentioned destination server can be based on facial image in several ways, generate face recognition result.Example Such as, technical staff can there will be the facial images of associated account to store in advance；Later, above-mentioned destination server can be with It whether determines in stored facial image including the facial image included by above-mentioned user images；If including above-mentioned target Server can be generated for characterizing in the presence of the face recognition result with the associated account of target user；It is above-mentioned if not including Destination server can be generated for characterizing the face recognition result being not present with the associated account of target user.Optionally, on It states destination server and is also based on face recognition technology and facial image, generate face recognition result.

It it is showing according to the application scenarios of the image generating method of the present embodiment with continued reference to Fig. 3 A- Fig. 3 C, Fig. 3 A- Fig. 3 C It is intended to.In the application scenarios, control device (i.e. above-mentioned executive agent) obtains the use of user by colour imagery shot first Family image 301 (please refers to Fig.3 A), and the depth information of target user is obtained by depth camera；Then, control is set It is standby to be based on user images 301, determine candidate dress ornament image 302 (please referring to Fig.3 B), wherein candidate dress ornament image 302 includes " T-shirt ", " skirt ", " one-piece dress "；Later, control device by acquire user voice, in candidate dress ornament image 302, The candidate dress ornament image that user chooses is determined for the image of one-piece dress, and using the image of one-piece dress as selected dress ornament figure Picture；Finally, image of the control device based on depth information and one-piece dress generates the fitting image 303 (please referring to Fig.3 C) of user.

The method that above-described embodiment of the application provides, by obtaining the user images and depth information of target user, so It is based on user images afterwards, determines at least one candidate dress ornament image, later at least one candidate dress ornament image, determines user The candidate dress ornament image chosen is finally based on depth information and selected dress ornament image, generates user's as dress ornament image is selected Image of fitting helps to improve the flexibility of user's fitting mode to enrich the flexibility of image formation mode.

With further reference to Fig. 4, it illustrates the flows 400 of another embodiment of image generating method.The image generates The flow 400 of method, includes the following steps：

Step 401, the user images and depth information of target user are obtained.

In the present embodiment, step 401 and the step 201 in Fig. 2 corresponding embodiments are almost the same, and which is not described herein again.

Step 402, user images are based on, determine at least one candidate dress ornament image.

In the present embodiment, step 402 and the step 202 in Fig. 2 corresponding embodiments are almost the same, and which is not described herein again.

Step 403, at least one candidate dress ornament image, determine that the candidate dress ornament image that user chooses takes as selected Adorn image.

In the present embodiment, step 403 and the step 203 in Fig. 2 corresponding embodiments are almost the same, and which is not described herein again.

Step 404, it is based on depth information and selected dress ornament image, generates the fitting image of user.

In the present embodiment, step 404 and the step 204 in Fig. 2 corresponding embodiments are almost the same, and which is not described herein again.

Step 405, it is sent to target indicator at least one of following：Fitting image, at least one candidate dress ornament image.

In the present embodiment, above-mentioned executive agent can also be sent at least one of following to target indicator：Fitting image, At least one candidate's dress ornament image.Wherein, above-mentioned target indicator can be the display communicated to connect with above-mentioned control device. The target indicator can be a liquid crystal display, can also be the screen that multiple screens are spliced, can also be use The device that projecting apparatus is shown.

It is appreciated that after above-mentioned executive agent sends fitting image to target indicator, user can be made to watch examination Clothing effect；After above-mentioned executive agent sends candidate dress ornament image to target indicator, user can be facilitated to select dress ornament figure Picture, and then watch clothes effect.

Step 406, it is based on control information, controls at least one of following controlled device：Target speaker, target blowing Machine, target aromitizer, target illumination lamp.

In the present embodiment, it is based on control information, above-mentioned executive agent can also control in following controlled device at least One：Target speaker, target hair-dryer, target aromitizer, target illumination lamp.Wherein, control information includes at least one of following： The control signal that destination client is sent, the control audio that target microphone obtains, the touching instruction that touch display detects, The user gesture image that target camera group is got.

Wherein, aforementioned display device is touch display, and above-mentioned target speaker can be communicated to connect with above-mentioned executive agent Speaker, the target speaker for play audio (such as background music etc.).Above-mentioned target hair-dryer can be and above-mentioned execution The hair-dryer of main body communication connection, the target hair-dryer can provide sea wind and other effects, so that user's shooting has sea wind effect Photo or video.Above-mentioned target aromitizer can be the aromitizer communicated to connect with above-mentioned executive agent, the target fragrance Device can provide various tastes, such as the fragrance of a flower, herbaceous taste, seawater taste etc., it will be understood that, can by the blowing function of hair-dryer It is propagated with the taste that is distributed target aromitizer rapider, user can be made to generate and be in outdoor feeling, help to seek Atmosphere is made, and then shoots photo or video with various different-effects.Above-mentioned target illumination lamp can be held with above-mentioned The headlamp of row main body communication connection, which can be made of one group of colour temperature and the adjustable LED light of brightness, optional , above-mentioned target illumination lamp can also be the laser lamp or other light sources to eye-safe, and above-mentioned control information can control this The direction of illumination of target illumination lamp, brightness, colour temperature etc., the front and back left side in space where which can be set to user Multiple positions such as right, for user manually or automatically control its direction of illumination, brightness, colour temperature etc., to simulate different scenes Under irradiation condition.Above-mentioned destination client (such as mobile phone, tablet computer etc.) can be communicated to connect with above-mentioned executive agent Client, the client can by application software, small routine or webpage etc. and above-mentioned executive agent, server or on It states controlled device to interact, which can be provided with user interface etc., the control letter which sends Number it can be used for controlling one or more of above-mentioned controlled device.Above-mentioned target microphone can be logical with above-mentioned executive agent Believe connection microphone, the target microphone can be used for acquire user voice, the target microphone for user with it is above-mentioned Executive agent, server or above-mentioned controlled device interact, the audio (i.e. above-mentioned control audio) which obtains It can be used for controlling one or more of above-mentioned controlled device.Above-mentioned touch display for user and above-mentioned executive agent, Server or above-mentioned controlled device interact, and the touching instruction which detects can be used for controlling above-mentioned controlled One or more of device.Above-mentioned target camera group can be the camera group communicated to connect with above-mentioned executive agent.On It states target camera group to interact for user and above-mentioned executive agent, server or above-mentioned controlled device, target camera shooting The user gesture image that head group is got can be used for controlling one or more of above-mentioned controlled device.Above-mentioned target camera Group may include four (can also be other quantity) colour imagery shots, to shoot the photo of user's all around all angles Or video；Optionally, above-mentioned target camera group can also include two (can also be other quantity) depth cameras, on The front and back of user can be respectively arranged at by stating depth camera, to obtain the depth information of user.

Optionally, above-mentioned controlled device can be arranged by holder in the fixed position in the spaces such as fitting room or removable On position；It can also be arranged in the fixed position in the spaces such as fitting room or removable by hanging, being embedded in the modes such as wall On position.

It is appreciated that when above-mentioned target microphone gets the voice of user, can show over the display corresponding Word；When above-mentioned target speaker plays audio, corresponding word can also be shown over the display.

Illustratively, after the voice " changing music " described in the user is got by above-mentioned target microphone, above-mentioned target Speaker can carry out music switching；When the gesture instruction " turning on light " of user, and above-mentioned camera gets the image of the gesture Later, above-mentioned target illumination lamp can automatically turn on.Herein, user can make gesture by oneself according to the custom of oneself Justice can also define the gesture that " the five fingers opening " is " turning on light " for example, user can define the gesture that " holding fist " is " turning on light ".

In some usage scenarios, aforementioned display device can be also used for showing various images, such as the image on grassland, seashore Image, certain sight spot image etc..Optionally, which can be that (such as 55 cun of color/graphics are aobvious for large-screen display Show device).

In some usage scenarios, above-mentioned destination client can be also used for user's logon account, know for example, by using face It logs in or is logged in by the way of account number cipher otherwise.Aforementioned display device is scanned as user by above-mentioned destination client to show After the Quick Response Code shown, user can control above-mentioned controlled device by the destination client.User can also pass through the target Client browses fitting image, selected dress ornament image etc. at any time.Shopping cart can be added in selected dress ornament image by user, to carry out Subsequent operation operations such as (such as) comparing, select, placing an order.Optionally, user can also pass through above-mentioned touch display, target wheat The realization of the equipment such as gram wind such as compares, selects, placing an order at the operations.It is appreciated that after user places an order, can be received by way of express delivery The dress ornament oneself chosen, it is possible thereby to realize on-line off-line combination.As a result, in user's fitting process, oneself can be felt The dress ornament of interest is labeled or is added shopping cart.Then into one from the dress ornament included by the dress ornament of mark or shopping cart Step selects dress ornament.After user, which opens, to do shopping, each dress ornament in shopping cart, photo when thering is corresponding user to try on and/ Or video, also, the fitting effects of multiple dress ornaments can be simultaneously displayed on display by above-mentioned executive agent, to help user It is compared and is selected.Further, user has chosen the purchase that can independently place an order by control device after dress ornament.User completes examination Listed account can be exited after clothing, leave fitting area.The fitting process of user can be recorded by above-mentioned executive agent, be pushed away It is sent in the account (such as cell phone software, small routine or account of website) of user, user can be browsed at any time by account, be divided Enjoy and buy dress ornament.It is appreciated that the excellent picture and small video in user's fitting process can be recorded by above-mentioned executive agent, Compare and select dress ornament for user.

In some usage scenarios, user can select to try true dress ornament on, at this point it is possible to will really be taken by salesman Decorations transfer to user to try on, and later, aforementioned display device can show the fitting effects of true dress ornament.At this point, aforementioned display device is in Image when existing image is no longer virtually trying can help user more intuitively to select dress ornament in this way.At this point, being filled in control Under the control set, display may be implemented multi-angle display, replace background；Target illumination lamp can adjust lighting angle and bright Degree；Target speaker can play background music；Target hair-dryer can provide blowing special efficacy, to allow user to undergo interesting examination Clothes body is tested.

It is appreciated that above-mentioned executive agent controls one or more of controlled device by controlling information, can try The atmosphere close to environment of really wearing the clothes is simulated between clothing, thus, it is possible to help user experience in true environment, light, background The wears effect of dress ornament after color etc. changes.Furthermore, it is possible to using multiple technologies and electronic device (such as above-mentioned target sound Case, camera group, target aromitizer, target hair-dryer, target illumination lamp, display etc.), based on a variety of interactive means (such as Image interaction, speech enabled, touch-control interaction etc.), it realizes user's efficiently pleasant fitting experience, user is facilitated to choose dress ornament.

Referring to FIG. 5, it illustrates the schematical users according to one embodiment of the image generating method of the application The flow 500 of fitting.The flow 500 of the fitting of the user, includes the following steps：

After user enters fitting room, above-mentioned executive agent can obtain the user images and depth information of the user.

It is then based on above-mentioned user images and face recognition technology, determines whether the user is that new user (determines whether In the presence of the account with the user-association).If it is new user, it indicates that the user's registration account；If not new user, then refer to Show user's login account.

Then, above-mentioned execution theme can be based on user images and AI algorithms, recommend dress ornament for the user, to determine at least One candidate dress ornament image.

Later, which can select dress ornament in above-mentioned at least one candidate dress ornament image, and be filled by above-mentioned control It sets (such as camera group) and indicates above-mentioned executive agent, to determine candidate dress ornament image that user chooses as selected dress ornament figure Picture.Executive agent can be based on depth information and selected dress ornament image, generate the fitting image of user, so that user carries out virtually Fitting.During virtual fitting, above-mentioned executive agent can send fitting image to display.Above-mentioned executive agent can be with The instruction that user is acquired by camera group equal controller, with the control information of generation, to control speaker, hair-dryer, perfume (or spice) Gustatory organ, headlamp etc., to simulate true fitting environment.

Next, selected dress ornament can be added to shopping cart by user, to carry out comparison selection into shopping cart.

Then, user can determine whether to try entity dress ornament (i.e. true dress ornament) on, if it is desired, then the user can To inform salesman, dress ornament is sent by salesman, entity dress ornament is carried out and tries on.

Finally, user may determine whether the dress ornament of oneself satisfaction.If so, then placing an order；If if not yet, having really It is fixed whether to need to continue to fit, if it is not required, then exiting account, leave fitting room, if it is desired, then above-mentioned executive agent after It is continuous to execute above-mentioned AI algorithms recommendation dress ornament step.

Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the flow of the image generating method in the present embodiment 400 highlight the step of sending fitting image or at least one candidate dress ornament image to target indicator, and based on control letter The step of breath, control controlled device.The scheme of the present embodiment description can show more images as a result, and build trueer Real atmosphere further enriches the flexibility of user's fitting mode, helps to attract passenger flow for boutique.

It generates and fills this application provides a kind of image as the realization to method shown in above-mentioned each figure with further reference to Fig. 6 The one embodiment set, the device embodiment are corresponding with embodiment of the method shown in Fig. 2.It should be noted that removing following skills Outside art feature, which can also include technical characteristic identical with embodiment of the method shown in Fig. 2, which can specifically answer For in various electronic equipments.

As shown in fig. 6, the video generation device 600 of the present embodiment includes：Acquiring unit 601, the first determination unit 602, Second determination unit 603 and generation unit 604.Wherein, acquiring unit 601 be configured to obtain target user user images and Depth information；First determination unit 602 is configured to be based on user images, determines at least one candidate dress ornament image；Second really Order member 603 is configured at least one candidate dress ornament image, determines that the candidate dress ornament image conduct that user chooses is selected Dress ornament image；Generation unit 604 is configured to be based on depth information and selected dress ornament image, generates the fitting image of user.

In the present embodiment, the acquiring unit 601 of video generation device 600 can be by wired connection mode or wireless Connection type obtains the user images and depth information of target user from other electronic equipments (such as camera shown in FIG. 1). Wherein, target user can be the user being located in a certain area of space.For example, the user of the fitting room in boutique.It is above-mentioned Depth information can be depth camera acquire, each position of body comprising above-mentioned target user and depth camera away from From information.Above-mentioned depth camera can be the depth camera using infrared photo structure；Can also be to be surveyed based on the flight time Depth camera away from method and Binocular Vision Principle.Above-mentioned user images can be the image of the user of picture or visual form. Above-mentioned depth information can include but is not limited at least one of following：Age information, Skin Color Information, hair style information, height information, Body-shape information etc..

In the present embodiment, the user images obtained based on acquiring unit 601, above-mentioned first determination unit 602 can be true Fixed at least one candidate dress ornament image.Wherein, above-mentioned candidate dress ornament image can be accorded in dress ornament included in the boutique Close the image of the dress ornament of certain conditions.Wherein, above-mentioned condition can be that style and/or size and/or price etc. are suitble to above-mentioned mesh Mark the dress ornament of user.

In the present embodiment, the second determination unit of above- mentioned information 603 can in above-mentioned at least one candidate dress ornament image, Determine that the candidate dress ornament image that user chooses is used as selected dress ornament image.

In practice, above-mentioned second determination unit may be used various ways and determine the candidate dress ornament image that user chooses. For example, after above-mentioned at least one candidate dress ornament image display, above-mentioned apparatus can acquire above-mentioned user's by camera Image, to determine that user watches the candidate dress ornament image chosen attentively, wherein above-mentioned apparatus user can be watched attentively 3 seconds and with On candidate dress ornament image, be determined as user and watch the candidate dress ornament image chosen attentively.Optionally, as above-mentioned at least one candidate When the color of dress ornament image is respectively red, yellow, and green, then above-mentioned apparatus can be by voice by above-mentioned at least one candidate dress ornament figure The distinctive information of the candidate dress ornament image of each of picture plays out, to inform user.For example, above-mentioned apparatus can pass through voice " it may I ask you and like the dress ornament of red yellow or green" inform the distinctive information of each candidate dress ornament image of user, then, By acquiring the return information (such as red) of user, to determine candidate dress ornament image that user chooses.

In the present embodiment, above-mentioned generation unit 604 can be based on the depth information and second acquired in acquiring unit 601 Dress ornament image is selected determined by determination unit 603, generates the fitting image of user.Wherein, above-mentioned fitting image can be two Image is tieed up, can also be threedimensional model；It can be an image, can also be multiple images；It can be picture, can also be to regard Frequently；It can also be direct picture, back side image, the side image etc. of user.Image of fitting can be half body image, whole body figure Picture can also be the image etc. at each visual angle.

In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：First transmission unit (does not show in figure Go out) it is configured to depth information being sent to destination service end；First receiving unit (not shown) is configured to receive mesh The threedimensional model for the user that mark server-side is built based on depth information；Generation unit be further configured to based on threedimensional model and Selected dress ornament image, generates the three-dimensional fitting image of user.Wherein, above-mentioned destination service end can be and above-mentioned apparatus communication link The server connect.Above-mentioned destination server can construct the three of user after receiving depth information using aforesaid way Dimension module.Then, above-mentioned apparatus can be based on threedimensional model and selected dress ornament image, using modes such as image superpositions, generate and use The three-dimensional fitting image at family.Optionally, above-mentioned apparatus can also be based on Unity3D, 3DMAX, three-dimensional modeling and animation software etc. Software is based on threedimensional model and selected dress ornament image, generates the three-dimensional fitting image of user.

In some optional realization methods of the present embodiment, the first determination unit is further configured to：User is schemed As being sent to destination service end；The matched at least one candidate dress ornament image of destination service end returns and user images is received, To determine at least one candidate dress ornament image.Wherein, destination server can be the server communicated to connect with above-mentioned apparatus.

In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：First transmission unit (does not show in figure Go out) be configured to send to target indicator it is at least one of following：Fitting image, at least one candidate dress ornament image.Wherein, on It can be the display communicated to connect with above-mentioned control device to state target indicator.The target indicator can be a liquid crystal Screen, be can also be the screen that multiple screens are spliced, can also be the device shown using projecting apparatus.

In some optional realization methods of the present embodiment, target indicator is touch display；And above-mentioned apparatus Further include：Control unit (not shown) is configured to, based on control information, control at least one of following controlled device： Target speaker, target hair-dryer, target aromitizer, target illumination lamp, wherein control information includes at least one of following：Target The control signal that client is sent, the control audio that target microphone obtains, the touching instruction that touch display detects, target The user gesture image that camera group is got.

Wherein, aforementioned display device is touch display, and above-mentioned target speaker can be the sound communicated to connect with above-mentioned apparatus Case, the target speaker is for broadcasting audio (such as background music etc.).Above-mentioned target hair-dryer can be and above-mentioned executive agent The hair-dryer of communication connection, the target hair-dryer can provide sea wind and other effects, so as to photograph of user's shooting with sea wind effect Piece or video.Above-mentioned target aromitizer can be the aromitizer communicated to connect with above-mentioned apparatus, which can carry For various tastes, such as the fragrance of a flower, herbaceous taste, seawater taste etc., it will be understood that, can be by target by the blowing function of hair-dryer The taste that aromitizer is distributed is propagated rapider, and user can be made to generate and be in outdoor feeling, helps to build atmosphere, into And shoot photo or video with various different-effects.Above-mentioned target illumination lamp can be communicated to connect with above-mentioned apparatus Headlamp, which can be made of one group of colour temperature and the adjustable LED light of brightness, optionally, above-mentioned target illumination Lamp can also be the laser lamp or other light sources to eye-safe, and above-mentioned control information can control the irradiation of the target illumination lamp Direction, brightness, colour temperature etc., the target illumination lamp can be set to multiple positions such as all around in space where user, can For user manually or automatically control its direction of illumination, brightness, colour temperature etc., to simulate the irradiation condition under different scenes.On It can be the client communicated to connect with above-mentioned apparatus to state destination client (such as mobile phone, tablet computer etc.), which can To be interacted by application software, small routine or webpage etc. and above-mentioned apparatus 600, server or above-mentioned controlled device, The client can be provided with user interface etc., the destination client send control signal can be used for controlling it is above-mentioned by Control one or more of device.Above-mentioned target microphone can be the microphone communicated to connect with above-mentioned apparatus 600, the target Microphone can be used for acquiring the voice of user, the target microphone for user and above-mentioned apparatus 600, server or it is above-mentioned by Control device interacts, and the audio (i.e. above-mentioned control audio) which obtains can be used for controlling above-mentioned controlled device One or more of.Above-mentioned touch display is handed over for user and above-mentioned apparatus 600, server or above-mentioned controlled device Mutually, the touching instruction which detects can be used for controlling one or more of above-mentioned controlled device.Above-mentioned mesh It can be the camera group communicated to connect with above-mentioned executive agent to mark camera group.Above-mentioned target camera group for user with it is upper It states device 600, server or above-mentioned controlled device to interact, the user gesture image which gets can be with For controlling one or more of above-mentioned controlled device.It (can also be other that above-mentioned target camera group, which may include four, Quantity) colour imagery shot, to shoot the photo or video of user's all around all angles；Optionally, above-mentioned target is taken the photograph As head group can also can be respectively arranged at including two (can also be other quantity) depth cameras, above-mentioned depth camera User's is front and back, to obtain the depth information of user.

In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：Storage unit (not shown) It is configured in response to determine that user images meet default storage condition, stores user images.Wherein, above-mentioned default storage condition Can be that user in user images is in particular state.Above-mentioned particular state can be smile state, face the shape of camera State etc..Above-mentioned default storage condition can also be in the presence of account associated with the facial image included by above-mentioned user images Family.

Illustratively, above-mentioned default storage condition can be the people that user images clearly and in user images are reflected Image position, posture, expression are suitable for taking pictures.During trying on, above-mentioned executive agent can be opened user in camera group as a result, Qi Hou reads in image in real time, and the image acquired in the camera group includes the image of people, and acquired image clearly, people When image position, posture, expression are suitable for taking pictures, take pictures, to store certain fitting images.Optionally, above-mentioned default storage item Part can also be that the time of trying on of user is more than preset duration threshold value (such as 1 minute).Herein, above-mentioned executive agent can be with The limb action and expression of user are analyzed based on scan picture technology and intelligent algorithm, it is light, natural, excellent in user At the time of U.S., the candid photograph of photo and small video is carried out.

In some optional realization methods of the present embodiment, the first determination unit is further configured to：Based on user Image determines at least one following user information of target user：Age information, Skin Color Information, hair style information, body-shape information； Based at least one user information, at least one candidate dress ornament image is determined.It is appreciated that above-mentioned apparatus 600 can according to It is one or more in the age information at family, Skin Color Information, hair style information, body-shape information, it determines to be suitble at least the one of user The image of a candidate's dress ornament.

In some optional realization methods of the present embodiment, user images include the direct picture of user, back side image With left and right sides image；And fitting image includes the front fitting image of user, back side fitting image and left and right sides fitting Image.It is appreciated that working as the front fitting image that fitting image includes user, back side fitting image and left and right sides fitting image When, contribute to the front of the selected dress ornament image that above-mentioned target user can be clearly seen that it is chosen, the back side and the left and right sides Fitting effects.Thus, it is possible to more fully understand the effect for selecting the corresponding selected dress ornament of dress ornament image.

The device that above-described embodiment of the application provides, by acquiring unit 601 obtain target user user images and Depth information, then the first determination unit 602 be based on user images, determine at least one candidate dress ornament image, second really later Order member 603 determines that the candidate dress ornament image that user chooses is used as selected dress ornament image at least one candidate dress ornament image, It ultimately produces unit 604 and is based on depth information and selected dress ornament image, generate the fitting image of user, to enrich image life At the flexibility of mode, the flexibility of user's fitting mode is helped to improve.

In some optional realization methods of the present embodiment, user images include facial image；And above-mentioned apparatus is also Including：Second receiving unit is configured to receive the face recognition result that destination service end returns, wherein face recognition result For destination server based on Face image synthesis, for characterizing whether there is result with the associated account of target user；The Two transmission units are configured in response to determine the presence of face recognition result characterization and the associated account of target user, to target Server-side sends store instruction, so that destination service end is associated storage by least one of following with account：At least one time Select dress ornament image, at least one user information, front fitting image, back side fitting image, left and right sides fitting image.

Below with reference to Fig. 7, it illustrates the friendships of camera group and control device in the image generation system according to the application Mutual process schematic.

Image generation system in the embodiment of the present application may include control device and be taken the photograph with what control device communicated to connect As head group, wherein：Camera group is configured to obtain the user images and depth information of target user；Control device is configured User images and depth information are obtained at from camera group；Based on user images, at least one candidate dress ornament image is determined；Extremely In a few candidate dress ornament image, determine that the candidate dress ornament image that user chooses is used as selected dress ornament image；Based on depth information With selected dress ornament image, the fitting image of user is generated.

As shown in fig. 7, in step 701, camera group obtains the user images and depth information of target user.

In the present embodiment, camera group can obtain the user images and depth information of target user.Wherein, camera Group may include colour imagery shot and depth camera.Target user can be the user being located in a certain area of space.For example, In the user of the fitting room of boutique.Above-mentioned depth information can be that depth camera acquires, comprising above-mentioned target user Information of each position of body at a distance from depth camera.Above-mentioned depth camera can be the depth using infrared photo structure Camera；It can also be the depth camera based on flight time telemetry and Binocular Vision Principle.Above-mentioned user images can be figure The image of the user of piece or visual form.Above-mentioned depth information can include but is not limited at least one of following：Age information, Skin Color Information, hair style information, height information, body-shape information etc..

In a step 702, control device obtains user images and depth information from camera group.

In the present embodiment, based on the user images and depth information that camera group is got in step 701, control device User images and depth information can be obtained from above-mentioned camera group.

In step 703, control device is based on user images, determines at least one candidate dress ornament image.

In the present embodiment, the user images got based on control device in step 702, control device can determine to A few candidate dress ornament image.Wherein, above-mentioned candidate dress ornament image can meet certain in dress ornament included in the boutique The image of the dress ornament of a little conditions.Wherein, above-mentioned condition can be that style and/or size and/or price etc. are suitble to above-mentioned target to use The dress ornament at family.

As an example, above-mentioned control device can be based on the letter of the dress of above-mentioned target user included in user images It ceases (such as dress ornament style information, apparel size information, dress ornament pricing information), determines at least one candidate dress ornament image.Example Such as, if the dress ornament that user is worn in user images is " one-piece dress ", above-mentioned control device can be by institute in the boutique Including the images of all one-piece dresses be determined as candidate dress ornament image；If the dress ornament that user is worn in user images is " XX brands ", the dress ornament price of the brand is between 500 yuan to 1000 yuan, then above-mentioned control device can be by institute in the boutique There is the image of dress ornament of the price between 500 yuan to 1000 yuan to be determined as candidate dress ornament image.

In step 704, control device determines the candidate dress ornament figure that user chooses at least one candidate dress ornament image As selected dress ornament image.

In the present embodiment, at least one candidate dress ornament image determined based on control device in step 703, control are set It is standby to determine that the candidate dress ornament image that user chooses takes as selected further in above-mentioned at least one candidate dress ornament image Adorn image.

In practice, above-mentioned control device may be used various ways and determine the candidate dress ornament image that user chooses.For example, After above-mentioned at least one candidate dress ornament image display, above-mentioned control device can acquire the figure of above-mentioned user by camera Picture, to determine that user watches the candidate dress ornament image chosen attentively, wherein above-mentioned control device user can be watched attentively 3 seconds and Above candidate dress ornament image is determined as user and watches the candidate dress ornament image chosen attentively.Optionally, when above-mentioned at least one time When the color of dress ornament image being selected to be respectively red, yellow, and green, then above-mentioned control device can be by voice by above-mentioned at least one candidate The distinctive information of each of dress ornament image candidate's dress ornament image plays out, to inform user.For example, above-mentioned control device can " may I ask you by voice and like the dress ornament of red yellow or green" inform the difference of each candidate dress ornament image of user Information, then, by acquiring the return information (such as red) of user, to determine candidate dress ornament image that user chooses.

In step 705, control device is based on depth information and selected dress ornament image, generates the fitting image of user.

In the present embodiment, control device can be based on obtaining in the depth information got in step 702 and step 702 Selected dress ornament image, generate the fitting image of user.Wherein, above-mentioned fitting image can be two dimensional image, can also be three Dimension module.Image of fitting can be an image, can also be multiple images.Image of fitting can be picture, can also be to regard Frequently；Can be direct picture, back side image, the side image etc. of user.Fitting image can be half body image, whole body images, It can also be the image etc. at each visual angle.

In practice, above-mentioned control device can construct the threedimensional model of above-mentioned target user first by depth information, Then threedimensional model and above-mentioned selected dress ornament image are subjected to image co-registration, to obtain the fitting image of threedimensional model characterization.It can Choosing, above-mentioned control device can also be overlapped above-mentioned user images and selected dress ornament image, then be based on depth information pair It is superimposed obtained image to be adjusted, to obtain the fitting image of threedimensional model characterization.

In some optional realization methods of the present embodiment, above system further includes the clothes communicated to connect with control device Business end.

In some optional realization methods of the present embodiment, above-mentioned server-side is configured to obtain from control device and use Family image；Based on user images, the user information of target user is determined；User information is input to dress ornament trained in advance to recommend Model obtains at least one candidate dress ornament image, wherein dress ornament recommended models are for characterizing user information and candidate dress ornament image Correspondence；At least one candidate dress ornament image is sent to control device.Wherein, above-mentioned user information may include but not It is limited at least one of following：Age information, Skin Color Information, hair style information, height information, body-shape information etc..

As an example, above-mentioned dress ornament recommended models can obtain in accordance with the following steps：

First, above-mentioned server or other electronic equipments can obtain multiple training samples, wherein training sample includes using Family information and multiple candidate dress ornament images corresponding with the user information.

Then, above-mentioned server or other electronic equipments can utilize machine learning algorithm, include by each training sample User information train introductory die using the corresponding multiple candidate dress ornament images of the user information of input as output as input Type, to obtain dress ornament recommended models.Wherein, above-mentioned initial model can be multilayer neural network, convolutional neural networks etc..

Optionally, above-mentioned dress ornament recommended models can also be a large amount of statistics of technical staff's process, and predetermined, storage Have a large amount of user information, candidate dress ornament image and its correspondence bivariate table or database.

In some optional realization methods of the present embodiment, above-mentioned server-side is further configured to from control device Obtain depth information；Based on depth information, the threedimensional model of user is built；Threedimensional model is sent to control device.

In some optional realization methods of the present embodiment, above-mentioned control device is further configured in response to true Determine user images and meet preset mark condition, marks user images；Labeled user images are sent to server-side；Above-mentioned clothes Business end, the user images for being configured to be labeled store.Wherein, above-mentioned preset mark condition can be that technical staff is pre- The condition for marking user images first determined.For example, above-mentioned preset mark condition can be at user in user images In particular state.The state etc. that above-mentioned particular state can be smile state, face camera.

In some optional realization methods of the present embodiment, above system further includes being shown with what control device communicated to connect Show device；And aforementioned display device, it is configured to receive at least one of following from control device and show：Fit image, at least one A candidate's dress ornament image, threedimensional model.Wherein, aforementioned display device can be a liquid crystal display, can also be that multiple screens carry out The screen being spliced can also be the device shown using projecting apparatus.

In some optional realization methods of the present embodiment, above system further include with control device communicate to connect with At least one of lower control device：Client, microphone, touch display；Above system further includes being communicated to connect with control device At least one of following controlled device：Speaker, hair-dryer, aromitizer, headlamp；And control device, it is further configured to According to the control information that at least one control device is sent, at least one of control controlled device.

Wherein, above-mentioned speaker is for broadcasting audio (such as background music etc.).It is equivalent that above-mentioned hair-dryer can provide sea wind Fruit, so as to photo or video of user's shooting with sea wind effect.Above-mentioned aromitizer can provide various tastes, such as spend Perfume, herbaceous taste, seawater taste etc., it will be understood that by the blowing function of hair-dryer, the taste that aromitizer is distributed can be propagated It is rapider, user can be made to generate and be in outdoor feeling, help to build atmosphere, and then shot with various different effects The photo or video of fruit.Above-mentioned headlamp can be made of one group of colour temperature and the adjustable LED light of brightness, optionally, above-mentioned photograph Bright lamp can also be the laser lamp or other light sources to eye-safe, and above-mentioned control information can control the irradiation side of the headlamp To, brightness, colour temperature etc., multiple positions such as all around in space where which can be set to user, for user Its direction of illumination, brightness, colour temperature etc. are manually or automatically controlled, to simulate the irradiation condition under different scenes.Above-mentioned client End (such as mobile phone, tablet computer etc.) can pass through application software, small routine or webpage etc. and above-mentioned control device, service Device or above-mentioned controlled device interact, which can be provided with user interface etc., the control which sends Signal can be used for controlling one or more of above-mentioned controlled device.Above-mentioned microphone can be used for acquiring the voice of user, The microphone interacts for user and above-mentioned control device, server or above-mentioned controlled device, which obtains Audio (i.e. above-mentioned control audio) can be used for controlling one or more of above-mentioned controlled device.Above-mentioned touch display can It is interacted for user and above-mentioned control device, server or above-mentioned controlled device, the touch which detects refers to Order can be used for controlling one or more of above-mentioned controlled device.

Optionally, above-mentioned control device can also include camera group.Above-mentioned camera group is for user and above-mentioned control Equipment, server or above-mentioned controlled device interact, and the user gesture image which gets can be used for controlling One or more of above-mentioned controlled device.Above-mentioned camera group may include four (can also be other quantity) colored camera shooting Head, to shoot the photo or video of user's all around all angles；Optionally, above-mentioned camera group can also include two A (can also be other quantity) depth camera, above-mentioned depth camera can be respectively arranged at the front and back of user, to obtain The depth information of user.

In practice, above-mentioned controlled device can be arranged by holder in the fixed position in the spaces such as fitting room or removable On position；It can also be arranged in the fixed position in the spaces such as fitting room or removable by hanging, being embedded in the modes such as wall On position.

In some optional realization methods of the present embodiment, above-mentioned camera group includes at least four colour imagery shots, At least four colour imagery shots are configured to obtain the direct picture of user, back side image and left and right sides image；And fitting Image includes the front fitting image of user, back side fitting image and left and right sides fitting image.It is appreciated that when fitting image When the front fitting image including user, back side fitting image and left and right sides fitting image, contribute to above-mentioned target user clear See to Chu the front for the selected dress ornament image that it is chosen, the fitting effects at the back side and the left and right sides.Thus, it is possible to more comprehensively The effect for understanding the corresponding selected dress ornament of the selected dress ornament image.Optionally, above-mentioned camera group can also include 2 depth Camera.

In some optional realization methods of the present embodiment, above-mentioned server-side is further configured to obtain target use The facial image at family；Recognition of face is carried out to facial image, it is determined whether exist and the associated account of target user；If so, By at least one of following storage is associated with account：At least one candidate's dress ornament image, fitting image, labeled user figure Picture.It is appreciated that when there is account associated with the facial image, above-mentioned control device or server may call upon use The historical record (such as the dress ornament information of the dress ornament information of historical viewings, history purchase, dress ornament information etc. for trying on of history) at family, More accurately to determine candidate dress ornament image.

Below with reference to Fig. 8, it illustrates the computer systems 800 suitable for the control device for realizing the embodiment of the present application Structural schematic diagram.Control device shown in Fig. 8 is only an example, to the function of the embodiment of the present application and should not use model Shroud carrys out any restrictions.

As shown in figure 8, computer system 800 includes central processing unit (CPU) 801, it can be read-only according to being stored in Program in memory (ROM) 802 or be loaded into the program in random access storage device (RAM) 803 from storage section 808 and Execute various actions appropriate and processing.In RAM 803, also it is stored with system 800 and operates required various programs and data. CPU 801, ROM 802 and RAM 803 are connected with each other by bus 804.Input/output (I/O) interface 805 is also connected to always Line 804.

It is connected to I/O interfaces 805 with lower component：Importation 806 including keyboard, mouse etc.；It is penetrated including such as cathode The output par, c 807 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage section 808 including hard disk etc.； And the communications portion 809 of the network interface card including LAN card, modem etc..Communications portion 809 via such as because The network of spy's net executes communication process.Driver 810 is also according to needing to be connected to I/O interfaces 805.Detachable media 811, such as Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 810, as needed in order to be read from thereon Computer program be mounted into storage section 808 as needed.

Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium On computer program, which includes the program code for method shown in execution flow chart.In such reality It applies in example, which can be downloaded and installed by communications portion 809 from network, and/or from detachable media 811 are mounted.When the computer program is executed by central processing unit (CPU) 801, limited in execution the present processes Above-mentioned function.

It should be noted that computer-readable medium described herein can be computer-readable signal media or meter Calculation machine readable storage medium storing program for executing either the two arbitrarily combines.Computer readable storage medium for example can be --- but not Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or arbitrary above combination.Meter The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to：Electrical connection with one or more conducting wires, just It takes formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type and may be programmed read-only storage Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device, Or above-mentioned any appropriate combination.In this application, can be any include computer readable storage medium or storage journey The tangible medium of sequence, the program can be commanded the either device use or in connection of execution system, device.And at this In application, computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated, Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but unlimited In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for By instruction execution system, device either device use or program in connection.Include on computer-readable medium Program code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc. or above-mentioned Any appropriate combination.

Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction Combination realize.

Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet Include acquiring unit, the first determination unit, the second determination unit and generation unit.Wherein, the title of these units is in certain situation Under do not constitute restriction to the unit itself, for example, acquiring unit is also described as " obtaining user's figure of target user The unit of picture and depth information ".

As on the other hand, present invention also provides a kind of computer-readable medium, which can be Included in control device described in above-described embodiment；Can also be individualism, and without be incorporated the control device in. Above computer readable medium carries one or more program, when said one or multiple programs are held by the control device When row so that the control device：Obtain the user images and depth information of target user；Based on user images, at least one is determined A candidate's dress ornament image；In at least one candidate dress ornament image, determine that the candidate dress ornament image that user chooses takes as selected Adorn image；Based on depth information and selected dress ornament image, the fitting image of user is generated.

Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein Can technical characteristic replaced mutually and the technical solution that is formed.

Claims

1. a kind of image generating method, including：

Obtain the user images and depth information of target user；

Based on the user images, at least one candidate dress ornament image is determined；

In at least one candidate dress ornament image, determine that the candidate dress ornament image that user chooses is used as selected dress ornament image；

Based on the depth information and the selected dress ornament image, the fitting image of user is generated.

2. according to the method described in claim 1, wherein, the method further includes：

The depth information is sent to destination service end；

Receive the threedimensional model for the user that the destination service end group is built in the depth information；And

It is described to be based on the depth information and the selected dress ornament image, the fitting image of user is generated, including：

Based on the threedimensional model and the selected dress ornament image, the three-dimensional fitting image of user is generated.

3. it is described to be based on the user images according to the method described in claim 1, wherein, determine at least one candidate dress ornament Image, including：

The user images are sent to destination service end；

The matched at least one candidate dress ornament image of the destination service end the returns and user images is received, with determination Go out at least one candidate dress ornament image.

4. according to the method described in claim 1, wherein, the method further includes：

It is sent to target indicator at least one of following：The fitting image, at least one candidate dress ornament image.

5. according to the method described in claim 4, wherein, the target indicator is touch display；And

The method further includes：

Based on control information, at least one of following controlled device is controlled：Target speaker, target hair-dryer, target aromitizer, Target illumination lamp, wherein the control information includes at least one of following：The control signal that destination client is sent, target wheat The control audio that gram wind obtains, the touching instruction that the touch display detects, the user hand that target camera group is got Gesture image.

6. according to the method described in one of claim 1-5, wherein the method further includes：

Meet default storage condition in response to the determination user images, stores the user images.

7. method according to claim 1 or 2, wherein it is described to be based on the user images, determine at least one candidate clothes Image is adornd, including：

Based on the user images, at least one following user information of the target user is determined：Age information, colour of skin letter Breath, hair style information, body-shape information；

Based at least one of described user information, at least one candidate dress ornament image is determined.

8. according to the method described in one of claim 1-5, wherein the user images include the direct picture of user, the back side Image and left and right sides image；And

Fitting image includes the front fitting image of user, back side fitting image and left and right sides fitting image.

9. according to the method described in claim 8, wherein, the user images include facial image；And

The method further includes：

Receive the face recognition result that destination service end returns, wherein the face recognition result is based on institute for destination server State Face image synthesis, for characterizing whether there is result with the associated account of the target user；

In response to the determination face recognition result characterization presence and the associated account of the target user, sent out to destination service end Store instruction is sent, so that destination service end is associated storage by least one of following with the account：At least one time Select at least one of dress ornament image, described user information, the front fitting image, back side fitting image, the left and right two Side fitting image.

10. a kind of video generation device, including：

Acquiring unit is configured to obtain the user images and depth information of target user；

First determination unit is configured to be based on the user images, determines at least one candidate dress ornament image；

Second determination unit is configured at least one candidate dress ornament image, determines the candidate dress ornament that user chooses Image is as selected dress ornament image；

Generation unit is configured to be based on the depth information and the selected dress ornament image, generates the fitting image of user.

11. device according to claim 10, wherein described device further includes：

First transmission unit is configured to the depth information being sent to destination service end；

First receiving unit is configured to receive the three-dimensional mould for the user that the destination service end group is built in the depth information Type；And

The generation unit, is further configured to：

12. device according to claim 10, wherein first determination unit is further configured to：

The user images are sent to destination service end；

13. device according to claim 10, wherein described device further includes：

First transmission unit is configured to send to target indicator at least one of following：The fitting image, described at least one A candidate's dress ornament image.

14. device according to claim 13, wherein the target indicator is touch display；And

Described device further includes：

Control unit is configured to, based on control information, control at least one of following controlled device：Target speaker, target Hair-dryer, target aromitizer, target illumination lamp, wherein the control information includes at least one of following：Destination client is sent Control signal, target microphone obtain control audio, the touching instruction that the touch display detects, target camera The user gesture image that group is got.

15. according to the device described in one of claim 10-14, wherein described device further includes：

Storage unit is configured in response to determine that the user images meet default storage condition, stores the user images.

16. the device according to claim 10 or 11, wherein first determination unit is further configured to：

17. according to the device described in one of claim 10-14, wherein the user images include the direct picture of user, the back of the body Face image and left and right sides image；And

18. device according to claim 17, wherein the user images include facial image；And

Described device further includes：

Second receiving unit is configured to receive the face recognition result that destination service end returns, wherein the recognition of face knot Fruit be destination server based on the Face image synthesis, for characterize whether there is and the associated account of the target user Result；

Second transmission unit is configured in response to determine that the face recognition result characterization presence is associated with the target user Account, store instruction is sent to destination service end, so that destination service end is closed at least one of following with the account Connection storage：At least one of at least one candidate dress ornament image, described user information, the front fitting image, the back of the body Interview clothing image, left and right sides fitting image.

19. a kind of image generation system, the camera the system comprises control device and with control device communication connection Group, wherein：

The camera group is configured to obtain the user images and depth information of target user；

The control device is configured to obtain the user images and the depth information from the camera group；Based on institute User images are stated, determine at least one candidate dress ornament image；In at least one candidate dress ornament image, determine that user chooses Candidate dress ornament image as selecting dress ornament image；Based on the depth information and the selected dress ornament image, generate user's Fitting image.

20. system according to claim 19, wherein the system also includes the clothes communicated to connect with the control device Business end；And

The server-side is configured to obtain the user images from the control device；Based on the user images, institute is determined State the user information of target user；The user information is input to dress ornament recommended models trained in advance, is obtained at least one Candidate dress ornament image, wherein the dress ornament recommended models are used to characterize the correspondence of user information and candidate dress ornament image；It will At least one candidate dress ornament image is sent to the control device.

21. system according to claim 20, wherein

The server-side is further configured to obtain the depth information from the control device；Based on the depth information, Build the threedimensional model of user；The threedimensional model is sent to the control device.

22. system according to claim 19, wherein

The control device is further configured to meet preset mark condition in response to the determination user images, marks institute State user images；Labeled user images are sent to the server-side；

The server-side, the user images for being configured to be labeled store.

23. system according to claim 21, wherein

The system also includes the displays communicated to connect with the control device；And

The display is configured to receive at least one of following from the control device and show：It is the fitting image, described At least one candidate's dress ornament image, the threedimensional model.

24. system according to claim 23, wherein

The system also includes at least one the following control devices communicated to connect with the control device：Client, microphone, Touch display；

The system also includes at least one the following controlled devices communicated to connect with the control device：Speaker, hair-dryer, perfume (or spice) Gustatory organ, headlamp；And

The control device is further configured to the control information sent according at least one of described control device, controls institute State at least one controlled device.

25. according to the system described in one of claim 18-24, wherein

The camera group includes at least four colour imagery shots, and at least four colour imagery shot is configured to obtain user Direct picture, back side image and left and right sides image；And

The fitting image includes the front fitting image of user, back side fitting image and left and right sides fitting image.

26. according to the system described in one of claim 22-24, wherein

The server-side is further configured to obtain the facial image of the target user；To the facial image into pedestrian Face identifies, it is determined whether exists and the associated account of the target user；If so, by it is at least one of following with the account into Row associated storage：At least one candidate dress ornament image, the fitting image, labeled user images.

27. a kind of control device, including：

One or more processors；

Storage device is stored thereon with one or more programs,

When one or more of programs are executed by one or more of processors so that one or more of processors are real The now method as described in any in claim 1-9.

28. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor The now method as described in any in claim 1-9.