CN110248450B

CN110248450B - Method and device for controlling light by combining people

Info

Publication number: CN110248450B
Application number: CN201910363478.3A
Authority: CN
Inventors: 傅峰峰
Original assignee: Guangzhou Fugang Life Intelligent Technology Co Ltd
Current assignee: Guangzhou Fugang Life Intelligent Technology Co Ltd
Priority date: 2019-04-30
Filing date: 2019-04-30
Publication date: 2021-11-12
Anticipated expiration: 2039-04-30
Also published as: CN110248450A

Abstract

The invention discloses a method for controlling light by combining people, which comprises the following steps: an acquisition step: acquiring current image information shot by a camera device, wherein the image information comprises a face image of a user; and (3) comparison: comparing the user face image with a light prediction model to obtain light parameters required by a corresponding user, wherein the light parameters comprise light brightness and light angles; the control steps are as follows: and controlling each indoor lamp to adjust to the corresponding lamp brightness and lamp angle according to the lamp parameters so as to project the lamp brightness and the lamp angle to the user. The invention also provides a device, electronic equipment and a storage medium for controlling the light by combining the person. According to the method for controlling the light by combining the characters, the optimal light projection mode required by the currently illuminated characters is obtained by obtaining the character images and comparing the character images with the prediction model, and the lamps are controlled to the corresponding parameters to project the light to the characters, so that a user can have a better mental appearance when being photographed.

Description

Method and device for controlling light by combining people

Technical Field

The invention relates to the technical field of light, in particular to a method and a device for controlling light by combining people.

Background

Most of the current indoor lamplight is completely arranged in advance; from the colour of light, the angle all aspects of light have all been fixed, and when this kind of light was fixed, also can make the user have the way to adjust according to actual scene, can not reach the light arrangement of higher photographic grade. For a large shopping mall or a hotel, when an event needs to be held, the effect of the light can influence the shooting result, so that the effect at the later stage of the event is influenced. Therefore, how to design a method capable of combining different characters to perform different light arrangements becomes a technical problem to be solved urgently by the technical personnel in the field.

Disclosure of Invention

In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a method for controlling light in combination with a character, which can solve the technical problem of character light beautification.

The invention also aims to provide a device for controlling the light by combining with a person, which can solve the technical problem of beautifying the light of the person.

The invention also aims to provide electronic equipment which can solve the technical problem of character light beautification.

It is a fourth object of the present invention to provide a computer-readable storage medium that can solve the technical problem of character light beautification.

One of the purposes of the invention is realized by adopting the following technical scheme:

a method for controlling light in combination with a person comprises the following steps:

an acquisition step: acquiring current image information shot by a camera device, wherein the image information comprises a face image of a user;

and (3) comparison: comparing the user face image with a light prediction model to obtain light parameters required by a corresponding user, wherein the light parameters comprise light brightness and light angles;

the control steps are as follows: and controlling each indoor lamp to adjust to the corresponding lamp brightness and lamp angle according to the lamp parameters so as to project the lamp brightness and the lamp angle to the user.

Further, the light prediction model is mainly constructed by the following steps:

a receiving step: receiving a current face picture shot by a user and a corresponding lighting parameter;

training: the method comprises the steps of training a current face picture and a light parameter corresponding to the current face picture through a neural network algorithm to obtain a light prediction model, wherein the input end of the light prediction model is picture information, and the output end of the light prediction model is the light parameter.

Further, the light parameters also include the color of the light.

Further, in the receiving step, receiving image style information input by a user;

training: the method comprises the steps of training a current face picture, image style information and corresponding lighting parameters through a neural network algorithm to obtain a lighting prediction model, wherein the input end of the lighting prediction model is the picture information and the image style information, and the output end of the lighting prediction model is the lighting parameters.

Further, before the step of comparing, a step of demand analysis is also included: receiving demand information of a user; analyzing the demand information to obtain corresponding image style information;

and (3) comparison: and comparing the facial image and the image style information of the user with the lamplight prediction model to obtain lamplight parameters required by the corresponding user, wherein the lamplight parameters comprise lamplight brightness, lamplight angles and lamplight colors.

Further, the neural network algorithm adopts a linear regression algorithm.

Further, the light angle comprises front light, front side light, side backlight, backlight and top light; the light colors comprise cool tones and warm tones, the warm tones comprise red, orange and yellow, and the cool tones comprise blue, green and purple.

The second purpose of the invention is realized by adopting the following technical scheme:

an apparatus for controlling light in conjunction with a person, comprising the following modules:

an acquisition module: the system comprises a camera, a display device and a display device, wherein the camera is used for acquiring current image information shot by the camera, and the image information comprises a face image of a user;

a comparison module: the system comprises a light prediction model, a user face image and a user face image, wherein the light prediction model is used for comparing the user face image with the light prediction model to obtain light parameters required by a corresponding user, and the light parameters comprise light brightness and light angles;

a control module: and the controller is used for controlling each indoor light to be adjusted to the corresponding light brightness and light angle according to the light parameters so as to project the light to the user.

The third purpose of the invention is realized by adopting the following technical scheme:

an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement a method for controlling light in conjunction with a person according to any one of the objects of the present invention.

The fourth purpose of the invention is realized by adopting the following technical scheme:

a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of lighting control in combination with a person according to any one of the objects of the invention.

Compared with the prior art, the invention has the beneficial effects that:

according to the method for controlling the light by combining the characters, the optimal light projection mode required by the currently illuminated characters is obtained by obtaining the character images and comparing the character images with the prediction model, and the lamps are controlled to the corresponding parameters to project the light to the characters, so that a user can have a better mental appearance when being photographed.

Drawings

Fig. 1 is a flowchart of a method for controlling lighting in conjunction with a person according to a first embodiment;

fig. 2 is a block diagram of a device for controlling lighting in conjunction with a person according to a second embodiment.

Detailed Description

The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.

Example one

There are several aspects that can affect the final shooting effect during the shooting process: one is the image quality of the character, and the other is the wearing effect of the character; still another is art relating to light. At present, a professional photographer shooting in an indoor booth takes a picture of light, which is very exquisite, so that the professional photographer can shoot a more distinctive and artistic image; however, in the actual process, the time for playing with the light is not so long, and especially when the activities are held in a hotel or a shopping mall, the whole activity program is complex, so that the time cannot be reserved independently for lighting the corresponding photographer; therefore, a good light effect is not supplemented in the shooting process; the light also has a very important auxiliary function for the figure shaping.

As shown in fig. 1, the present embodiment provides a method for controlling light in combination with a person, including the following steps:

s1: acquiring current image information shot by a camera device, wherein the image information comprises a face image of a user; the face of the person can be most reflected in the state and the appearance of the person, so that the face image information of the person needs to be acquired first in the embodiment, and only after the face image is acquired, the light corresponding to the face image required by the user can be further analyzed in the mode required by the user, so that the advantages of the person can be further reflected. Various emotions of the user can also be displayed through the facial image, such as joy, surprise and the like, and different facial expressions also need different light effects to be matched to reflect the current state of the user.

But besides the facial image information of the user, the overall standing posture of the user and the background where the user is located can be acquired; the effect of obtaining a better image needs to take into account that the overall information entered into the camera makes the content of the analysis more comprehensive.

S2: comparing the user face image with the light prediction model to obtain light parameters required by the corresponding user, wherein the light parameters comprise light brightness, light angle and light color; the accuracy of model can make the accuracy of later stage judgement improve, and when the model that obtains was enough accurate, the light effect and the shooting effect that obtain are also better.

The light prediction model is mainly constructed by the following steps:

a receiving step: receiving a current face picture shot by a user and a corresponding lighting parameter; the current face picture shot here is a carefully selected picture, all materials are provided by professional photographers, the professional photographers shoot images in a shed, and then corresponding lighting parameters are recorded, the materials are all obtained through fine selection, and not only are images obtained randomly, the more accurate the obtained data are, the more detailed the obtained model is.

Training: the method comprises the steps of training a current face picture and a light parameter corresponding to the current face picture through a neural network algorithm to obtain a light prediction model, wherein the input end of the light prediction model is picture information, and the output end of the light prediction model is the light parameter. The neural network algorithm adopts a linear regression algorithm. The different models differ in their ability to fit or describe the data. Our goal is ultimately to find a linear regression model that describes the relationship between data most accurately. A cost function is then needed. The cost function is used to describe the difference between the linear regression model and the formal data. If there is no difference at all, it indicates that the linear regression model completely describes the relationship before the data. If a best-fit linear regression model needs to be found, the corresponding cost function needs to be minimized. The linear regression algorithm has high modeling speed, does not need complex calculation, and still has high running speed under the condition of large data volume. And it can give an understanding and interpretation of each variable in terms of coefficients, and is also sensitive to outliers. A linear regression algorithm is used in this implementation to operate.

In addition to the above manner, the method further comprises receiving image style information input by a user; the user has a favorite preference, so that one parameter is set in an overlapping manner to analyze from another dimension when starting setting. The image style information can be specifically split into the brightness of lamplight and the number of adopted lamps; training is performed by these two factors. In the present embodiment, the detailed description is made with respect to the layout of the lights and the number of the lights.

The lamp can be arranged in a single lamp or in a double lamp or in a triple lamp, and the single lamp arrangement can be realized by only adjusting the corresponding angle, brightness and color. The light distribution mode of the double lamps comprises the matching of a front lamp 2 and a rear lamp 2, the matching of a left lamp 2 and a right lamp 2 and the matching of an upper lamp 2 and a lower lamp 2; the photo shot by the double-lamp light distribution mode emphasizes personality, and has rich tone and strong stereoscopic impression.

A three lamp configuration requires three forms of light fixtures, primary, secondary and background light. The indoor photography needs to be assisted by combining light besides natural light, and the light photography skills are mainly reflected in light distribution. The effect of taking photos is directly influenced by the quality of the light distribution. The lighting is preferably provided with a main light, an auxiliary light and a background light. Main light the main light is the main illumination source for lamplight photography and is used to illuminate the main body of the scenery and the main parts of the scenery. If the person is shot, the function of the method is to make the shot person have proper brightness and the function of face modeling is to draw the figure shape, depict the figure shape and the internal movement, reflect the skin color texture and make up the face shape defect. The main light is a light source with strong directivity, and is generally placed at a certain distance in the front direction and at an angle of 45 degrees with the optical axis of the lens, so that the object can obtain proper brightness. The main light can be adjusted, for example, the reflector can be moved up and down, left and right, and back and forth, so that five planes (forehead, left and right cheeks, nose bridge and chin) of the face of the shot person generate soft strong light parts, and the soft strong light parts protrude out of the image, are bright in outline and are rich in round feeling. When the direction of the lamp is adjusted later, more is also adjusted for the parameters of the main light.

The auxiliary light is used for illuminating the shadow part of the shot object to supplement the deficiency of the main light illumination, so that the shot object obtains proper contrast, enriches the shade gradation and harmonious light and shade gradation. The auxiliary light is soft in light and large in illumination area, and is generally placed near the camera, and the height of the auxiliary light is the same as that of the lens on the other side of the main light, so that the auxiliary light can generate uniform illumination on a shooting plane. When the human image is shot, the background light can be as high as the scapula of the shot person and slightly inclines upwards, so that the soft lighting part on the background is positioned between the ears and the shoulders of the shot person. In addition, the background light can be projected to the camera from the back of the shot person, and a bright contour light is formed around the head of the shot person, so that the main body is highlighted, and the hierarchy and the stereoscopic impression are increased. When the lamp is adjusted, the angle, brightness and color of the main light can be mainly adjusted, and other lights are auxiliary lights.

The light is used for shooting the portrait, and the position, the height and the strength of the light can be adjusted to make up for the natural defects of the face of a person, so that the best effect of beauty is obtained. If the face is enlarged, the main light can be placed at a position which forms an angle of 45 degrees with the camera, the main light lamp is downwards projected from high to low, the light-dark ratio can be slightly larger, and the effect of being thinner than the original face of the person can be achieved by reducing the brightness of the auxiliary light through the light distribution method.

When a face with a thin face or high cheekbones or with wrinkles and a deep eye socket is shot, the main light lamp is placed at an angle of less than 45 degrees with the camera, and the position of the main light lamp is lower, so that the light ratio is reduced; when the face shapes with different cheek sizes are shot, the main light can be placed on the side with the small cheek to receive the light, the side with the large cheek generates certain shadows and looks thin, and a small illuminating lamp can be additionally arranged on the side with the small cheek to illuminate the part with the thin cheek;

shooting the concave nose bridge, and illuminating the concave part of the nose with light rays to ensure that the nose bridge is not too concave; the nose is too convex or has an arch back, the nose can be treated in the shadow, and the illumination is slightly dark; the nose shape is slightly inclined, if the nose shape is inclined to the right, the nose shape can be illuminated from a slightly left direction, so that a more prominent bright spot is formed at a slightly left position below the nose by utilizing the reflection effect of light rays, and the image of the inclined nose shape is also corrected. By optically compensating for some imperfections of the person himself, a better shot material is provided.

Training: the method comprises the steps of training a current face picture, image style information and corresponding lighting parameters through a neural network algorithm to obtain a lighting prediction model, wherein the input end of the lighting prediction model is the picture information and the image style information, and the output end of the lighting prediction model is the lighting parameters. In this embodiment, the lighting angle includes two angles, one is an angle relative to the person to be photographed, and the other is a pitch angle; the combination of the two can have the following concrete expression forms: front light, front side light, side backlight, backlight and top light; the light colors comprise cool tones and warm tones, the warm tones comprise red, orange and yellow, and the cool tones comprise blue, green and purple.

Different angles can present different character faces, and the front light is also called as front light, which means the light with the same projection direction and shooting direction. When the light is in the same direction, the shot object is uniformly illuminated, the shadow of the shot object is shielded by the shot object, and the tone is softer. Can shoot the texture of the surface of the shot object and bring better color restoration. However, it is disadvantageous in that the effect of atmospheric perspective is exhibited on the screen, and the effect of spatial stereoscopic perception is also poor.

The front side light is also called oblique light, the direction of the light projection forms a horizontal angle of about 45 degrees with the object and the camera, and the illumination appears at nine and ten am and three and four pm. The light is more in line with the visual habits of people in daily life. The projection of the illuminated object falls on the oblique side, and the illuminated object has obvious light and shade difference and can better express the texture of the shot object. 45-degree side light can generate light and shadow arrangement, so that the shot object has rich shadow tones, the depth is highlighted, and the effect of stereoscopic impression is generated. In particular, the texture of the surface structure can be displayed finely.

Sidelight, i.e., light from the left or right side of the subject, is at a horizontal angle of about 90 degrees with respect to the subject and the camera. This light can produce a significant contrast. The shadow is elongated and has expressive force, the surface structure is very obvious, and each tiny bulge generates an obvious shadow. The adoption of side light photography can result in stronger modeling effect. In photography of a person, a specific emotion of the person is often expressed by sidelight. Side lights are sometimes used as decorative lights to highlight a certain part or detail of the picture.

Side backlight: illumination rays from obliquely forward (left-front or right-front) of the camera, which form an angle of about 120 ° to 150 ° with the optical axis of the lens, are called side backlight. By adopting side backlighting, the light receiving surface of the face and the body of the shot person only occupies a small part, and the shadow surface occupies a large part, so the tone is heavier. By adopting the lighting method, the stereoscopic impression of the shot is better than that of the forward lighting, but the stereoscopic impression of the part covered by the shadow in the image is still weaker.

The back light is a condition in which the subject is just between the light source and the camera, and this condition is liable to cause insufficient exposure of the subject. Generally, a photographer should avoid shooting an object under a backlight condition as much as possible, but a special effect caused by the backlight is not lost as a skill of art photography in some cases.

The ground light is also the silhouette photography, which is to highlight the main body to represent the outline posture of the object and the outline of the object, the object to be photographed by the silhouette photography may be a person, an object or a certain scene, and the object itself often only has a black outline and does not contain any details. In this embodiment, the form of the ground light is not generally adopted, and since the general activities are not the photographic art, such a representation form is not required, so that the light in the direction can be removed when the light angle is set.

S3: and controlling each indoor lamp to adjust to the corresponding lamp brightness, lamp angle and lamp color according to the lamp parameters so as to project the lamp brightness, lamp angle and lamp color to the user. Each lamp can be a single lamp arranged on one angle adjusting device or a lamp group, so that when angle control is carried out, only the lamps at corresponding angles are controlled to be on or off.

In addition to the above, there are other ways, before step S3, there is a requirement analysis step: receiving demand information of a user; analyzing the demand information to obtain corresponding image style information; and comparing the facial image and the image style information of the user with the lamplight prediction model to obtain lamplight parameters required by the corresponding user, wherein the lamplight parameters comprise lamplight brightness, lamplight angles and lamplight colors.

For example, when a commercial establishment is in a mall, there is typically a fixed venue for stage construction, at which time the lights are also arranged and the relative distance of the photographers around the stage with respect to the persons in the stage is determined. When a shot person gets on the stage, the camera acquires the facial image information of the person, and then better shooting effect can be obtained by comparing the facial image information and the lighting irradiation mode; then adjust lamps and lanterns to corresponding angle, luminance and colour, then project light to the shot person department for it is whole to appear more young and more energetic under the light projection.

In the method for controlling the light by combining the character in the embodiment, the image of the character is obtained and compared with the prediction model to obtain the optimal light projection mode required by the character irradiated by the light at present, and the lamp is controlled to the corresponding parameters to project the light of the character, so that a user can present a better mental appearance when being photographed or watched.

Example two

As shown in fig. 2, the embodiment provides a device for controlling light in combination with a person, which includes the following modules:

a comparison module: the system comprises a light prediction model, a user face image and a user face image, wherein the light prediction model is used for comparing the user face image with the light prediction model to obtain light parameters required by a corresponding user, and the light parameters comprise light brightness, light angles and light colors; the light prediction model is mainly constructed by the following steps:

training: the method comprises the steps of training a current face picture and a light parameter corresponding to the current face picture through a neural network algorithm to obtain a light prediction model, wherein the input end of the light prediction model is picture information, and the output end of the light prediction model is the light parameter. The neural network algorithm adopts a linear regression algorithm.

EXAMPLE III

The third embodiment discloses an electronic device, which comprises a processor, a memory and a program, wherein the processor and the memory can adopt one or more programs, the program is stored in the memory and is configured to be executed by the processor, and when the processor executes the program, the method for controlling the light in combination with the character in the first embodiment is realized. The electronic device may be a series of electronic devices such as a mobile phone, a computer, a tablet computer, and the like.

Example four

The fourth embodiment discloses a computer-readable storage medium, which is used for storing a program, and when the program is executed by a processor, the method for controlling the light by combining the character in the first embodiment is realized.

Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the method provided by any embodiment of the present invention.

From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes instructions for enabling an electronic device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.

It should be noted that, in the embodiment of the content-based update notification apparatus, the included units and modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.

The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.

Claims

1. A method for controlling light by combining people is characterized by comprising the following steps:

an acquisition step: acquiring current image information shot by a camera device, wherein the image information comprises a face image of a user; the facial image of the user is used for displaying various emotions of the user, and different facial expressions are matched with different lighting effects to reflect the current state of the user;

the control steps are as follows: and controlling each indoor lamp to adjust to the corresponding lamp brightness and lamp angle according to the lamp parameters so as to project the lamp brightness and the lamp angle to the user, so that the user can present better mental appearance when being photographed.

2. The method of claim 1, wherein the light prediction model is constructed by the steps of:

3. A method of controlling lighting in conjunction with a character as claimed in claim 1 or claim 2, wherein said lighting parameters further include lighting color, and wherein said number of light fixtures in said controlling step is one or more.

4. The method of claim 2, wherein the receiving step further comprises receiving image style information input by a user;

5. The method of claim 4, further comprising a requirement analysis step before the comparison step: receiving demand information of a user; analyzing the demand information to obtain corresponding image style information;

6. The method as claimed in claim 2, wherein the neural network algorithm is a linear regression algorithm.

7. The method of claim 3, wherein the lighting angles comprise front lighting, side backlighting, and backlighting; the light colors comprise cool tones and warm tones, the warm tones comprise red, orange and yellow, and the cool tones comprise blue, green and purple.

8. A device for controlling light in combination with a person, which is characterized by executing the method for controlling light in combination with the person according to any one of claims 1-7, and comprises the following modules:

a control module: the intelligent lighting control system is used for controlling indoor lighting to be adjusted to corresponding lighting brightness and lighting angle according to the lighting parameters so as to be projected to a user, so that the user can present better mental appearance when being photographed.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a method of controlling light in conjunction with a person according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements a method of lighting control in conjunction with a character as claimed in any one of claims 1 to 7.