Summary of the invention
In order to improve video speech quality, the embodiment of the invention provides a kind of method, device and equipment of Switch Video picture.Described technical scheme is as follows:
A kind of method of Switch Video picture, described method comprises:
Carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place;
When detecting when described default handover event takes place, described first picture pick-up device is switched to second picture pick-up device.
Preferably, carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place, comprising:
When video calling begins, start first picture pick-up device and at least one second picture pick-up device, carry out in the video call process at application first picture pick-up device, according to the image of described first picture pick-up device and described at least one second picture pick-up device collection, detect whether default handover event takes place;
And/or,
Carry out in the video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of described terminal equipment is gathered, detect whether default handover event takes place.
Preferably, carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place, comprising:
Detect in the image of described first picture pick-up device and described at least one second picture pick-up device collection and whether comprise people's face;
In the image of the described first picture pick-up device collection, do not comprise people's face, and the image of described at least one second picture pick-up device collection detects described default handover event takes place when comprising people's face;
When the image of described at least one second picture pick-up device collection comprises people's face, and hold time when surpassing default duration, detect described default handover event takes place.
Preferably, carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place, comprising:
According to the voice signal that the audio frequency apparatus of described terminal equipment is gathered, obtain the source direction of described voice signal;
When the source direction of the voice signal that gets access to belongs to the described second picture pick-up device scope, detect described default handover event takes place.
Preferably, carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place, comprising:
Voice signal according to the audio frequency apparatus of described terminal equipment is gathered carries out speech recognition;
When recognizing described voice signal and the default voice that switch when consistent, detect described default handover event takes place, described default switching voice are used for the switching of triggering picture pick-up device.
A kind of device of Switch Video picture, described device comprises:
The handover event detection module is used for carrying out video call process at application first picture pick-up device, detects by gathering image and/or audio-frequency information whether default handover event takes place;
The picture pick-up device handover module is used for when detecting the described default handover event of generation described first picture pick-up device being switched to second picture pick-up device.
Preferably, described handover event detection module comprises:
The first handover event detecting unit, be used for when video calling begins, start first picture pick-up device and at least one second picture pick-up device, carry out in the video call process at application first picture pick-up device, according to the image of described first picture pick-up device and described at least one second picture pick-up device collection, detect whether default handover event takes place;
The second handover event detecting unit is used for carrying out video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of described terminal equipment is gathered, detects whether default handover event takes place.
Preferably, the described first handover event detecting unit comprises:
Whether people's face detection sub-unit comprises people's face in the image for detection of described first picture pick-up device and described at least one second picture pick-up device collection;
The first face detection sub-unit is used for not comprising people's face when the image of the described first picture pick-up device collection, and the image of described at least one second picture pick-up device collection detects described default handover event takes place when comprising people's face;
Second people's face detection sub-unit is used for comprising people's face when the image of described at least one second picture pick-up device collection, and holds time when surpassing default duration, detects described default handover event takes place.
Preferably, the described second handover event detecting unit comprises:
The sound source direction obtains subelement, is used for the voice signal according to the audio frequency apparatus collection of described terminal equipment, obtains the source direction of described voice signal;
The first sound detection subelement when being used for source direction when the voice signal that gets access to and belonging to the described second picture pick-up device scope, detects the described default handover event of generation.
Preferably, the described second handover event detecting unit comprises:
The speech recognition subelement is used for the voice signal according to the audio frequency apparatus collection of described terminal equipment, carries out speech recognition;
The second sound detection sub-unit is used for detecting the described default handover event of generation when recognizing described voice signal and the default voice that switch when consistent, and described default switching voice are for the switching of triggering picture pick-up device.
A kind of equipment comprises:
Touch display screen;
One or more processors;
Memory; With
One or more modules, described one or more module stores are in described memory and be configured to be carried out by described one or more processors, and wherein, described one or more modules have following function:
Carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place;
When detecting when described default handover event takes place, described first picture pick-up device is switched to second picture pick-up device.
The beneficial effect that the technical scheme that the embodiment of the invention provides is brought is:
The method that the embodiment of the invention provides, device and equipment, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, simplify handover operation, improved the quality of video calling.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
Fig. 1 is the flow chart of the method for a kind of Switch Video picture of providing of the embodiment of the invention.The executive agent of this inventive embodiments is terminal equipment, is applied under the scene that terminal equipment has at least two picture pick-up devices, and referring to Fig. 1, this method comprises:
101: carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place;
In the embodiment of the invention, terminal equipment has at least two picture pick-up devices, can be used for video calling, and generally speaking, the IMAQ scope of these at least two picture pick-up devices is the zone of the different directions of terminal equipment.Preferably, these at least two picture pick-up devices comprise preposition camera and rearmounted camera, are the front region of terminal equipment as the IMAQ scope of preposition camera, and the IMAQ scope of rearmounted camera is the rear area of terminal equipment.
Wherein, this first picture pick-up device is any picture pick-up device in these at least two picture pick-up devices, when video calling begins, terminal equipment can carry out video calling as this first picture pick-up device with the picture pick-up device of terminal equipment acquiescence, the picture pick-up device that uses in the time of last video calling can also being closed carries out video calling as this first picture pick-up device, as the user mobile phone is set and when beginning to carry out video calling, gives tacit consent to the preposition camera of use, perhaps the user arranges mobile phone and use the camera that uses when once video calling is closed when beginning to carry out video calling, and the embodiment of the invention is not done restriction to this.
In addition, when video calling begins, start this first picture pick-up device, other picture pick-up devices on this terminal equipment can start, and also can not start, and the embodiment of the invention is not done restriction to this.
Wherein, default handover event is used for triggering this picture pick-up device of switching, in the embodiment of the invention, when terminal equipment detects when default handover event takes place by gathering image and/or audio-frequency information, can intelligence switch picture pick-up device, make that the user can be by using different picture pick-up device Switch Video pictures to carry out video calling in video call process.
102: should be default during handover event when detecting generation, this first picture pick-up device is switched to second picture pick-up device.
Wherein, this second picture pick-up device is this first picture pick-up device any picture pick-up device in addition on this terminal equipment.
Particularly, should be default during handover event when detecting generation, terminal equipment switches to and uses this second picture pick-up device to carry out video calling by using this first picture pick-up device to carry out video calling, namely in the process of video calling, the image of this second picture pick-up device collection is sent to the object user of video calling, receive the image that this object user sends, the image of this user's transmission and the image of this second picture pick-up device collection are simultaneously displayed on the display screen of terminal equipment, at this moment, this first picture pick-up device can be closed, namely can think after video call process in the user use this second picture pick-up device to carry out video calling always, can also keep this first picture pick-up device to open, after video call process in, should be default during handover event when detecting generation, carry out picture pick-up device again and switch.
For example, put camera before use and carry out in the process of video calling, detect default handover event takes place, then preposition camera is switched to rearmounted camera, carry out video calling.
The method that the embodiment of the invention provides is carried out in the video call process at application first picture pick-up device, detects by gathering image and/or audio-frequency information whether default handover event takes place; When detecting when described default handover event takes place, described first picture pick-up device is switched to second picture pick-up device.Adopt technical scheme of the present invention, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
Alternatively, carry out in the video call process at application first picture pick-up device, detect whether default handover event takes place, can adopt at least one item of following method:
When video calling begins, start first picture pick-up device and at least one second picture pick-up device, carry out in the video call process at application first picture pick-up device, according to the image of this first picture pick-up device and this at least one second picture pick-up device collection, detect whether default handover event takes place;
Carry out in the video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, detect whether default handover event takes place.
Alternatively, carry out in the video call process at application first picture pick-up device, according to the image of this first picture pick-up device and this at least one second picture pick-up device collection, detect whether default handover event takes place, can adopt following method:
Detect in the image of this first picture pick-up device and this at least one second picture pick-up device collection and whether comprise people's face;
Do not comprise people's face in the image of this first picture pick-up device collection, and the image of this at least one second picture pick-up device collection is when comprising people's face, detecting generation should default handover event;
The image of at least one second picture pick-up device collection comprises people's face when this, and holds time when surpassing default duration, and detecting generation should default handover event.
Alternatively, carry out in the video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, detect whether default handover event takes place, can adopt following method:
According to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, obtain the source direction of this voice signal;
When the source direction of the voice signal that gets access to belonged to this second picture pick-up device scope, detecting generation should default handover event.
Alternatively, carry out in the video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, detect whether default handover event takes place, can adopt following method:
Voice signal according to the audio frequency apparatus of this terminal equipment is gathered carries out speech recognition;
When recognizing this voice signal and the default voice that switch when consistent, detecting generation should default handover event, and this is default to switch the switching that voice are used for the triggering picture pick-up device.
The method that the embodiment of the invention provides is carried out in the video call process at application first picture pick-up device, detects by gathering image and/or audio-frequency information whether default handover event takes place; When detecting when described default handover event takes place, described first picture pick-up device is switched to second picture pick-up device.Adopt technical scheme of the present invention, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
Fig. 2 is the flow chart of the method for a kind of Switch Video picture of providing of the embodiment of the invention.This inventive embodiments is terminal equipment with the executive agent, and to have two picture pick-up devices on this terminal equipment be that example describes technical scheme provided by the invention, and referring to Fig. 2, described method comprises:
201: when video calling begins, start two picture pick-up devices on the terminal equipment;
Particularly, when video calling begins, terminal equipment receives the video calling instruction, this video calling instruction triggers starts two picture pick-up devices on the terminal equipment, in video call process, can use these two picture pick-up devices to gather image, and the image of any the picture pick-up device collection in these two picture pick-up devices sent to the object user of video calling, carry out video calling.
202: carry out in the video call process using first picture pick-up device, detect in the image of this first picture pick-up device and this second picture pick-up device collection whether comprise people's face;
Wherein, this second picture pick-up device and this first picture pick-up device are different picture pick-up devices, in video call process, this first picture pick-up device and this second picture pick-up device are all gathered image, then detect respectively in the image of the image of this first picture pick-up device collection and this second picture pick-up device collection and whether comprise people's face, this testing process will be carried out always, finish until video calling, make terminal equipment to detect according to the image that collects in real time, and control the switching of this picture pick-up device according to testing result.
Those skilled in the art can know, people's face detects to refer to detect whether there is the face picture in the digital picture arbitrarily, and ignores such as building, number etc. other anything, can be used for video monitor and man-machine interaction etc.
In the embodiment of the invention, by respectively the image of this first picture pick-up device collection and the image of this second picture pick-up device collection being carried out the detection of people's face, can determine in the image pickup scope of the image pickup scope of this first picture pick-up device and this second picture pick-up device, whether have the user, and then determine whether and to switch picture pick-up device.
203: in the image of this first picture pick-up device collection, do not comprise people's face, and the image of this second picture pick-up device collection switches to this second picture pick-up device with this first picture pick-up device when comprising people's face;
Particularly, in the image of this first picture pick-up device collection, do not comprise people's face, and when the image of this second picture pick-up device collection comprises people's face, show and in the image pickup scope of this first picture pick-up device, do not have the user, in the image pickup scope of this second picture pick-up device, there is the user, switch to this second picture pick-up device with this first picture pick-up device this moment, so that this user carries out video calling.
Using terminal equipment to carry out in the process of video calling, the user can be after being fixed on assigned address with terminal equipment, arbitrarily mobile around terminal equipment, when the user is moved in the image pickup scope of this second picture pick-up device by the image pickup scope of this first picture pick-up device, terminal equipment detects in the image of this first picture pick-up device collection and does not comprise people's face, and the image of this second picture pick-up device collection comprises people's face, then this first picture pick-up device is switched to this second picture pick-up device.
By respectively the image of this first picture pick-up device collection and the image of this second picture pick-up device collection being carried out the detection of people's face, realized when the user appears in the IMAQ scope of this first picture pick-up device or this second picture pick-up device, terminal equipment switches to the picture pick-up device of current use the picture pick-up device of user's in-scope correspondence automatically, avoided the user manually to carry out the switching of picture pick-up device, realized intelligent switching picture pick-up device, be different from simultaneously and use a picture pick-up device, use at least two picture pick-up devices to carry out video calling and intelligence switching picture pick-up device, image pickup scope when having enlarged video calling makes the moving range of user when video calling increase.
204: when including people's face in the image of this first picture pick-up device and this second picture pick-up device collection, do not carry out picture pick-up device and switch;
Particularly, when including people's face in the image of this first picture pick-up device and this second picture pick-up device collection, show in the image pickup scope of the image pickup scope of this first picture pick-up device and this second picture pick-up device and all have the user, at this moment, do not carry out picture pick-up device and switch, to avoid the frequent switching of picture pick-up device.
205: when the image of this second picture pick-up device collection comprises people's face, and hold time when surpassing default duration, this first picture pick-up device is switched to this second picture pick-up device.
Alternatively, this step 205 is applied to after the step 204, namely carry out in the video call process at application first picture pick-up device, when detecting this first picture pick-up device and this second picture pick-up device and include people's face, not carrying out picture pick-up device switches, because in video call process, terminal equipment detects whether comprise people's face in the picture pick-up device in real time, therefore, in case when detecting this second picture pick-up device and beginning to comprise people's face, namely begin to add up this second picture pick-up device and comprise holding time of people's face, hold time when surpassing default duration when this, this first picture pick-up device is switched to this second picture pick-up device.
Particularly, carry out in the process of video calling at application first picture pick-up device, when the image that detects this second picture pick-up device collection comprises people's face, and holding time of people's face surpasses when presetting duration, show in the image pickup scope of this second picture pick-up device and have the user, and the interior duration of image pickup scope that this user is in this second picture pick-up device has surpassed default duration, and switch to this second picture pick-up device with this first picture pick-up device this moment.
Alternatively, terminal equipment comprises that the frame number of people's face adds up this second picture pick-up device and comprise holding time of people's face in can the image according to this second picture pick-up device collection, when the continuous frame number that comprises people's face surpasses default number, determining that this is held time surpasses default duration, or the image of presetting frame number when the interval still comprises people's face, and then definite this held time and surpassed default duration, it is multiple that this determines that the concrete grammar of holding time can also have, and do not repeat them here.
Wherein, this default duration and default number can be arranged by the developer, can also in use be arranged by the user, and the embodiment of the invention is not done restriction to this.
This step 204 and step 205 can be applied at least two users and use same terminal equipment and object user to carry out under the scene of video calling, for example user A and user B use terminal equipment and user C to carry out video calling, user A is in the image pickup scope of this first picture pick-up device, when using this first picture pick-up device, user A and user C carry out video calling, this moment is when entering in the image pickup scope of this second picture pick-up device as user B, not carrying out picture pick-up device switches, when the duration of user B in the image pickup scope of this second picture pick-up device surpasses default duration, this first picture pick-up device is switched to this second picture pick-up device, make user B and user C carry out video calling, when the duration of user B in the image pickup scope of this second picture pick-up device less than this default duration, be user B when behind the image pickup scope that enters this second picture pick-up device, leaving again, do not carry out picture pick-up device and switch.
In the embodiment of the invention, carry out in the video call process at application first picture pick-up device, this first picture pick-up device and this second picture pick-up device are all gathered image, when not carrying out the picture pick-up device switching, the image of this second picture pick-up device collection can be deleted behind of short duration buffer memory, namely can preestablish the buffer memory duration, when the buffer memory duration of the image of gathering when this second picture pick-up device surpasses the preset buffer memory duration, the image-erasing that this second picture pick-up device is gathered.
The embodiment of the invention is to be example to have two picture pick-up devices on the terminal equipment, when terminal equipment has plural picture pick-up device, detect respectively in the image of this plural picture pick-up device collection and whether comprise people's face, when not comprising people's face in the image of the picture pick-up device collection of current use, the picture pick-up device of current use can be switched to the picture pick-up device of the image correspondence of the arbitrary people's of comprising face, and when comprising people's face in the image of the picture pick-up device collection of current use, can not carry out picture pick-up device switches, can also comprise holding time of people's face according in the image of this plural picture pick-up device collection, the picture pick-up device of current use is switched to the picture pick-up device of this image correspondence of holding time the longest, and the embodiment of the invention is not done restriction to this.
The method that the embodiment of the invention provides, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
Fig. 3 is the flow chart of the method for a kind of Switch Video picture of providing of the embodiment of the invention.This inventive embodiments is terminal equipment with the executive agent, and to have two picture pick-up devices on this terminal equipment be that example describes technical scheme provided by the invention, and referring to Fig. 3, described method comprises:
301: carry out in the video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, obtain the source direction of this voice signal;
Those skilled in the art can know that terminal equipment can pass through the audio frequency apparatus collected sound signal, according to the time difference of the different sensors on this voice signal incoming terminal equipment, obtains the source direction of this voice signal.
Need to prove that when determining whether by audio-frequency information to need to switch picture pick-up device, can not start second camera in advance and gather image, the embodiment of the invention is not done restriction to this.
302: when the source direction of the voice signal that gets access to belongs to this second picture pick-up device scope, this first picture pick-up device is switched to this second picture pick-up device;
In the embodiment of the invention, can determine user residing position in video call process according to the source direction of this voice signal, can determine that namely the user is in this first picture pick-up device scope or is in this second picture pick-up device scope, can determine whether that according to the residing position of user needs carry out picture pick-up device and switch.
Wherein, this second picture pick-up device scope refers to terminal equipment in the zone of this second picture pick-up device direction, is the front region of mobile phone as the scope of the preposition camera of mobile phone.
When the source direction of the voice signal that gets access to belongs to this second picture pick-up device scope, show that the user is in the image pickup scope of this second picture pick-up device, switch to this second picture pick-up device with this first picture pick-up device this moment, namely starts this second picture pick-up device and gather image, carries out video calling.
303: when the source direction of the voice signal that gets access to belongs to this first picture pick-up device scope, do not carry out picture pick-up device and switch;
304: when the source direction of the voice signal that gets access to belongs to the scope junction of this first picture pick-up device and this second picture pick-up device, do not carry out picture pick-up device and switch.
The scope junction that the source direction of this voice signal belongs to this first picture pick-up device and this second picture pick-up device refers to that the source direction of this voice signal neither belongs to terminal equipment in the zone of the direction of this first image pickup scope equipment, do not belong to terminal equipment in the zone of the direction of this second picture pick-up device yet, perhaps the source direction of this voice signal belongs to the handing-over zone in above-mentioned two zones, belongs to the scope junction of preposition camera and the rearmounted camera of mobile phone as the source direction at the voice signal of mobile phone side regions.
Fig. 4 is the voice signal source direction schematic diagram that a kind of terminal equipment that the embodiment of the invention provides is gathered, as shown in Figure 4, terminal equipment has two picture pick-up devices, be respectively first picture pick-up device and second picture pick-up device, this first picture pick-up device scope is the lower zone of terminal equipment among Fig. 4, this second picture pick-up device scope is the upper area of terminal equipment among Fig. 4, therefore, the source direction of sound source 1 belongs to this first picture pick-up device scope, the source direction of sound source 2 belongs to this second picture pick-up device scope, and the source direction of sound source 3 belongs to the scope junction of this first picture pick-up device and this second picture pick-up device.
The embodiment of the invention can be applicable at least two users and uses same terminal equipment and object user to carry out under the scene of video calling simultaneously, for example, user A and user B use terminal equipment and user C to carry out video calling, user A is in the image pickup scope of this first picture pick-up device, user B is in the image pickup scope of this second picture pick-up device, when user A sounds, the source direction of the voice signal that gets access to belongs to this first picture pick-up device scope, not carrying out picture pick-up device switches, user A and user C carry out video calling, when user B sounds, the source direction of the voice signal that gets access to belongs to this second picture pick-up device scope, at this moment, this first picture pick-up device is switched to this second picture pick-up device, make user B to carry out video calling with user C, by obtaining the source direction of voice signal, the control picture pick-up device switches, and makes at least two usefulness can carry out video calling with the object user per family.
The embodiment of the invention is to be example to have two picture pick-up devices on the terminal equipment, when terminal equipment has plural picture pick-up device, obtain the source direction of voice signal, the picture pick-up device of current use is switched to the picture pick-up device of this source direction correspondence, realized the switching between the plural picture pick-up device on the terminal equipment in the video call process.
In embodiments of the present invention, when whether terminal equipment can comprise people's face in the image that detects this first picture pick-up device and this second picture pick-up device collection, obtain the source direction of voice signal, when including people's face in the image of this first picture pick-up device and this second picture pick-up device collection, when namely at least two users are in the image pickup scope of the image pickup scope of this first picture pick-up device and this second picture pick-up device respectively, source direction according to voice signal, the switching of control picture pick-up device, keep the picture pick-up device of current use to be the picture pick-up device of the source direction correspondence of this voice signal, realize that at least two users and object user carry out video calling, when the user of the image pickup scope that is in arbitrary picture pick-up device leaves, detect in the image of this arbitrary picture pick-up device collection and do not comprise people's face, no longer carry out picture pick-up device this moment and switch.
The method that the embodiment of the invention provides, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
Fig. 5 is the flow chart of the method for a kind of Switch Video picture of providing of the embodiment of the invention.This inventive embodiments is terminal equipment with the executive agent, and to have two picture pick-up devices on this terminal equipment be that example describes technical scheme provided by the invention, and referring to Fig. 5, described method comprises:
501: when video calling begins, start two picture pick-up devices on the terminal equipment;
The embodiment of the invention is with when video calling begins, and two picture pick-up devices that start on the terminal equipment are that example describes.
502: carry out in the video call process at application first picture pick-up device, the voice signal according to the audio frequency apparatus of this terminal equipment is gathered carries out speech recognition;
Those skilled in the art can know that speech recognition refers to by identification and understanding process voice signal be changed into corresponding text or order, realizes various function according to the text or order.
Whether carry out in the video call process at application first picture pick-up device, terminal equipment is gathered user's voice signal by audio frequency apparatus, and this voice signal is carried out speech recognition, serve as the voice signal that the indication picture pick-up device switches to judge this voice signal.
503: when recognizing this voice signal and the default voice that switch when consistent, this first picture pick-up device is switched to this second picture pick-up device.
Should default switch the switching that voice are used for triggering picture pick-up device, when recognizing this voice signal and the default voice that switch when consistent, triggering switches to this second picture pick-up device to the switching of picture pick-up device with this first picture pick-up device.Should defaultly switch voice can be arranged by the developer, also can in use be arranged by the user.
For example, should defaultly switch voice and can be " switching camera ", when the user says " switching camera ", terminal equipment is gathered user's voice signal, the voice signal " switching camera " that recognizes the user is consistent with default switching voice, at this moment, this first picture pick-up device is switched to this second picture pick-up device.
In the embodiment of the invention, by the speech recognition to voice signal, make the user can realize the switching of picture pick-up device by assigning sound instruction, and need not manually to carry out the switching of picture pick-up device, operate easier.
The embodiment of the invention is to be example to have two picture pick-up devices on the terminal equipment, when terminal equipment has plural picture pick-up device, obtain user's voice signal, when this voice signal and predefined first switches voice when consistent, the picture pick-up device of current use is switched to the picture pick-up device of this first switching voice correspondence, by user's sound instruction, realize the switching between the plural picture pick-up device on the terminal equipment.
Wherein, the mapping relations between these a plurality of default switching voice and arbitrary default switching voice and this plural picture pick-up device can be arranged by the developer, also can in use be arranged by the user.
For example, the camera that " switching to preposition camera " instruction can trigger current use switches to preposition camera, and " switching to the side camera " instruction can trigger the camera that the camera of current use is switched to the side.
The method that the embodiment of the invention provides, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
Fig. 6 is the apparatus structure schematic diagram of a kind of Switch Video picture of providing of the embodiment of the invention.Referring to Fig. 6, described device comprises:
Handover event detection module 61 is used for carrying out video call process at application first picture pick-up device, detects by gathering image and/or audio-frequency information whether default handover event takes place;
Picture pick-up device handover module 62 is used for when detecting generation and should preset handover event this first picture pick-up device being switched to second picture pick-up device.
Alternatively, this handover event detection module 61 comprises:
The first handover event detecting unit, be used for when video calling begins, start first picture pick-up device and at least one second picture pick-up device, carry out in the video call process at application first picture pick-up device, according to the image of this first picture pick-up device and this at least one second picture pick-up device collection, detect whether default handover event takes place;
The second handover event detecting unit is used for carrying out video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, detects whether default handover event takes place.
Alternatively, this first handover event detecting unit comprises:
Whether people's face detection sub-unit comprises people's face in the image for detection of this first picture pick-up device and this at least one second picture pick-up device collection;
The first face detection sub-unit is used for not comprising people's face when the image of this first picture pick-up device collection, and the image of this at least one second picture pick-up device collection is when comprising people's face, and detecting generation should default handover event;
Second people's face detection sub-unit is used for comprising people's face when the image of this at least one second picture pick-up device collection, and holds time when surpassing default duration, and detecting generation should default handover event.
Alternatively, this second handover event detecting unit comprises:
The sound source direction obtains subelement, is used for the voice signal according to the audio frequency apparatus collection of this terminal equipment, obtains the source direction of this voice signal;
The first sound detection subelement is used for when the source direction of the voice signal that gets access to belongs to this second picture pick-up device scope, and detecting generation should default handover event.
Alternatively, this second handover event detecting unit comprises:
The speech recognition subelement is used for the voice signal according to the audio frequency apparatus collection of this terminal equipment, carries out speech recognition;
The second sound detection sub-unit is used for when recognizing this voice signal and the default voice that switch when consistent, and detecting generation should default handover event, and these default switching voice are for the switching of triggering picture pick-up device.
The device that the embodiment of the invention provides, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
Need to prove: the Switch Video picture that above-described embodiment provides device the Switch Video picture the time, only the division with above-mentioned each functional module is illustrated, in the practical application, can as required the above-mentioned functions distribution be finished by different functional modules, the internal structure of the equipment of being about to is divided into different functional modules, to finish all or part of function described above.In addition, the Switch Video picture that above-described embodiment provides device and the Switch Video picture method embodiment belong to same design, its specific implementation process sees method embodiment for details, repeats no more here.
The embodiment of the invention also provides a kind of equipment, comprising:
Touch display screen;
One or more processors;
Memory; With
One or more modules, these one or more module stores are in this memory and be configured to be carried out by these one or more processors, and wherein, these one or more modules have following function:
Carry out in the video call process at application first picture pick-up device, detect by gathering image and/or audio-frequency information whether default handover event takes place;
Should be default during handover event when detecting generation, this first picture pick-up device is switched to second picture pick-up device.
Alternatively, these one or more modules are used for when video calling begins, start first picture pick-up device and at least one second picture pick-up device, carry out in the video call process at application first picture pick-up device, according to the image of this first picture pick-up device and this at least one second picture pick-up device collection, detect whether default handover event takes place; And/or, carry out in the video call process at application first picture pick-up device, according to the voice signal that the audio frequency apparatus of this terminal equipment is gathered, detect whether default handover event takes place.
Alternatively, whether these one or more modules also comprise people's face in the image for detection of this at least one first picture pick-up device and this second picture pick-up device collection; Do not comprise people's face in the image of this first picture pick-up device collection, and the image of this at least one second picture pick-up device collection is when comprising people's face, detecting generation should default handover event; The image of at least one second picture pick-up device collection comprises people's face when this, and holds time when surpassing default duration, and detecting generation should default handover event.
Alternatively, these one or more modules also are used for the voice signal according to the audio frequency apparatus collection of this terminal equipment, obtain the source direction of this voice signal; When the source direction of the voice signal that gets access to belonged to this second picture pick-up device scope, detecting generation should default handover event.
Alternatively, these one or more modules also are used for the voice signal according to the audio frequency apparatus collection of this terminal equipment, carry out speech recognition; When recognizing this voice signal and the default voice that switch when consistent, detecting generation should default handover event, and this is default to switch the switching that voice are used for the triggering picture pick-up device.
The equipment that the embodiment of the invention provides, by when the video call process, detect by gathering image and/or audio-frequency information whether default handover event takes place, when detecting when default handover event takes place, first picture pick-up device of current use is switched to this first picture pick-up device any picture pick-up device in addition, realized that the intelligence of picture pick-up device is switched on the terminal equipment, image pickup scope when having enlarged video calling, simultaneously do not need the user manually to carry out the switching of video pictures, improved the quality of video calling.
The all or part of step that one of ordinary skill in the art will appreciate that realization above-described embodiment can be finished by hardware, also can instruct relevant hardware to finish by program, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium of mentioning can be read-only memory, disk or CD etc.
The above only is preferred embodiment of the present invention, and is in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of doing, is equal to replacement, improvement etc., all should be included within protection scope of the present invention.