CN112969047B - Control method and device of smart watch, smart watch and storage medium - Google Patents
Control method and device of smart watch, smart watch and storage medium Download PDFInfo
- Publication number
- CN112969047B CN112969047B CN202110198958.6A CN202110198958A CN112969047B CN 112969047 B CN112969047 B CN 112969047B CN 202110198958 A CN202110198958 A CN 202110198958A CN 112969047 B CN112969047 B CN 112969047B
- Authority
- CN
- China
- Prior art keywords
- camera
- distance
- face
- smart watch
- video image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
- H04N7/142—Constructional details of the terminal equipment, e.g. arrangements of the camera and the display
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The application discloses a control method of a smart watch, comprising the following steps: when the fact that the intelligent watch starts a video call function is detected, acquiring a video image acquired by the intelligent watch; detecting whether the distance between the face feature point in the video image and the image center point is smaller than a preset distance or not; if not, rotating the camera of the intelligent watch to enable the distance to be smaller than the preset distance. The application also discloses a control device of the intelligent watch, the intelligent watch and a computer readable storage medium. The method and the device reduce the situation that the video call quality is influenced due to the fact that the portrait offset is generated in the video shot by the intelligent watch.
Description
Technical Field
The application relates to the technical field of intelligent wearable equipment, in particular to a control method of an intelligent watch, a control device of the intelligent watch, the intelligent watch and a computer readable storage medium.
Background
Along with the development of science and technology, the function of intelligent wrist-watch is more and more powerful to begin to be equipped with the camera, the user can carry out video voice call through the camera of intelligent wrist-watch. However, since the smart watch is generally worn on the hand of the user and is prone to shake along with the swing of the arm, when the user uses the smart watch to perform a video call, if the smart watch shakes, the image of the user may shift or be blurred, and thus the quality of the video call is affected.
The above is only for the purpose of assisting understanding of the technical solutions of the present application, and does not represent an admission that the above is prior art.
Disclosure of Invention
The present application mainly aims to provide a control method of a smart watch, a control device of the smart watch, the smart watch and a computer readable storage medium, and aims to solve the problem of how to reduce the occurrence of the situation that the video call quality is affected due to the human image offset generated by the video shot by the smart watch.
In order to achieve the above object, the present application provides a method for controlling a smart watch, including the steps of:
when the fact that the intelligent watch starts a video call function is detected, acquiring a video image acquired by the intelligent watch;
detecting whether the distance between the face characteristic point in the video image and the image center point is smaller than a preset distance or not;
if not, the camera of the intelligent watch is rotated so that the distance is smaller than the preset distance.
Further, after the step of obtaining the video image collected by the smart watch, the method further includes:
detecting whether a human face area exists in the video image;
if yes, executing the step of detecting whether the distance between the face feature point in the video image and the image center point is smaller than a preset distance;
if not, determining the offset direction of the camera, and controlling the camera to rotate in the direction opposite to the offset direction.
Further, the step of determining the offset direction of the camera comprises:
determining a reference object from the video image;
and determining the offset direction of the camera according to the relative position relation of the reference object in the video images of the front frame and the rear frame.
Further, the step of determining the offset direction of the camera comprises:
and determining the offset direction of the camera according to the acceleration data acquired by the intelligent watch.
Further, the distance is a first distance; the preset distance is a first preset distance; after the step of obtaining the video image collected by the smart watch, the method further comprises:
when a plurality of face regions are detected to exist in the video image, detecting whether second distances between face characteristic points corresponding to the face regions are smaller than a second preset distance, wherein the second preset distance is larger than the first preset distance;
if yes, respectively executing the step of detecting whether the distance between the face characteristic point in the video image and the image central point is smaller than a preset distance for each face characteristic point;
if not, determining a target face area from the plurality of face areas, and executing the step of detecting whether the distance between the face characteristic point in the video image and the image center point is smaller than a preset distance or not based on the face characteristic point corresponding to the target face area.
Further, the step of determining a target face region from a plurality of face regions comprises:
determining a first distance between a face feature point corresponding to each face region and the central point of the image;
and taking the face area with the minimum first distance as a target face area.
Furthermore, the camera is a first camera, the smart watch is also provided with a second camera, and the shooting direction of the second camera is different from that of the first camera; the control method of the smart watch further comprises the following steps:
when the fact that the intelligent watch starts a video call function is detected, whether the intelligent watch is in a motion state or not is detected;
if so, acquiring a video image in a video shooting area of the second camera;
and displaying the video image acquired by the first camera and the video image acquired by the second camera in parallel.
In order to achieve the above object, the present application also provides a control device for a smart watch, the control device for the smart watch including:
the acquisition module is used for acquiring a video image acquired by the intelligent watch when the intelligent watch is detected to start a video call function;
the detection module is used for detecting whether the distance between the face characteristic point in the video image and the image center point is smaller than a preset distance or not;
and the processing module is used for rotating the camera of the intelligent watch if the distance is not less than the preset distance.
In order to achieve the above object, the present application further provides a smart watch, including:
the intelligent watch comprises a memory, a processor and a control program of the intelligent watch, wherein the control program of the intelligent watch is stored on the memory and can run on the processor, and when the control program of the intelligent watch is executed by the processor, the steps of the control method of the intelligent watch are realized.
To achieve the above object, the present application also provides a computer-readable storage medium, on which a control program of a smart watch is stored, and when the control program of the smart watch is executed by a processor, the steps of the control method of the smart watch are implemented.
The application provides a control method of an intelligent watch, a control device of the intelligent watch, the intelligent watch and a computer readable storage medium, in the process of starting a video call function of the intelligent watch, automatic positioning and tracking of the portrait position are achieved, when the intelligent watch enables the collected video to generate portrait offset due to shaking or other reasons, the angle of the camera for collecting the video can be rapidly adjusted, the portrait in the video can be maintained in the image center area as far as possible, the situation that the video call quality is affected due to the portrait offset generated by the video shot by the intelligent watch is reduced, and the quality of the video call by utilizing the intelligent watch is further guaranteed.
Drawings
Fig. 1 is a schematic diagram illustrating steps of a control method of a smart watch according to an embodiment of the present application;
fig. 2 is a schematic block diagram of a control device of a smart watch according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a smart watch according to an embodiment of the present application.
The implementation, functional features and advantages of the object of the present application will be further explained with reference to the embodiments, and with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, in an embodiment, the method for controlling a smart watch includes:
s10, when detecting that the intelligent watch starts a video call function, acquiring a video image acquired by the intelligent watch;
s20, detecting whether the distance between the face feature point in the video image and the image center point is smaller than a preset distance;
and S30, if not, rotating the camera of the intelligent watch to enable the distance to be smaller than the preset distance.
In this embodiment, the terminal in this embodiment may be a smart watch, or may be a control device of the smart watch.
As described in step S10: the intelligent watch is provided with a camera, the camera is rotatably connected with the intelligent watch through a movable support, and the intelligent watch can rotate through controlling the camera to adjust the shooting direction of the camera.
Optionally, when the user uses the video call function of the smart watch, the shooting direction of the camera of the smart watch can be made to face the user, so that the user is in the video shooting area of the camera; and the camera can be recorded as a first camera.
Optionally, when the smart watch detects that the video call function of the smart watch is turned on, the first camera is used for collecting video data in the video shooting area, and video images are obtained from the collected video data in a timing or real-time mode.
As described in step S20: after the intelligent watch obtains the video image, the face recognition technology and the image recognition technology are used for recognizing the face characteristic points in the face area in the video image. The face characteristic point can be at least one characteristic point which can represent the middle position of the face, such as the nose, the mouth, the eyebrow and the like of the person.
Optionally, after the face feature point in the video image is identified, the smart watch determines a first position corresponding to the face feature point, further determines a distance between the first position and a second position corresponding to an image center point of the video image, and may record the determined distance as the first distance. The calculation unit of the first distance may be the number of pixels.
Further, when the smart watch determines that the first distance between the first position and the second position is obtained, whether the first distance is smaller than a preset distance is detected. The preset distance is used for measuring the deviation degree of the human face feature point and the image central point, and the specific value can be set according to the actual situation, for example, set to be 20 pixel points. It should be noted that the preset distance may be recorded as a first preset distance.
Optionally, when the smart watch detects that the first distance is smaller than the preset distance, the smart watch may not process the first distance.
As set forth in step S30: when the intelligent watch detects that the first distance is larger than or equal to the preset distance, the direction of the face characteristic point relative to the image center point is determined according to the relative position relation between the face characteristic point and the image center point, then the rotation direction of the camera of the intelligent watch is determined based on the direction, and the camera is controlled to rotate in the rotation direction, so that the distance (namely the first distance) between the face characteristic point and the image center point is shortened until the first distance is smaller than the preset distance.
Optionally, in the process of controlling the camera to rotate, the camera may be controlled to rotate at a first preset angle each time, and the value range of the first preset angle may be 0.1 ° to 0.5 °. After the camera is controlled to rotate by a first preset angle in the rotating direction each time, updating a first distance according to a video image acquired after the camera rotates, and detecting whether the first distance is smaller than a preset distance; if not, controlling the camera to rotate again by the first preset angle in the rotating direction; if yes, the camera is not controlled to rotate any more.
In an embodiment, in the process of starting the video call function of the smart watch, the automatic positioning and tracking of the portrait position are realized, so that when the smart watch makes the collected video generate portrait offset due to jitter or other reasons, the angle of the camera for collecting the video can be rapidly adjusted, the portrait in the video can be maintained in the image center area as much as possible, the situation that the video shot by the smart watch generates portrait offset to influence the video call quality is reduced, and the quality of the video call by the smart watch is ensured.
In an embodiment, on the basis of the above embodiment, after the step of acquiring the video image collected by the smartwatch, the method further includes:
s40, detecting whether a face area exists in the video image;
step S41, if yes, executing the step of detecting whether the distance between the face characteristic point in the video image and the image central point is smaller than a preset distance;
and S42, if not, determining the offset direction of the camera, and controlling the camera to rotate in the direction opposite to the offset direction.
In this embodiment, after the smart watch obtains the video image, it may first detect whether a face region exists in the video image by using a face recognition technology, that is, detect whether a portrait exists in the video image.
Optionally, when the smart watch detects that a face area exists in the video image, the step of detecting whether the distance between the face feature point in the video image and the image center point is smaller than a preset distance is executed, so that the smart watch can position and track the position of the portrait based on the step, and when the portrait in the video is detected to be shifted, the angle of the camera for acquiring the video can be rapidly adjusted, the portrait in the video can be maintained in the image center area as much as possible, thereby reducing the occurrence of the situation that the quality of the video call is affected due to the portrait shift generated by the video shot by the smart watch, and further ensuring the quality of the video call by using the smart watch.
It should be understood that the face feature points in the video image are identified in the face region of the video image.
Optionally, when the smart watch detects that no face region exists in the video image, and the video call function of the smart watch is still turned on at this time, it is determined that the shooting direction of the camera has deviated from the position of the face of the user, and therefore the camera needs to be controlled to rotate, so that the video image acquired by the camera can include the face region of the user.
Therefore, when the smart watch detects that no face region exists in the video image, it is necessary to determine an offset direction of the camera (i.e., a direction in which a shooting manner of the camera deviates from a face direction of the user), then determine an opposite direction of the offset direction as a rotation direction of the camera, and rotate the camera in the rotation direction by controlling the camera, and rotate by a preset angle (the preset angle may be recorded as a second preset angle) each time until the video image acquired by the camera may include the face region (i.e., so that the face image of the user may return to the video image), and then the smart watch performs the step of detecting whether the distance between the face feature point and the image center point in the video image is smaller than the preset distance.
The second preset angle is greater than or equal to the first preset angle, and preferably greater than the first preset angle; therefore, if a face area exists in the video image, but the first distance between the face characteristic point in the face area and the image center point is greater than the preset distance, the shooting direction of the camera is finely adjusted only by using the first preset angle; if the face area is not identified in the video image, the shooting direction of the camera can be adjusted greatly by using a second preset angle, so that the face image of the user can be quickly returned to the video image.
The mode of the smart watch for determining the offset direction of the camera can be that a reference object is determined from the video image, and then the offset direction of the camera is determined according to the relative position relationship of the reference object in the video images of the front frame and the back frame; or, the offset direction of the camera may be determined according to acceleration data acquired by the smart watch.
Like this, when the condition that the portrait squinted out video image took place (when the camera led to its shooting direction to leave people's face position because of the inequality power promptly) for the shooting direction of intelligent wrist-watch can quick adjustment camera, so that the portrait can in time get back to in the video image, and then guaranteed to utilize intelligent wrist-watch to carry out the quality of video conversation.
In an embodiment, on the basis of the above embodiment, the step of determining the offset direction of the camera includes:
step S50, determining a reference object from the video image;
and S51, determining the offset direction of the camera according to the relative position relation of the reference object in the video images of the front frame and the rear frame.
In this embodiment, when determining the offset direction of the camera, the smartwatch may determine a marker image as a reference object from the video image by using an image recognition technology, and then determine positions of the reference object in at least two frames of video images successively acquired by the camera. The position of the reference object in the previous frame of video image is taken as the third position, and the position of the reference object in the next frame of video image is taken as the fourth position.
It should be noted that, in this embodiment, the time interval between the two frames of video images selected for the smart watch is not limited, and may be determined according to the needs of the actual situation, but the two frames of video images selected for the smart watch all need to include a reference object.
Further, after the smart watch obtains the third position and the fourth position, the orientation of the third position relative to the fourth position can be determined according to the relative position relationship between the third position and the fourth position, and then the offset direction of the camera is determined based on the orientation.
For example, because the third position is an initial position, when it is determined that the third position is below the fourth position, it is described that the object image in the image moves upward and is substantially shifted downward relative to the camera (i.e., the shift direction is a downward direction), such a situation occurs that the human image cannot be recorded in the video, and then the camera may be controlled to rotate in a direction opposite to the shift direction (i.e., rotate upward) until the human image appears in the video (even if a human face region exists in the video image).
Conversely, when the third position is determined to be above the fourth position, it is described that the object image in the image moves downwards and is substantially shifted upwards relative to the camera, which may cause the portrait to be unrecorded in the video, and at this time, the camera may be controlled to rotate in the direction opposite to the shifting direction (i.e., to rotate downwards) until the portrait appears in the video.
Optionally, after the smart watch determines that the third position and the fourth position are obtained, the distance between the third position and the fourth position may be determined first, and whether the distance between the third position and the fourth position is greater than a preset distance is detected. The preset distance can be recorded as a third preset distance, and the value of the third preset distance can be set according to actual requirements, for example, the value is set to be 1/18 of the side length of the video image, and the counting unit of the side length is the number of the pixel points.
Optionally, when the smart watch detects that the distance between the third position and the fourth position is greater than a third preset distance, it indicates that the video cannot record the portrait because the deviation degree of the shooting direction of the camera is large, and therefore the step of determining the offset direction of the camera and controlling the camera to rotate in the direction opposite to the offset direction needs to be further performed.
Optionally, when the terminal detects that the distance between the third position and the fourth position is less than or equal to a third preset distance, it indicates that the deviation degree of the shooting direction of the camera is small (or no deviation occurs), and at this time, the video recording of the portrait should be caused by the fact that the user actively leaves the video shooting area of the camera, so the smart watch may not process the portrait and the user actively returns to the video shooting area.
Like this, when the condition that the portrait squished out video image takes place (when the camera leads to its shooting direction to leave people's face position because of inequality promptly), just can intelligent judgement intelligent wrist-watch's the skew direction of the camera to adjust the shooting direction of camera based on this, so that the portrait can in time get back to in the video image, and then guaranteed to utilize intelligent wrist-watch to carry out the quality of video conversation.
In an embodiment, on the basis of the above embodiment, the step of determining the offset direction of the camera includes:
and S60, determining the offset direction of the camera according to the acceleration data acquired by the intelligent watch.
In this embodiment, be provided with acceleration sensor in the intelligent wrist-watch, through acceleration sensor, the intelligent wrist-watch can be in real time or regularly gather the acceleration data of this end, and acceleration data can be used to estimate the direction of motion of intelligent wrist-watch.
Because intelligence wrist-watch and camera are connected to an organic whole, consequently when the intelligent wrist-watch detects that there is not the face area in the video image, can be according to the acceleration data of gathering before gathering this video image, confirm the direction of motion of intelligent wrist-watch to regard this direction of motion as the skew direction of camera.
Therefore, the intelligent watch only needs to control the camera to rotate towards the opposite direction of the offset direction, and rotates a preset angle (the preset angle can be recorded as a second preset angle) at each time, so that the video image collected by the camera can finally comprise a face area (namely, the face image of a user can return to the video image), and then the intelligent watch executes the step of detecting whether the distance between the face characteristic point and the image central point in the video image is smaller than the preset distance.
Therefore, when the portrait deviates out of the video image (namely, when the camera leaves the position of the face due to the fact that the shooting direction of the camera is caused by inequality), the deviation direction of the camera of the intelligent watch can be intelligently judged, the shooting direction of the camera is adjusted based on the deviation direction, so that the portrait can timely return to the video image, and the quality of video conversation by utilizing the intelligent watch is guaranteed.
In an embodiment, on the basis of the above embodiment, after the step of obtaining the video image collected by the smart watch, the method further includes:
step S70, when a plurality of face areas are detected in the video image, detecting whether second distances between face characteristic points corresponding to the face areas are smaller than a second preset distance, wherein the second preset distance is larger than the first preset distance;
step S71, if yes, respectively executing the step of detecting whether the distance between the face characteristic point in the video image and the image center point is smaller than a preset distance for each face characteristic point;
and step S72, if not, determining a target face area from the plurality of face areas, and executing the step of detecting whether the distance between the face characteristic point in the video image and the image center point is smaller than a preset distance or not based on the face characteristic point corresponding to the target face area.
In this embodiment, when the smart watch detects that a face region exists in the video image, whether a plurality of face regions exist in the video image may be further detected.
When the smart watch detects that only one face region exists in the video image, the step of detecting whether the distance between the face feature point in the video image and the image center point is smaller than a preset distance is directly executed (namely, step S20).
Optionally, when the smartwatch detects that a plurality of face regions exist in the video image, the smartwatch respectively identifies face feature points in each face region (each face region determines a face feature point), and respectively determines a distance between each face feature point and records the distance as the second distance.
Further, the smart watch detects whether each second distance is smaller than a second preset distance. The second preset distance is greater than the first preset distance, and is two times of the first preset distance.
Optionally, when the smartwatch detects that all the second distances are smaller than a second preset distance, the smartwatch respectively executes the step of detecting whether the distance between the face feature point in the video image and the image center point is smaller than the preset distance for the face feature point corresponding to each face region, so that the first distance between the face feature point corresponding to each face region and the image center point is smaller than the first preset distance. The method is equivalent to constructing a circular area with the center point of the image as the center of a circle and the first preset distance as the radius, and controlling the rotation of the camera to enable all the characteristic points of the face to be in the circular area.
In order to make all the face regions closer to the central point of the image, the value of the first preset distance can be appropriately reduced.
Optionally, when the smartwatch detects that at least one second distance is greater than a second preset distance, a target face area is determined from the plurality of face areas, and based on a face feature point corresponding to the target face area, the step of detecting whether the distance between the face feature point in the video image and the image center point is smaller than the preset distance is executed, that is, whether the camera needs to be controlled to rotate is determined by detecting whether a first distance between the face feature point corresponding to the target face area and the image center point is smaller than a first preset distance.
Optionally, when the smart watch determines the target face region, a first distance between the face feature point corresponding to each face region and the image center point may be determined first, then the smallest first distance is selected from the first distances, and the face region corresponding to the selected first distance is used as the target face region.
Optionally, the smartwatch may also pre-store a reference face image of a legal user, and then identify a face area matched with the reference face image as a target face area from a plurality of face areas of the video image. The face image matching method may adopt pupil feature detection, image similarity detection and other methods.
Therefore, when a plurality of face areas appear in the video image, the face areas can be drawn close to the middle of the image as far as possible, or the target face areas can be located in the middle of the image, and the quality of video call by using the intelligent watch is further guaranteed.
In an embodiment, based on the above embodiment, the method for controlling a smart watch further includes:
s80, detecting whether the intelligent watch is in a motion state or not when the intelligent watch starts a video call function;
s81, if yes, acquiring a video image in a video shooting area of the second camera;
and S82, displaying the video image acquired by the first camera and the video image acquired by the second camera in parallel.
In this embodiment, the camera used for collecting the video image in the above embodiment may be recorded as a first camera, the smart watch is further provided with a second camera, a shooting direction of the second camera is different from that of the first camera, and is consistent with a face orientation of a user when the user watches the smart watch, that is, the second camera is used for collecting a video image in front of the face of the user.
Therefore, it can be understood that the shooting direction of the second camera is exactly opposite to the initial shooting direction of the first camera, that is, the first camera is used for shooting the side facing the human face, and the second camera is used for shooting the side facing the human face.
Optionally, when detecting that the smart watch starts the video call function and acquiring the video image required by the video call function by using the first camera, the smart watch can be detected whether to be in a motion state.
Optionally, the mode of detecting whether the smart watch is in the motion state may be acceleration data acquired by an acceleration sensor provided in the smart watch, so as to determine whether the smart watch is in the motion state. The detection principle is that the change value of the relevant acceleration data within a certain time is detected, the change value is compared with a preset threshold value, and if the change value exceeds the preset threshold value, the intelligent watch can be judged to be in a motion state; and if the current value is less than or equal to the preset threshold value, judging that the intelligent watch is not in the motion state.
Optionally, the mode of detecting whether the smart watch is in the motion state may also be a mode of recording the rotation frequency of the first camera within a certain time period, so as to determine whether the smart watch is in the motion state. When the rotation frequency is detected to be greater than the preset frequency, the intelligent watch is judged to be in a motion state; and if the rotation frequency is detected to be less than or equal to the preset frequency, judging that the intelligent watch is not in the motion state.
Optionally, when the intelligent watch is detected to be in a motion state, the second camera is started, and the second camera is used for collecting video images in the video shooting area. The video image collected by the second camera is recorded as a second video image, and the video image collected by the first camera is recorded as a first video image.
Further, the smart watch displays the first video image and the second video image which are acquired simultaneously on the screen of the smart watch in parallel. At this time, the smart watch may also display the video image transmitted by the device at the video call end.
Like this, when the user opened the video conversation function of intelligent wrist-watch to when putting into attention to the screen of intelligent wrist-watch, make the user observe video image's shooting quality based on first video image, can also follow the road conditions in its advancing direction through the second video image, when appearing the barrier on its advancing direction like this or having other dangerous circumstances to take place, make the user in time avoid, thereby security when having guaranteed the user and used the video conversation function of intelligent wrist-watch.
Referring to fig. 2, in an embodiment of the present application, there is provided a control device 10 for a smart watch, including:
the acquisition module 11 is configured to acquire a video image acquired by the smart watch when detecting that the smart watch starts a video call function;
the detection module 12 is configured to detect whether a distance between a face feature point in the video image and an image center point is smaller than a preset distance;
and the processing module 13 is used for rotating the camera of the intelligent watch if the distance is not less than the preset distance.
Referring to fig. 3, an embodiment of the present application further provides a smart watch, where the smart watch may be a server, and an internal structure of the smart watch may be as shown in fig. 3. The smart watch includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the smart watch is configured to provide computing and control capabilities. The memory of the intelligent watch comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the smart watch is used for a control program of the smart watch. The network interface of the intelligent watch is used for being connected and communicated with an external terminal through a network. The computer program is executed by a processor to implement a method of controlling a smart watch.
Those skilled in the art will appreciate that the structure shown in fig. 3 is only a block diagram of a part of the structure related to the present application, and does not constitute a limitation of the smart watch to which the present application is applied.
Furthermore, the present application also proposes a computer-readable storage medium, which includes a control program of a smart watch, the control program of the smart watch implementing the steps of the control method of the smart watch as described in the above embodiments when executed by a processor. It is to be understood that the computer-readable storage medium in the present embodiment may be a volatile-readable storage medium or a non-volatile-readable storage medium.
In summary, according to the control method of the smart watch, the control device of the smart watch, the smart watch and the storage medium provided in the embodiments of the present application, in the process of enabling the video call function of the smart watch, automatic positioning and tracking of the portrait position are achieved, so that when the captured video is subjected to portrait offset due to shake or other reasons in the smart watch, the angle at which the camera captures the video can be rapidly adjusted, and the portrait in the video can be maintained in the image center area as much as possible, thereby reducing the occurrence of the situation that the video call quality is affected due to portrait offset generated in the video captured by the smart watch, and further ensuring the quality of the video call using the smart watch.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of another identical element in a process, apparatus, article, or method comprising the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all the equivalent structures or equivalent processes that can be directly or indirectly applied to other related technical fields by using the contents of the specification and the drawings of the present application are also included in the scope of the present application.
Claims (9)
1. A control method of a smart watch, comprising:
when the fact that the intelligent watch starts a video call function is detected, acquiring a video image acquired by the intelligent watch;
when a plurality of face areas exist in the video image, whether second distances between face characteristic points corresponding to the face areas are smaller than a second preset distance or not is detected;
if the second distances are smaller than the second preset distance, respectively detecting whether a first distance between a face feature point in the video image and an image center point is smaller than a first preset distance or not for each face feature point, wherein the second preset distance is larger than the first preset distance;
if the second distance unevenness is smaller than the second preset distance, determining a target face region from the plurality of face regions, and detecting whether the first distance between a face feature point in the video image and an image center point is smaller than the first preset distance or not based on a face feature point corresponding to the target face region;
if the first distance is not smaller than the first preset distance, rotating a camera of the intelligent watch so that the first distance is smaller than the first preset distance.
2. The method for controlling a smart watch of claim 1, wherein after the step of obtaining the video image captured by the smart watch, the method further comprises:
detecting whether a human face area exists in the video image;
if not, determining the offset direction of the camera, taking the opposite direction of the offset direction as the rotation direction of the camera, and controlling the camera to rotate towards the rotation direction at a second preset angle every time until the video image acquired by the camera comprises a face area.
3. The method of controlling a smart watch of claim 2, wherein the step of determining the direction of the offset of the camera comprises:
determining a reference object from the video image;
and determining the offset direction of the camera according to the relative position relation of the reference object in the video images of the front frame and the rear frame.
4. The method of controlling a smart watch of claim 2, wherein the step of determining the offset direction of the camera comprises:
and determining the offset direction of the camera according to the acceleration data acquired by the intelligent watch.
5. The method of controlling a smartwatch according to claim 1, wherein the step of determining a target face region from the plurality of face regions comprises:
determining the first distance between the face feature point corresponding to each face region and the image center point;
and taking the face area with the minimum first distance as a target face area.
6. The method for controlling the smart watch according to claim 1, wherein the camera is a first camera, and the smart watch is further provided with a second camera, and a shooting direction of the second camera is different from that of the first camera; the control method of the smart watch further comprises the following steps:
when the fact that the intelligent watch starts a video call function is detected, whether the intelligent watch is in a motion state or not is detected;
if so, acquiring a video image in a video shooting area of the second camera;
and displaying the video image acquired by the first camera and the video image acquired by the second camera in parallel.
7. A control device of a smart watch, comprising:
the acquisition module is used for acquiring a video image acquired by the intelligent watch when the intelligent watch starts a video call function;
the detection module is used for detecting whether second distances between the face characteristic points corresponding to the face areas are smaller than a second preset distance when a plurality of face areas exist in the video image;
if the second distances are smaller than the second preset distance, respectively detecting whether a first distance between a face characteristic point in the video image and an image center point is smaller than a first preset distance for each face characteristic point, wherein the second preset distance is larger than the first preset distance;
if the second distance unevenness is smaller than the second preset distance, determining a target face area from the plurality of face areas, and detecting whether the first distance between a face feature point in the video image and an image center point is smaller than the first preset distance or not based on a face feature point corresponding to the target face area;
and the processing module is used for rotating the camera of the intelligent watch if the first distance is not less than the first preset distance so as to enable the first distance to be less than the first preset distance.
8. A smart watch comprising a memory, a processor and a control program of the smart watch stored on the memory and executable on the processor, the control program of the smart watch implementing the steps of the control method of the smart watch according to any one of claims 1 to 6 when executed by the processor.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a control program of a smart watch, which when executed by a processor implements the steps of the control method of the smart watch according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110198958.6A CN112969047B (en) | 2021-02-22 | 2021-02-22 | Control method and device of smart watch, smart watch and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110198958.6A CN112969047B (en) | 2021-02-22 | 2021-02-22 | Control method and device of smart watch, smart watch and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112969047A CN112969047A (en) | 2021-06-15 |
| CN112969047B true CN112969047B (en) | 2023-01-24 |
Family
ID=76285569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110198958.6A Active CN112969047B (en) | 2021-02-22 | 2021-02-22 | Control method and device of smart watch, smart watch and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112969047B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4944055B2 (en) * | 2008-03-19 | 2012-05-30 | 富士フイルム株式会社 | Imaging apparatus and imaging control method |
| CN108900770B (en) * | 2018-07-17 | 2021-01-22 | 广东小天才科技有限公司 | Method and device for controlling rotation of camera, smart watch and mobile terminal |
| CN110177242B (en) * | 2019-04-08 | 2020-12-25 | 广东小天才科技有限公司 | Video call method based on wearable device and wearable device |
| CN110472491A (en) * | 2019-07-05 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Abnormal face detecting method, abnormality recognition method, device, equipment and medium |
| CN111147749A (en) * | 2019-12-31 | 2020-05-12 | 宇龙计算机通信科技(深圳)有限公司 | Photographing method, photographing device, terminal and storage medium |
-
2021
- 2021-02-22 CN CN202110198958.6A patent/CN112969047B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112969047A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108447091B (en) | Target positioning method and device, electronic equipment and storage medium | |
| US8314854B2 (en) | Apparatus and method for image recognition of facial areas in photographic images from a digital camera | |
| US8243159B2 (en) | Image capturing device, image processing device, image analysis method for the image capturing device and the image processing device, and program for facial attribute detection | |
| CN110765847B (en) | Font adjustment method, device, equipment and medium based on face recognition | |
| CN108875507B (en) | Pedestrian tracking method, apparatus, system, and computer-readable storage medium | |
| US9571740B2 (en) | Image recognition device that recognizes specific object area, method of controlling the device, and storage medium, as well as image pickup apparatus, and display device | |
| US10091466B2 (en) | Visual perception determination system and method | |
| CN111354024B (en) | Behavior prediction method of key target, AI server and storage medium | |
| CN111325144A (en) | Behavior detection method and apparatus, computer device and computer-readable storage medium | |
| JP4957711B2 (en) | Detection apparatus and method, and program | |
| US20160104036A1 (en) | Method and apparatus for detecting blink | |
| US20220004748A1 (en) | Video display method, device and system, and video camera | |
| CN111582179B (en) | Monitoring video analysis method and device, computer equipment and storage medium | |
| US10621424B2 (en) | Multi-level state detecting system and method | |
| CN114429474A (en) | Human body key point detection method and device and computer storage medium | |
| CN112749655A (en) | Sight tracking method, sight tracking device, computer equipment and storage medium | |
| CN104238733A (en) | Method for triggering signal and electronic device for vehicle | |
| EP2993891B1 (en) | Electronic device and image capture method thereof | |
| CN112969047B (en) | Control method and device of smart watch, smart watch and storage medium | |
| US20210256713A1 (en) | Image processing apparatus and image processing method | |
| CN111582024B (en) | Video stream processing method, device, computer equipment and storage medium | |
| CN113269148A (en) | Sight estimation method, sight estimation device, computer equipment and storage medium | |
| CN112597854B (en) | Non-matching type face recognition system and method | |
| WO2019040068A1 (en) | Image processing devices with efficient motion blur detection and methods of operating same | |
| JP2013179614A (en) | Imaging apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |