CN111258415A - Video-based limb movement detection method, device, terminal and medium - Google Patents
Video-based limb movement detection method, device, terminal and medium Download PDFInfo
- Publication number
- CN111258415A CN111258415A CN201811459981.0A CN201811459981A CN111258415A CN 111258415 A CN111258415 A CN 111258415A CN 201811459981 A CN201811459981 A CN 201811459981A CN 111258415 A CN111258415 A CN 111258415A
- Authority
- CN
- China
- Prior art keywords
- data frame
- video
- limb
- target data
- limb action
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Abstract
The embodiment of the disclosure discloses a video-based limb action detection method, a video-based limb action detection device, a video-based limb action detection terminal and a video-based limb action detection medium, wherein the method comprises the following steps: in the video shooting process, limb actions are detected in real time on data frames in the video; if the data frame losing the limb movement is detected in the video, taking a preset number of data frames behind the data frame losing the limb movement as target data frames; and acquiring a video effect corresponding to the limb action in the last frame data of the data frame losing the limb action, and maintaining the video effect in the data frame losing the limb action and the target data frame. The method and the device for displaying the video special effect solve the problem that in the prior art, the display effect of the video special effect is influenced due to the fact that the detection result of the limb action in the video data is inaccurate, accurate detection of the limb action of a user in the video shooting process is achieved, and the display effect of the video special effect is guaranteed.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of internet, in particular to a video-based limb action detection method, device, terminal and medium.
Background
The development of network technology makes video interaction application very popular in people's daily life.
With the increase of application functions, a user can add various video special effects in the video through limb action control. At the moment, the display of the video special effect is directly influenced on the result precision of the user limb motion detection. For example, in the video shooting process, a user wants to control flames appearing in the video to slowly change from large to small through gestures in body movements, but the flames directly disappear after appearing in the finally shot video effect, and the reason why the phenomenon appears is that the detection result of the terminal on the gesture changes in the video data is inaccurate in the shooting process.
Therefore, how to accurately detect the body movement of the video data to ensure the display effect of the video special effect still remains a problem to be solved at present.
BRIEF SUMMARY OF THE PRESENT DISCLOSURE
The embodiment of the disclosure provides a video-based limb movement detection method, a video-based limb movement detection device, a video-based limb movement detection terminal and a video-based limb movement detection medium, so that accurate detection of limb movement in video data is realized, and a special effect display effect of a video is ensured.
In a first aspect, an embodiment of the present disclosure provides a video-based limb movement detection method, where the method includes:
in the process of shooting a video, detecting a data frame in the video in real time;
if a data frame losing a limb action is detected in the video, taking a preset number of data frames behind the data frame losing the limb action as target data frames, wherein the limb action is used for controlling a video effect;
and acquiring a video effect corresponding to the limb action in the last frame data of the data frame losing the limb action, and maintaining the video effect in the data frame losing the limb action and the target data frame.
Optionally, the method further includes:
and triggering a video effect corresponding to the limb action detection result in the data frame after the target data frame according to the limb action detection result of the data frame after the target data frame.
Optionally, triggering, according to a limb motion detection result of a data frame after the target data frame, a video effect corresponding to the limb motion detection result in the data frame after the target data frame, includes:
if no limb action is detected in the data frame after the target data frame, triggering a corresponding excessive video effect under the condition of no limb action in the data frame after the target data frame;
and if the body action is detected in the data frame behind the target data frame, controlling and displaying the corresponding video effect in the data frame behind the target data frame according to the body action.
Optionally, the influencing factors of the detection result of the limb movement include: the shooting environment of the video and the motion state of the limb action.
In a second aspect, an embodiment of the present disclosure further provides a video-based limb movement detection apparatus, where the apparatus includes:
the limb action detection module is used for detecting data frames in the video in real time in the video shooting process;
a target data frame determination module, configured to, if a data frame missing a limb motion is detected in the video, take a preset number of data frames after the data frame missing the limb motion as a target data frame, where the limb motion is used to control a video effect;
and the video effect maintaining module is used for acquiring a video effect corresponding to the limb action in the last frame data of the data frame losing the limb action and maintaining the video effect in the data frame losing the limb action and the target data frame.
Optionally, the apparatus further comprises:
and the video effect triggering module is used for triggering a video effect corresponding to the limb action detection result in the data frame after the target data frame according to the limb action detection result of the data frame after the target data frame.
Optionally, the video effect triggering module includes:
a first triggering unit, configured to trigger a corresponding excessive video effect in a case of no limb motion in a data frame following the target data frame if no limb motion is detected in the data frame following the target data frame;
and the second triggering unit is used for controlling and displaying the corresponding video effect in the data frame after the target data frame according to the body action if the body action is detected in the data frame after the target data frame.
Optionally, the influencing factors of the detection result of the limb movement include: the shooting environment of the video and the motion state of the limb action.
In a third aspect, an embodiment of the present disclosure further provides a terminal, including:
one or more processing devices;
a storage device for storing one or more programs,
when executed by the one or more processing devices, cause the one or more processing devices to implement a video-based limb motion detection method according to any embodiment of the present disclosure.
In a fourth aspect, the embodiments of the present disclosure further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by an apparatus, implements the video-based limb movement detection method according to any embodiment of the present disclosure.
The method and the device for detecting the limb movement in real time carry out limb movement detection on the data frame in the video shooting process; if the data frame losing the limb movement is detected in the video, taking a preset number of data frames behind the data frame losing the limb movement as target data frames; the method and the device have the advantages that the video effect corresponding to the limb action in the last frame data of the data frame losing the limb action is obtained, the video effect is maintained in the data frame losing the limb action and the target data frame, the problem that the display effect of the video special effect is influenced due to the fact that the detection result of the limb action in the video data is inaccurate in the prior art is solved, accurate detection of the limb action of a user in the video shooting process is achieved, and the display effect of the video special effect is guaranteed.
Drawings
Fig. 1 is a schematic flowchart of a video-based limb movement detection method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of another video-based limb movement detection method provided by the embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a video-based limb movement detection apparatus provided in an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a hardware structure of a terminal according to an embodiment of the present disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the disclosure and are not limiting of the disclosure. It should be further noted that, for the convenience of description, only some of the structures relevant to the present disclosure are shown in the drawings, not all of them.
Optional features and examples are provided in each of the embodiments described below, and each of the features described in the embodiments may be combined to form multiple alternatives.
Fig. 1 is a schematic flow chart of a video-based limb movement detection method according to an embodiment of the present disclosure, which is applicable to a situation where a user adds a video effect of limb movement control in a process of shooting a video, and detects a limb movement of the user in real time.
As shown in fig. 1, a video-based limb movement detection method provided in an embodiment of the present disclosure may include:
and S110, detecting data frames in the video in real time in the video shooting process.
The user can start an application with a video shooting function installed on the terminal, such as a video interaction application, to shoot a video, and the application supports the user to control the addition of a video effect through body movement in the video shooting process, wherein the video effect refers to an editing effect on the video on the basis of the original shooting video, such as adding an animation special effect in the video, changing the display form of the video special effect, adding a video filter and the like.
In the shooting process, the camera transmits video data acquired in real time to the terminal application, the terminal application detects the video data in real time after acquiring the video data, and judges whether the user limb action exists in the current data frame by frame so as to trigger a corresponding video effect according to the detected limb action. The corresponding relationship between the limb action and the video effect can be preset in the development process of the terminal application, or can be a user-defined corresponding relationship before shooting is started based on materials provided by the terminal application. The limb actions in the embodiment include various control actions formed by the user limbs, including limb actions formed by the mutual cooperation of the head, the fingers, the palm, the arms, the legs and the feet of the user.
And S120, detecting whether a data frame with the limb motion lost exists in the video.
If the data frame of the missing body motion is detected, operation S140 is performed, and if the data frame of the missing body motion is not detected, operation S130 is performed.
And S130, displaying a corresponding video effect according to the detected limb movement.
And S140, taking the data frames with preset number after the data frames with the lost limb actions as target data frames.
If the user triggers the addition of the video effect through the limb action control in the shooting process, but the limb action detection result shows that the limb action does not exist in the current data frame, namely the current data frame is the data frame losing the limb action, the data frames with the preset number behind the current data frame are used as target data frames, and the video effect is delayed. When the body motion of the user is not detected in the current data frame, the body motion of the user does not necessarily mean that the body motion of the user does not exist in the subsequent video data frame, or the user interrupts the operation of controlling the video effect by the body motion. The fact that the body motion of the user is not detected in the current data frame can be the influence of interference factors in the video shooting process, such as the shooting environment of the video, the motion state of the body motion and the like. The number of the target data frames can be determined according to experimental tests or data statistics, and the target data frames can be reasonably set on the basis of ensuring the accuracy of the limb movement detection result in the video shooting process, and can be 1 frame or 2 frames and the like.
For example, light in the current video shooting environment is abnormal, or the movement speed of the limb movement is too high, so that the limb movement of the user does not exist in the current data frame or the data of the following frames, and actually the user still continuously controls the video effect through the limb movement, the detection result of the limb movement based on the current data frame is inaccurate, and therefore, it is obviously unreasonable if the video effect is interrupted or a new video effect is triggered only according to the detection result of the limb movement of the current data frame.
S150, acquiring a video effect corresponding to the limb motion in the last frame data of the data frame losing the limb motion, and maintaining the video effect in the data frame losing the limb motion and the target data frame.
By performing the short delay of the video effect in the previous frame data in the current data frame and the target data frame, rather than directly processing the data frame of the current loss gesture as frame loss data, for example, ending the display of the video effect in the current data frame or displaying a new video effect discontinuous from the video effect in the previous data frame, the non-continuity and the obtrusiveness of the change of the video effect are avoided. With the continuous video shooting, the real-time gesture detection is continuously carried out on the data behind the target data frame so as to determine whether the gesture exists in the subsequent data frame, and whether the gesture of the user is really lost in the currently shot video data is determined by combining the subsequent gesture detection result, so that the accuracy of the gesture detection in the video shooting process is improved.
For example, if the user currently wants to capture a video clip with flame size controlled by gesture, including 30 frames of data, but no user gesture is detected in the 25 th frame of the video clip, the data of the 26 th to 27 th frames can be used as the target data frame, the flame effect in the 24 th frame is maintained in the 25 th to 27 th frames, and then gesture detection is continuously performed on the 28 th and following data frames in real time, and the change of the flame size is controlled according to the detected gesture. By means of the scheme, even if the user gesture is not detected in the 25 th frame data, the effect of the change of the flame size in the 25 th frame data still keeps consistency with the effect in the front and back adjacent data frames, the flame is not directly displayed in the 25 th frame data based on the gesture which is not detected, if the user gesture is detected in the 26 th frame data, the flame reappears, and the non-consistency of the change of the flame effect in the 25 th frame data and the jumping change of the whole flame display effect are avoided.
According to the technical scheme, the data frames in the shot video are detected in real time, if the data frames losing the body actions are detected in the video, a delay strategy of a video effect is adopted, the video effect is not directly interrupted or a non-relevant new video effect is triggered in the data frames losing the body actions, the problem that the display effect of the video special effect is influenced due to the fact that the detection result of the body actions in the video data is inaccurate in the prior art is solved, accurate detection of the body actions of the user in the video shooting process is achieved, the frame loss probability in the video shooting process is reduced, the display effect of the video special effect is guaranteed, and the phenomenon that the display of the video effect is discontinuous or abrupt due to the loss of the body actions in part of the data frames is avoided.
Fig. 2 is a schematic flow chart of another video-based limb movement detection method provided by the embodiment of the present disclosure, which is expanded on the basis of various alternatives in the above embodiment, and can be combined with various alternatives in the above embodiment.
As shown in fig. 2, a video-based limb movement detection method provided by an embodiment of the present disclosure may include:
and S210, detecting data frames in the video in real time in the video shooting process.
S220, detecting whether a data frame with a lost limb motion exists in the video.
If the data frame of the missing body motion is detected, operation S240 is performed, and if the data frame of the missing body motion is not detected, operation S230 is performed.
And S230, displaying the corresponding video effect according to the detected limb movement.
And S240, taking the data frames with preset number after the data frames with the lost limb movement as target data frames.
And S250, acquiring a video effect corresponding to the limb motion in the last frame data of the data frame losing the limb motion, and maintaining the video effect in the data frame losing the limb motion and the target data frame.
And S260, triggering a video effect corresponding to the limb action detection result in the data frame after the target data frame according to the limb action detection result of the data frame after the target data frame.
After the short delay of the video effect, according to the real-time detection result of the data frame after the target data frame, whether the limb action of the user is really lost in the currently shot video data or not can be confirmed, or whether the user stops the operation of controlling the addition of the video effect by utilizing the limb action.
Optionally, triggering a video effect corresponding to the limb motion detection result in the data frame after the target data frame according to the limb motion detection result of the data frame after the target data frame, including:
if no limb movement is detected in the data frame following the target data frame, a corresponding excessive video effect is triggered in the data frame following the target data frame when no limb movement is detected. The excessive video effect is a video effect associated with the maintained video effect, which is determined according to a preset rule, and the preset rule can be flexibly set according to a specific video effect type, such as slow disappearance and appearance of the video effect, enhanced display, bouncing of a material object, and the like. In addition, the excessive video effect may be an effect provided to the user by the terminal application based on a specific video effect, or a user-defined continuation video effect without body motion.
And if the body action is detected in the data frame after the target data frame, displaying the corresponding video effect according to the body action control in the data frame after the target data frame, namely triggering the video effect of the body action control according to the preset corresponding relation between the body action and the video effect.
Illustratively, a user adds a flame size change effect comprising 30 frames of data in a shot video through gesture control, but a user gesture is not detected in 25 th frame of the video, the 26 th frame of data can be taken as a target data frame, and a flame display effect in 24 th frame of data is maintained in 25 th-26 th frame of data, if a gesture is still not detected in 27 th frame of data, and the gesture is really lost in the corresponding video data frame, a preset flame over-video effect is triggered in 27 th frame of data, namely a video effect showing slow flame off is displayed; and if the gesture is detected in the 27 th frame data, which corresponds to the situation that the gesture is false lost in the video data frame, controlling the size of the flame displayed in the 27 th frame data according to the gesture.
According to the technical scheme, the body motion is detected in real time on the data frame in the shot video, if the data frame losing the body motion is detected in the video, a video effect delay strategy is adopted in the data frame losing the body motion and the target data frame, and the corresponding video effect is triggered in the data frame behind the target data frame based on the body motion detection result, so that the phenomenon that the video effect display is discontinuous or abrupt due to the loss of the body motion in part of the data frames can be avoided no matter whether the user body motion in the video data frame is really lost or falsely lost, and the accuracy of the body motion detection in the video data is improved.
Fig. 3 is a schematic structural diagram of a video-based limb movement detection device according to an embodiment of the present disclosure, which is applicable to a situation where a user adds a video effect of limb movement control to detect a limb movement of the user in real time in a process of shooting a video by the user. The limb movement detection device can be realized in a software and/or hardware mode, and can be configured on any terminal with a network communication function.
As shown in fig. 3, the video-based limb movement detection apparatus provided by the embodiment of the present disclosure includes a limb movement detection module 310, a target data frame determination module 320, and a video effect maintenance module 330, where:
the body motion detection module 310 is configured to detect a data frame in a video in real time during a video shooting process;
a target data frame determining module 320, configured to, if a data frame missing a limb motion is detected in the video, take a preset number of data frames after the data frame missing the limb motion as a target data frame, where the limb motion is used to control a video effect;
the video effect maintaining module 330 is configured to obtain a video effect corresponding to the limb motion in the previous frame data of the data frame with the lost limb motion, and maintain the video effect in the data frame with the lost limb motion and the target data frame.
Optionally, the limb movement detecting device further includes:
the video effect triggering module 340 is configured to trigger a video effect corresponding to the limb action detection result in the data frame after the target data frame according to the limb action detection result of the data frame after the target data frame.
Optionally, the video effect triggering module 340 includes:
the first triggering unit is used for triggering a corresponding excessive video effect under the condition of no limb action in a data frame after a target data frame if the limb action is not detected in the data frame after the target data frame, wherein the excessive video effect is a video effect which is determined according to a preset rule and is associated with a maintained video effect;
and the second triggering unit is used for controlling and displaying the corresponding video effect in the data frame after the target data frame according to the body action if the body action is detected in the data frame after the target data frame.
Optionally, the influencing factors of the detection result of the limb movement include: the shooting environment of the video and the motion state of the limb action.
The video-based limb movement detection device can execute the video-based limb movement detection method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method.
Fig. 4 is a schematic diagram of a hardware structure of a terminal according to an embodiment of the present disclosure. Referring now to fig. 4, a block diagram of a terminal 400 suitable for use in implementing embodiments of the present disclosure is shown. The terminal in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The terminal shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 4, the terminal 400 may include one or more processing devices (e.g., central processing units, graphics processors, etc.) 401, and a storage device 408 for storing one or more programs. Among other things, the processing device 401 may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage device 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the terminal 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
Generally, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the terminal 400 to communicate with other devices, either wirelessly or by wire, for exchanging data. While fig. 4 illustrates a terminal 400 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication device 409, or from the storage device 408, or from the ROM 402. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 401.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the terminal; or may exist separately and not be assembled into the terminal.
The computer readable medium carries one or more programs which, when executed by the terminal, cause the terminal to: in the process of shooting a video, detecting a data frame in the video in real time; if a data frame losing a limb action is detected in the video, taking a preset number of data frames behind the data frame losing the limb action as target data frames, wherein the limb action is used for controlling a video effect; and acquiring a video effect corresponding to the limb action in the last frame data of the data frame losing the limb action, and maintaining the video effect in the data frame losing the limb action and the target data frame.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (10)
1. A video-based limb movement detection method is characterized by comprising the following steps:
in the process of shooting a video, detecting a data frame in the video in real time;
if a data frame losing a limb action is detected in the video, taking a preset number of data frames behind the data frame losing the limb action as target data frames, wherein the limb action is used for controlling a video effect;
and acquiring a video effect corresponding to the limb action in the last frame data of the data frame losing the limb action, and maintaining the video effect in the data frame losing the limb action and the target data frame.
2. The method of claim 1, further comprising:
and triggering a video effect corresponding to the limb action detection result in the data frame after the target data frame according to the limb action detection result of the data frame after the target data frame.
3. The method according to claim 2, wherein triggering a video effect corresponding to the body motion detection result in the data frame following the target data frame according to the body motion detection result of the data frame following the target data frame comprises:
if no limb action is detected in the data frame after the target data frame, triggering a corresponding excessive video effect under the condition of no limb action in the data frame after the target data frame;
and if the body action is detected in the data frame behind the target data frame, controlling and displaying the corresponding video effect in the data frame behind the target data frame according to the body action.
4. A method according to any of claims 1-3, wherein the influencing factors of the detection of the limb movement comprise: the shooting environment of the video and the motion state of the limb action.
5. A video-based limb movement detection device, comprising:
the limb action detection module is used for detecting data frames in the video in real time in the video shooting process;
a target data frame determination module, configured to, if a data frame missing a limb motion is detected in the video, take a preset number of data frames after the data frame missing the limb motion as a target data frame, where the limb motion is used to control a video effect;
and the video effect maintaining module is used for acquiring a video effect corresponding to the limb action in the last frame data of the data frame losing the limb action and maintaining the video effect in the data frame losing the limb action and the target data frame.
6. The apparatus of claim 5, further comprising:
and the video effect triggering module is used for triggering a video effect corresponding to the limb action detection result in the data frame after the target data frame according to the limb action detection result of the data frame after the target data frame.
7. The apparatus of claim 6, wherein the video effect trigger module comprises:
a first triggering unit, configured to trigger a corresponding excessive video effect in a case of no limb motion in a data frame following the target data frame if no limb motion is detected in the data frame following the target data frame;
and the second triggering unit is used for controlling and displaying the corresponding video effect in the data frame after the target data frame according to the body action if the body action is detected in the data frame after the target data frame.
8. The apparatus according to any one of claims 5-7, wherein the influencing factors of the detection result of the limb movement comprise: the shooting environment of the video and the motion state of the limb action.
9. A terminal, comprising:
one or more processing devices;
a storage device for storing one or more programs,
when executed by the one or more processing devices, cause the one or more processing devices to implement the video-based limb motion detection method of any one of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processing device, carries out the video-based limb movement detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459981.0A CN111258415B (en) | 2018-11-30 | 2018-11-30 | Video-based limb movement detection method, device, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459981.0A CN111258415B (en) | 2018-11-30 | 2018-11-30 | Video-based limb movement detection method, device, terminal and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111258415A true CN111258415A (en) | 2020-06-09 |
| CN111258415B CN111258415B (en) | 2021-05-07 |
Family
ID=70946584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811459981.0A Active CN111258415B (en) | 2018-11-30 | 2018-11-30 | Video-based limb movement detection method, device, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111258415B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103297742A (en) * | 2012-02-27 | 2013-09-11 | 联想(北京)有限公司 | Data processing method, microprocessor, communication terminal and server |
| US20150221118A1 (en) * | 2014-02-05 | 2015-08-06 | Elena Shaburova | Method for real time video processing for changing proportions of an object in the video |
| CN104853238A (en) * | 2014-11-25 | 2015-08-19 | 苏州乐聚一堂电子科技有限公司 | Combined beat special effect system and combined beat special effect processing method |
| CN104902212A (en) * | 2015-04-30 | 2015-09-09 | 努比亚技术有限公司 | Video communication method and apparatus |
| CN105554429A (en) * | 2015-11-19 | 2016-05-04 | 掌赢信息科技（上海）有限公司 | Video conversation display method and video conversation equipment |
| US20180137632A1 (en) * | 2016-11-15 | 2018-05-17 | Gvbb Holdings S.A.R.L. | System and method of hybrid tracking for match moving |
| CN108833818A (en) * | 2018-06-28 | 2018-11-16 | 腾讯科技（深圳）有限公司 | video recording method, device, terminal and storage medium |
-
2018
- 2018-11-30 CN CN201811459981.0A patent/CN111258415B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103297742A (en) * | 2012-02-27 | 2013-09-11 | 联想(北京)有限公司 | Data processing method, microprocessor, communication terminal and server |
| US20150221118A1 (en) * | 2014-02-05 | 2015-08-06 | Elena Shaburova | Method for real time video processing for changing proportions of an object in the video |
| CN104853238A (en) * | 2014-11-25 | 2015-08-19 | 苏州乐聚一堂电子科技有限公司 | Combined beat special effect system and combined beat special effect processing method |
| CN104902212A (en) * | 2015-04-30 | 2015-09-09 | 努比亚技术有限公司 | Video communication method and apparatus |
| CN105554429A (en) * | 2015-11-19 | 2016-05-04 | 掌赢信息科技（上海）有限公司 | Video conversation display method and video conversation equipment |
| US20180137632A1 (en) * | 2016-11-15 | 2018-05-17 | Gvbb Holdings S.A.R.L. | System and method of hybrid tracking for match moving |
| CN108833818A (en) * | 2018-06-28 | 2018-11-16 | 腾讯科技（深圳）有限公司 | video recording method, device, terminal and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| ADRIENNE HEINRICH; DI GENG; DMITRY ZNAMENSKIY; JELTE PETER VINK;: ""Robust and Sensitive Video Motion Detection for Sleep Analysis"", 《 IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS》 * |
| 刘垚: ""用于视频动作检测的时空多任务神经网络"", 《万方数据知识服务平台》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111258415B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107102936B (en) | Fluency evaluation method, mobile terminal and storage medium | |
| CN108228358B (en) | Method, device, mobile terminal and storage medium for correcting vertical synchronization signal | |
| CN109922265B (en) | Video shooting method and terminal equipment | |
| WO2021169236A1 (en) | Rendering method and apparatus | |
| CN111225138A (en) | Camera control method and device, storage medium and terminal | |
| WO2016197590A1 (en) | Method and apparatus for providing screenshot service on terminal device and storage medium and device | |
| CN111858318B (en) | Response time testing method, device, equipment and computer storage medium | |
| CN113923499B (en) | Display control method, device, equipment and storage medium | |
| CN113395572B (en) | Video processing method and device, storage medium and electronic equipment | |
| CN113253885B (en) | Method, device, equipment, readable storage medium and product for displaying target content | |
| EP4123983A1 (en) | Video stream playing control method and apparatus, and storage medium | |
| WO2023169305A1 (en) | Special effect video generating method and apparatus, electronic device, and storage medium | |
| CN113342230A (en) | Control display method, device, equipment and medium | |
| CN111770374B (en) | Video playing method and device | |
| CN114699767A (en) | Game data processing method, device, medium and electronic equipment | |
| WO2023273562A1 (en) | Video playback method and apparatus, electronic device, and medium | |
| CN109492163B (en) | List display recording method and device, terminal equipment and storage medium | |
| CN113703896A (en) | Event trigger control method and device, electronic equipment and medium | |
| WO2024016924A1 (en) | Video processing method and apparatus, and electronic device and storage medium | |
| CN111258415B (en) | Video-based limb movement detection method, device, terminal and medium | |
| WO2023030325A1 (en) | Buffer processing method and apparatus | |
| CN111263084B (en) | Video-based gesture jitter detection method, device, terminal and medium | |
| CN110489318A (en) | Grasping means, device, storage medium and the terminal of systrace information | |
| CN110225391B (en) | Video playing control method and device, electronic equipment and storage medium | |
| CN114554292A (en) | Method and device for switching visual angle, electronic equipment, storage medium and program product |
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 |