CN111736707A - Picture switching method and device - Google Patents
Picture switching method and device Download PDFInfo
- Publication number
- CN111736707A CN111736707A CN202010819903.8A CN202010819903A CN111736707A CN 111736707 A CN111736707 A CN 111736707A CN 202010819903 A CN202010819903 A CN 202010819903A CN 111736707 A CN111736707 A CN 111736707A
- Authority
- CN
- China
- Prior art keywords
- image
- gesture
- user
- finger
- palm
- 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.)
- Pending
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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention provides a picture switching method and a picture switching device, wherein the picture switching method comprises the following steps: when a picture corresponding to an input source signal is displayed on terminal equipment, acquiring gesture images shot by a plurality of cameras from different view angles in a specific area; comparing the background image corresponding to the specific area with the gesture image to identify a foreground image comprising a hand of the user from the gesture image; identifying a palm image and a finger image of a user's hand from the foreground image; recognizing a user gesture from the palm image and the finger image; and when the user gesture is matched with the predefined gesture, switching the input source signal, so that the terminal equipment is switched to display a picture corresponding to other input source signals. According to the embodiment of the invention, the user can realize the input signal source switching of the terminal equipment through the gesture, so that the picture switching is realized, and the picture is switched through the gesture of the user, so that the terminal equipment can be protected, and the user operation experience is good.
Description
Technical Field
The present invention relates to the multimedia technology field, and in particular, to a picture switching method and a picture switching apparatus.
Background
With the development of electronic technology, touch screens have been widely used in terminal devices. In a terminal device capable of displaying a screen, when a user wants to switch the screen, the screen can be switched by performing operations such as sliding and clicking on a touch screen.
However, the touch screen based screen switching method cannot meet the user requirements, and the touch screen method is easy to damage the terminal device, and particularly for the terminal device used in public, the terminal device is usually higher in price and high in replacement cost, so that in order to meet the changing user personalized requirements, a user gesture based screen switching method is urgently needed, so that the user can conveniently realize screen switching through gestures, the terminal device can be protected, and the user operation experience is good.
Disclosure of Invention
In view of the above problems, embodiments of the present invention are proposed to provide a picture switching method and a corresponding picture switching apparatus that overcome or at least partially solve the above problems.
In order to solve the above problem, an embodiment of the present invention discloses a method for switching a picture, where the method includes:
when a picture corresponding to an input source signal is displayed on terminal equipment, acquiring gesture images shot by a plurality of cameras from different view angles in a specific area;
comparing the background image corresponding to the specific area with the gesture image to identify a foreground image comprising a hand of the user from the gesture image;
identifying a palm image and a finger image of a user's hand from the foreground image;
recognizing a user gesture from the palm image and the finger image;
and when the user gesture is matched with the predefined gesture, switching the input source signal, so that the terminal equipment is switched to display a picture corresponding to other input source signals.
Optionally, the recognizing a palm image and a finger image of the user's hand from the foreground image comprises:
carrying out corrosion operation on the foreground image by adopting a preset corrosion core;
performing expansion operation on the foreground image subjected to the corrosion operation by adopting a preset expansion core;
when the corrosion operation and the expansion operation reach preset times, obtaining a palm image of the hand of the user from the foreground image;
and carrying out exclusive OR operation on the palm image and the foreground image, and obtaining a finger image of the hand of the user from the foreground image.
Optionally, after the exclusive or operation is performed on the palm image and the foreground image, and a finger image of a hand of a user is obtained from the foreground image, the method further includes:
and carrying out corrosion operation on the finger part by adopting a preset corrosion core.
Optionally, the recognizing a user gesture from the palm image and the finger image comprises:
identifying a palm center from the palm image;
recognizing a part of a first designated position in the finger image as a fingertip of the finger, and recognizing a part of a second designated position in the finger image as a root of the finger;
obtaining an internal reference and an external reference of the camera by adopting a Zhangyingyou calibration method;
drawing a user gesture based on the internal reference and the external reference of the camera, the palm, the fingertips and the root.
Optionally, the first designated location is a center of gravity of a front 1/4 of the finger image and the second designated location is a center of gravity of a rear 1/4 of the finger image.
Optionally, the method further comprises:
acquiring a historical gesture image during previous gesture recognition;
and when the number of the historical finger images corresponding to the historical gesture images is different from the number of the finger images corresponding to the gesture images, ignoring the finger images which do not match with the historical finger images in the historical gesture images.
Optionally, the predefined gesture has a corresponding webcam, and when the user gesture is matched with the predefined gesture, the input source signal is switched, so that the terminal device is switched to display a picture corresponding to another input source signal, including:
determining a target predefined gesture matched with the user gesture from a preset gesture library;
and switching the input source signal to the video stream shot by the target network camera corresponding to the target predefined gesture so as to switch to display the picture corresponding to the video stream shot by the target network camera.
The embodiment of the invention also discloses an all-in-one machine supporting the picture switching, the all-in-one machine is connected with the camera and the input source signal, and the all-in-one machine comprises:
the display module is used for acquiring gesture images shot by a plurality of cameras from different view angles in a specific area when displaying a picture corresponding to an input source signal;
the comparison module is used for comparing the background image corresponding to the specific area with the gesture image so as to identify a foreground image comprising a hand of a user from the gesture image;
the first recognition module is used for recognizing a palm image and a finger image of a hand of a user from the foreground image;
a second recognition module for recognizing a user gesture from the palm image and the finger image;
and the switching module is used for switching the input source signals when the user gesture is matched with the predefined gesture, so that the images corresponding to other input source signals are displayed by switching.
The embodiment of the invention also discloses an electronic device, which comprises: a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the picture switching method.
The embodiment of the invention also discloses a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program realizes the steps of the picture switching method when being executed by a processor.
The embodiment of the invention has the following advantages:
the invention provides a picture switching method and a picture switching device, when a picture corresponding to an input source signal is displayed on a terminal device, gesture images shot by a plurality of cameras from different visual angles in a specific area are obtained, a foreground image comprising a hand of a user is identified from the gesture images by comparing a background image and the gesture images corresponding to the specific area, the hand, a palm image and a finger image of the user are identified from the foreground image, and the user gesture is identified from the palm image and the finger image, wherein when the user gesture is matched with a predefined gesture, the input source signal is switched, so that the terminal device is switched to display pictures corresponding to other input source signals. According to the embodiment of the invention, the user can realize the input signal source switching of the terminal equipment through the gesture, so that the picture switching is realized, and the picture is switched through the gesture of the user, so that the terminal equipment can be protected, and the user operation experience is good.
Drawings
FIG. 1 is a flowchart illustrating steps of an embodiment of a method for switching frames according to the present invention;
FIG. 2 is a block diagram of an embodiment of an all-in-one machine of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a screen switching method according to the present invention is shown, which may specifically include the following steps:
step 101, when a picture corresponding to an input source signal is displayed on a terminal device, acquiring gesture images shot by a plurality of cameras from different perspectives in a specific area.
The terminal equipment of the embodiment of the invention can be an all-in-one machine. Specifically, the all-in-one machine is an integrated device integrating functions of windows, recorded broadcasting and the like, and comprises all functions of recorded broadcasting and plug-ins for additionally operating recorded broadcasting on the windows, such as live broadcasting, recording, pausing, voting, signal switching, volume adjustment and the like. In a specific application, the all-in-one machine of the embodiment of the invention can be put into a live broadcast system for use, specifically, the live broadcast system comprising the all-in-one machine can be deployed in a specified place in advance, the all-in-one machine can be connected with a plurality of input source signals, and a video picture corresponding to the input source signals is displayed on the all-in-one machine. For example, a live broadcast system for examination monitoring can be deployed in an examination room, and is used for shooting the experiment operation process of students through a network camera in the examination process, and then inputting the shot operation process into the all-in-one machine as an input source signal so as to display the pictures of the operation instruments of the students on the all-in-one machine.
In the embodiment of the invention, the all-in-one machine is connected with the plurality of cameras, for example, the plurality of cameras can be two cameras for recording the hand gesture switching of the user. When a user wants to switch the picture displayed on the all-in-one machine, the gesture can be set in a specific area shot by the camera, so that the camera can acquire the gesture image of the user. The gesture image is a depth image with depth information.
And 102, comparing the background image corresponding to the specific area with the gesture image to identify a foreground image comprising the hand of the user from the gesture image.
In the embodiment of the invention, in order to improve the gesture recognition efficiency, the camera connected with the all-in-one machine is fixed at a specific position, so that a specific area is fixed after the camera is fixed, and then picture information is collected for the specific area to be used as a background image. Of course, if the kiosk is moved or the camera is adjusted in position, the position of the specific area will be changed accordingly, and new picture information will be collected for the specific area again as a background image.
After the gesture image is acquired, by comparing the background image with the gesture image, the pixels which are different from the background image by a certain threshold value are taken out from the gesture image and are used as foreground images, namely the images of the hands of the user. Because the background image in the embodiment of the invention can be processed in advance, the recognition efficiency of the foreground image can be improved when the foreground image is extracted based on the background image and the gesture image.
And 103, identifying a palm image and a finger image of the hand of the user from the foreground image.
In an exemplary embodiment, the step 103 of recognizing the palm image and the finger image of the hand of the user from the foreground image includes:
carrying out corrosion operation on the foreground image by adopting a preset corrosion core;
performing expansion operation on the foreground image subjected to the corrosion operation by adopting a preset expansion core;
when the corrosion operation and the expansion operation reach preset times, obtaining a palm image of the hand of the user from the foreground image;
and carrying out exclusive OR operation on the palm image and the foreground image, and obtaining a finger image of the hand of the user from the foreground image.
In the embodiment of the invention, after the foreground image is obtained, the palm image and the finger image are obtained through the corrosion operation and the expansion operation so as to segment the hand of the user in the foreground image. Wherein the erosion operation of the image is to use an erosion kernel, such as a 5x5 matrix, and the convolution of the image takes the minimum value in the matrix for the pixel at the center of the erosion kernel, the dilation operation of the image is to use a dilation kernel, and the convolution of the image takes the maximum value in the matrix for the pixel at the center of the dilation kernel.
Specifically, in the embodiment of the present invention, a first corrosion operation is performed on the foreground image, and a second expansion operation is performed, so that noise in the foreground image can be removed, then a preset number of corrosion operations are performed, the finger image is corroded away, and the palm image is left. Optionally, in the embodiment of the present invention, the finger image of the foreground image may be obtained by performing an exclusive or operation on the palm image and the foreground image.
In an alternative example, using a kernel of 5x5, the preset number of times is 10, and the image effect is the best.
In an exemplary embodiment, after the exclusive-oring the palm image and the foreground image and obtaining the finger image of the user hand from the foreground image, the method further includes:
and carrying out corrosion operation on the finger part by adopting a preset corrosion core.
In the embodiment of the invention, the obtained finger image can be corroded once, so that the obtained finger image is smooth, the fluctuation of the unsmooth pixels at the edge on the candidate fingertip positioning is avoided, and the accuracy of gesture recognition is further ensured.
After the palm image and the finger image are segmented from the foreground image, the user gesture can be further recognized based on the palm image and the finger image, wherein the user gesture can reflect the position and the orientation of the finger of the user.
In an exemplary embodiment, the recognizing the user gesture from the palm image and the finger image includes:
identifying a palm center from the palm image;
recognizing a part of a first designated position in the finger image as a fingertip of the finger, and recognizing a part of a second designated position in the finger image as a root of the finger;
obtaining an internal reference and an external reference of the camera by adopting a Zhangyingyou calibration method;
drawing a user gesture based on the internal reference and the external reference of the camera, the palm, the fingertips and the root.
In the embodiment of the invention, the palm center is identified from the palm image, then the internal reference and the external reference of the camera are obtained based on the Zhang Zhengyou calibration method by combining the finger tip and the finger root identified from the finger image, and the palm center, the finger root and the finger tip can be connected to draw the gesture of the user. Preferably, in the embodiment of the present invention, a portion at a first designated position in the finger image may be taken as a fingertip of the finger, and a portion at a second designated position in the finger image may be taken as a root of the finger.
Optionally, the first designated location is a center of gravity of a front 1/4 of the finger image and the second designated location is a center of gravity of a rear 1/4 of the finger image.
In the embodiment of the present invention, in order to obtain stability of the finger information, the center of gravity of the front 1/4 of each finger image may be taken as the fingertip of the finger, and the center of gravity of the rear 1/4 may be taken as the root of the finger. In a preferred example, in order to further improve the extraction accuracy, the embodiment of the present invention may further prompt the user to input personal information, such as age, sex, height, and the like, so that the specific positions of the first specified position and the second specified position may be adjusted in combination with the personal information.
In an exemplary embodiment, the method further comprises:
acquiring a historical gesture image during previous gesture recognition;
and when the number of the historical finger images corresponding to the historical gesture images is different from the number of the finger images corresponding to the gesture images, ignoring the finger images which do not match with the historical finger images in the historical gesture images.
In the embodiment of the invention, because the visual angles of the two cameras are different, the phenomenon that the number of the finger images obtained from the gesture images is different can occur, if the phenomenon occurs, the newly-appeared finger image can be obtained as the specific finger image according to the historical gesture image during the previous gesture recognition, and the specific finger image is matched and ignored at the time.
And 105, switching the input source signals when the user gesture is matched with the predefined gesture, so that the terminal equipment is switched to display pictures corresponding to other input source signals.
After the user gesture is determined, the user gesture can be matched with the predefined gesture, if the user gesture is matched with the predefined gesture, the input source signals can be switched on the all-in-one machine, so that pictures corresponding to signals from other input sources are displayed on the all-in-one machine, and therefore the pictures can be switched.
In an exemplary embodiment, switching the input source signal when the user gesture matches a predefined gesture, so that the terminal device switches to display a picture corresponding to the other input source signal, includes:
determining a target predefined gesture matched with the user gesture from a preset gesture library;
and switching the input source signal to the video stream shot by the target network camera corresponding to the target predefined gesture so as to switch to display the picture corresponding to the video stream shot by the target network camera.
Each predefined gesture of the embodiment of the present invention may be set to have a corresponding webcam. After the current user gesture of the user is recognized, the user gesture is compared with the predefined gesture, a target predefined gesture corresponding to the user gesture can be determined, then an input source signal (video stream) corresponding to the corresponding network camera is determined according to the target predefined gesture, finally, an internal program of the all-in-one machine displays the video stream acquired by the corresponding network camera on a back plate of the all-in-one machine, and the purpose of switching the pictures of the all-in-one machine is achieved.
In a specific application scenario, the embodiment of the invention can be applied to examination monitoring, and an invigilator teacher looks at the all-in-one machine to show a video stream (input signal source) of a student examination shot by a network camera, so that a picture of an examinee operating experimental instrument is shown on the all-in-one machine.
By applying the embodiment of the invention, when a picture corresponding to an input source signal is displayed on the all-in-one machine, gesture images shot by a plurality of cameras from different visual angles in a specific area are obtained, a foreground image comprising a hand of a user is identified from the gesture images by comparing a background image and the gesture images corresponding to the specific area, a palm image and a finger image of the hand of the user are identified from the foreground image, and a user gesture is identified from the palm image and the finger image, wherein the input source signal is switched when the user gesture is matched with a predefined gesture, so that the all-in-one machine is switched to display pictures corresponding to other input source signals. According to the embodiment of the invention, the user can realize the switching of the input signal source of the all-in-one machine through the gesture, so that the switching of the pictures is realized, and the pictures are switched through the gesture of the user, so that not only can the terminal equipment be protected, but also the user operation experience is good. The gesture recognition method and the gesture recognition device are high in gesture recognition accuracy rate, and smooth interaction experience is provided for users.
According to the embodiment of the invention, the gesture recognition model can be obtained by counting the sample characteristics and deeply learning the neural network technology, so that the gesture of the user can be obtained by recognizing the gesture image based on the gesture recognition model. Specifically, the gesture recognition model of the embodiment of the present invention may be obtained by collecting a training gesture image of a plurality of live-action shot images, and then inputting the key point positions of the training gesture image, i.e., palm center, finger root, finger tip, and the like, to the gesture recognition model for training until reaching the end condition, so as to obtain a trained gesture recognition model for recognizing the gesture of the user. In an optional example, the gesture image of the embodiment of the present invention may be a depth image with depth information, and then the gesture image may be input to a gesture recognition model to perform recognition of a key point position, the all-in-one machine of the embodiment of the present invention may further include an infrared ray, the depth information may be determined according to a time when the infrared ray is emitted to a hand, and then the depth information is input to the gesture recognition model to perform training and recognition of a user gesture, and by this way, when the user considers that the gesture recognition is not accurate enough, the infrared ray on the all-in-one machine is turned on, and the gesture recognition is performed by combining the depth information acquired based on the infrared ray, not only more choices are made for the user, but also the gesture recognition accuracy is improved to some extent.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 2, a block diagram of an embodiment of an all-in-one machine according to the present invention is shown, where the all-in-one machine is connected to a camera and an input source by signals, and the all-in-one machine may specifically include the following modules:
the display module 201 is configured to obtain gesture images shot by multiple cameras from different viewpoints in a specific area when a picture corresponding to an input source signal is displayed;
a comparing module 202, configured to compare the background image corresponding to the specific region with the gesture image, so as to identify a foreground image including a hand of the user from the gesture image;
a first recognition module 203, configured to recognize a palm image and a finger image of a hand of a user from the foreground image;
a second recognition module 204 for recognizing a user gesture from the palm image and the finger image;
a switching module 205, configured to switch the input source signal when the user gesture matches the predefined gesture, so as to switch to display a picture corresponding to another input source signal.
In a preferred embodiment of the present invention, the first identifying module 203 is configured to perform a corrosion operation on the foreground image by using a preset corrosion check; performing expansion operation on the foreground image subjected to the corrosion operation by adopting a preset expansion core; when the corrosion operation and the expansion operation reach preset times, obtaining a palm image of the hand of the user from the foreground image; and carrying out exclusive OR operation on the palm image and the foreground image, and obtaining a finger image of the hand of the user from the foreground image.
In a preferred embodiment of the present invention, the first identification module 203 is configured to perform a corrosion operation on the finger portion by using a predetermined corrosion check.
In a preferred embodiment of the present invention, the second identifying module 204 is configured to identify a palm center from the palm image; recognizing a part of a first designated position in the finger image as a fingertip of the finger, and recognizing a part of a second designated position in the finger image as a root of the finger; obtaining an internal reference and an external reference of the camera by adopting a Zhangyingyou calibration method; drawing a user gesture based on the internal reference and the external reference of the camera, the palm, the fingertips and the root.
In a preferred embodiment of the present invention, the first designated location is the center of gravity of the front 1/4 of the finger image and the second designated location is the center of gravity of the rear 1/4 of the finger image.
In a preferred embodiment of the present invention, the first recognition module 203 is configured to obtain a historical gesture image in a previous gesture recognition; and when the number of the historical finger images corresponding to the historical gesture images is different from the number of the finger images corresponding to the gesture images, ignoring the finger images which do not match with the historical finger images in the historical gesture images.
In a preferred embodiment of the present invention, the predefined gesture has a corresponding webcam, and the switching module 205 is configured to determine a target predefined gesture matching the user gesture from a preset gesture library; and switching the input source signal to the video stream shot by the target network camera corresponding to the target predefined gesture so as to switch to display the picture corresponding to the video stream shot by the target network camera.
For the all-in-one machine embodiment, since it is basically similar to the method embodiment, the description is simple, and for relevant points, reference may be made to the partial description of the method embodiment.
An embodiment of the present invention further provides an electronic device, including: the method comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein when the computer program is executed by the processor, each process of the picture switching method embodiment is realized, the same technical effect can be achieved, and the description is omitted for avoiding repetition.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements each process of the foregoing image switching method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal 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, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The above detailed description is provided for a picture switching method and a picture switching apparatus provided by the present invention, and the principle and the implementation of the present invention are explained in the present document by applying specific examples, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for switching pictures, the method comprising:
when a picture corresponding to an input source signal is displayed on terminal equipment, acquiring gesture images shot by a plurality of cameras from different view angles in a specific area;
comparing the background image corresponding to the specific area with the gesture image to identify a foreground image comprising a hand of the user from the gesture image;
identifying a palm image and a finger image of a user's hand from the foreground image;
recognizing a user gesture from the palm image and the finger image;
and when the user gesture is matched with the predefined gesture, switching the input source signal, so that the terminal equipment is switched to display a picture corresponding to other input source signals.
2. The method of claim 1, wherein the identifying palm and finger images of the user's hand from the foreground image comprises:
carrying out corrosion operation on the foreground image by adopting a preset corrosion core;
performing expansion operation on the foreground image subjected to the corrosion operation by adopting a preset expansion core;
when the corrosion operation and the expansion operation reach preset times, obtaining a palm image of the hand of the user from the foreground image;
and carrying out exclusive OR operation on the palm image and the foreground image, and obtaining a finger image of the hand of the user from the foreground image.
3. The method of claim 2, wherein after said exclusive-oring the palm image and the foreground image, deriving a finger image of the user's hand from the foreground image, the method further comprises:
and carrying out corrosion operation on the finger part by adopting a preset corrosion core.
4. The method of claim 1, wherein the recognizing a user gesture from the palm image and the finger image comprises:
identifying a palm center from the palm image;
recognizing a part of a first designated position in the finger image as a fingertip of the finger, and recognizing a part of a second designated position in the finger image as a root of the finger;
obtaining an internal reference and an external reference of the camera by adopting a Zhangyingyou calibration method;
drawing a user gesture based on the internal reference and the external reference of the camera, the palm, the fingertips and the root.
5. The method of claim 4, wherein the first designated location is a center of gravity of a front 1/4 of the finger image and the second designated location is a center of gravity of a rear 1/4 of the finger image.
6. The method of claim 4, further comprising:
acquiring a historical gesture image during previous gesture recognition;
and when the number of the historical finger images corresponding to the historical gesture images is different from the number of the finger images corresponding to the gesture images, ignoring the finger images which do not match with the historical finger images in the historical gesture images.
7. The method according to claim 1 or 6, wherein the predefined gesture has a corresponding webcam, and when the user gesture matches the predefined gesture, the input source signal is switched, so that the terminal device is switched to show a picture corresponding to the other input source signal, the method comprises:
determining a target predefined gesture matched with the user gesture from a preset gesture library;
and switching the input source signal to the video stream shot by the target network camera corresponding to the target predefined gesture so as to switch to display the picture corresponding to the video stream shot by the target network camera.
8. An all-in-one machine supporting picture switching is characterized in that the all-in-one machine is in signal connection with a camera and an input source, and the all-in-one machine comprises:
the display module is used for acquiring gesture images shot by a plurality of cameras from different view angles in a specific area when displaying a picture corresponding to an input source signal;
the comparison module is used for comparing the background image corresponding to the specific area with the gesture image so as to identify a foreground image comprising a hand of a user from the gesture image;
the first recognition module is used for recognizing a palm image and a finger image of a hand of a user from the foreground image;
a second recognition module for recognizing a user gesture from the palm image and the finger image;
and the switching module is used for switching the input source signals when the user gesture is matched with the predefined gesture, so that the images corresponding to other input source signals are displayed by switching.
9. An electronic device, comprising: processor, memory and computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the picture switching method according to any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the picture switching method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010819903.8A CN111736707A (en) | 2020-08-14 | 2020-08-14 | Picture switching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010819903.8A CN111736707A (en) | 2020-08-14 | 2020-08-14 | Picture switching method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111736707A true CN111736707A (en) | 2020-10-02 |
Family
ID=72658492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010819903.8A Pending CN111736707A (en) | 2020-08-14 | 2020-08-14 | Picture switching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111736707A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116684647A (en) * | 2023-06-27 | 2023-09-01 | 上海宝玖数字科技有限公司 | Equipment control method, system and equipment in video real-time transmission scene |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130081785A (en) * | 2012-01-10 | 2013-07-18 | 주식회사 시우엘케이 | Palm pad having gesture recognition function |
| CN103971102A (en) * | 2014-05-21 | 2014-08-06 | 南京大学 | Static gesture recognition method based on finger contour and decision-making trees |
| KR101526426B1 (en) * | 2013-12-31 | 2015-06-05 | 현대자동차 주식회사 | Gesture recognize apparatus and method |
| CN104699233A (en) * | 2014-04-14 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Screen operation control method and system |
| CN108256504A (en) * | 2018-02-11 | 2018-07-06 | 苏州笛卡测试技术有限公司 | A kind of Three-Dimensional Dynamic gesture identification method based on deep learning |
-
2020
- 2020-08-14 CN CN202010819903.8A patent/CN111736707A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130081785A (en) * | 2012-01-10 | 2013-07-18 | 주식회사 시우엘케이 | Palm pad having gesture recognition function |
| KR101526426B1 (en) * | 2013-12-31 | 2015-06-05 | 현대자동차 주식회사 | Gesture recognize apparatus and method |
| CN104699233A (en) * | 2014-04-14 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Screen operation control method and system |
| CN103971102A (en) * | 2014-05-21 | 2014-08-06 | 南京大学 | Static gesture recognition method based on finger contour and decision-making trees |
| CN108256504A (en) * | 2018-02-11 | 2018-07-06 | 苏州笛卡测试技术有限公司 | A kind of Three-Dimensional Dynamic gesture identification method based on deep learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116684647A (en) * | 2023-06-27 | 2023-09-01 | 上海宝玖数字科技有限公司 | Equipment control method, system and equipment in video real-time transmission scene |
| CN116684647B (en) * | 2023-06-27 | 2024-01-26 | 上海宝玖数字科技有限公司 | Equipment control method, system and equipment in video real-time transmission scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105933607B (en) | A kind of take pictures effect method of adjustment and the mobile terminal of mobile terminal | |
| CN107944409B (en) | Video analysis method and device capable of distinguishing key actions | |
| CN108985176B (en) | Image generation method and device | |
| CN107909022B (en) | Video processing method and device, terminal equipment and storage medium | |
| CN109034069B (en) | Method and apparatus for generating information | |
| KR20220058857A (en) | Learning situation analysis method and apparatus, electronic device and storage medium, computer program | |
| US12008167B2 (en) | Action recognition method and device for target object, and electronic apparatus | |
| CN108921070B (en) | Image processing method, model training method and corresponding device | |
| CN112672208B (en) | Video playing method, device, electronic equipment, server and system | |
| US10015445B1 (en) | Room conferencing system with heat map annotation of documents | |
| KR20140045897A (en) | Device and method for media stream recognition based on visual image matching | |
| JP2007265125A (en) | Content display | |
| CN112115894B (en) | Training method and device of hand key point detection model and electronic equipment | |
| CN111401238B (en) | Method and device for detecting character close-up fragments in video | |
| CN113934297B (en) | Interaction method and device based on augmented reality, electronic equipment and medium | |
| KR20130088493A (en) | Method for providing user interface and video receving apparatus thereof | |
| CN107368181B (en) | Gesture recognition method and device | |
| CN111818385B (en) | Video processing method, video processing device and terminal equipment | |
| EP3885934A1 (en) | Video search method and apparatus, computer device, and storage medium | |
| CN111736707A (en) | Picture switching method and device | |
| CN113674313A (en) | Pedestrian tracking method and device, storage medium and electronic equipment | |
| Miniakhmetova et al. | An approach to personalized video summarization based on user preferences analysis | |
| JP6397508B2 (en) | Method and apparatus for generating a personal input panel | |
| CN115035947A (en) | Protein structure modeling method and device, electronic device and storage medium | |
| CN114639056A (en) | Live content identification method and device, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |