A method for controlling a display device based on gestures

Abstract

The application discloses a method for controlling a display device based on a gesture, comprising: acquiring bone node information of a manipulator and bone node information of a manipulating hand in an image; generating a feature vector describing a hand posture of the manipulator according to the bone node information of the manipulating hand; matching the feature vector describing the hand posture of the manipulator with a gesture model in a gesture model library; classifying the image into a frame image with a gesture category and a frame image without the gesture category according to a matching result; obtaining gesture category information in the frame image with the gesture category; acquiring gesture category information and hand position information in the frame image without the gesture category according to the bone node information of the manipulator and the gesture category information of front and back frames of the frame image without the gesture category; and generating an instruction for controlling the display device according to the gesture category information and the hand position information in the frame image with the gesture category and the frame image without the gesture category.

Description

Technical Field

[0001] This invention relates to the field of electronic information technology, and in particular to a method for controlling a display device based on gestures. Background Technology

[0002] With the rapid development of information technology, distributed display devices have been widely used in public places, commercial displays, home entertainment, and many other fields. However, traditional control methods for display devices, such as physical buttons and remote controls, are cumbersome and not intuitive. In recent years, although vision recognition-based control methods have emerged, sometimes the triggering object has not stopped moving even after the gesture has been completed, often resulting in judgment delays or misjudgments. Their accuracy and robustness still need improvement. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this disclosure proposes a method for controlling a display device based on gestures in a first aspect, comprising: acquiring skeletal node information of a manipulator and skeletal node information of a manipulator's hand in an image; generating a feature vector describing the manipulator's hand posture based on the skeletal node information of the manipulator's hand; matching the feature vector describing the manipulator's hand posture with a gesture model in a gesture model library; dividing the image into frame images with gesture categories and frame images without gesture categories based on the matching result; obtaining gesture category information in the frame images with gesture categories; acquiring gesture category information and hand position information in the frame images without gesture categories based on the manipulator's skeletal node information and the gesture category information of the preceding and following frames of the frame images without gesture categories; and generating instructions to control the display device based on the gesture category information and hand position information of the frame images with gesture categories and the gesture category information and hand position information of the frame images without gesture categories.

[0004] Preferably, it also includes: capturing real-time skeletal node information of the operator through a depth camera, the skeletal node information including the three-dimensional coordinates of the joints and the connection relationship between the joints.

[0005] Preferably, the operator's hand skeletal node information in the gesture-category frame image is calculated by interpolation using the skeletal node information of the operator in the gesture-category frame image before and after the gesture-category frame image.

[0006] Preferably, the operator's hand skeletal node information in the non-gesture category frame image is matched with the gesture model in the gesture model library to obtain the gesture category of the operator in the non-gesture category frame image.

[0007] Preferably, the wrist node position of the operator in the non-gesture category frame image is obtained based on the skeletal node information of the operator and the skeletal node information of the operator's hand; and the hand position information of the operator in the non-gesture category frame image is obtained based on the wrist node position of the operator in the non-gesture category frame image.

[0008] Preferably, the gesture category information in the gesture category frames before and after the frame image without a gesture category is compared. If the gesture category information of the frame before and after the frame belongs to the same gesture category, then it is determined that the gesture information in the frame image without a gesture category is also the same as the gesture category information of the frame before and after the frame.

[0009] Preferably, if the gesture category information of the preceding and following frames belongs to two consecutive different gesture categories, then it is determined that the gesture category information in the frame without a gesture category is the same as the gesture category information of the preceding frame or the gesture category information of the following frame.

[0010] Preferably, gestures with and without gesture category frames are classified into first-level response gesture one and second-level response gesture two. The displacement change data of gesture one and gesture two of the same hand of the operator between frames are obtained. When the displacement change data of gesture one meets the condition for triggering gesture two, it is determined whether the displacement change data of gesture two meets the condition for triggering menu display. If it does, an instruction to control the display device is generated.

[0011] In a second aspect, this disclosure provides an apparatus for controlling a display device based on gestures, comprising: an acquisition unit for acquiring skeletal node information of the operator and skeletal node information of the operator's hand in an image;

[0012] The matching unit generates a feature vector describing the operator's hand posture based on the skeletal node information of the operator's hand, matches the feature vector describing the operator's hand posture with the gesture models in the gesture model library, and divides the image into frame images with gesture categories and frame images without gesture categories based on the matching result, thereby obtaining the gesture category information in the frame images with gesture categories; the judgment unit obtains the gesture category information and hand position information in the frame images without gesture categories based on the operator's skeletal node information and the gesture category information of the frames before and after the frame images without gesture categories; the generation unit generates instructions to control the display device based on the gesture category information and hand position information of the frame images with gesture categories and the gesture category information and hand position information of the frame images without gesture categories.

[0013] In a third aspect, this disclosure provides a computer-readable medium storing a computer program that is loaded and executed by a processing module to implement the steps of any of the methods described above.

[0014] Some technical advantages of this disclosure are as follows: A method for controlling a display device based on gestures includes: acquiring skeletal node information of the operator and the skeletal node information of the operator's hand in an image; generating a feature vector describing the operator's hand posture based on the skeletal node information of the operator's hand; matching the feature vector describing the operator's hand posture with a gesture model in a gesture model library; dividing the image into frames with gesture categories and frames without gesture categories based on the matching result; obtaining gesture category information in frames with gesture categories; acquiring gesture category information and hand position information in frames without gesture categories based on the operator's skeletal node information and the gesture category information of the preceding and following frames of frames without gesture categories; and generating instructions to control the display device based on the gesture category information and hand position information of frames with and without gesture categories. By combining the gesture posture and hand position information of frames without gesture categories, the display device responds to the operation corresponding to the gesture posture more accurately and quickly, avoiding response delays. Ultimately, it can quickly and accurately control distributed display devices, avoiding accidental triggering of distributed display devices or delayed response of display devices due to delays or errors in gesture judgment. Attached Figure Description

[0015] To better understand the technical solutions of this disclosure, reference can be made to the following accompanying drawings, which are used to assist in the illustration of the prior art or embodiments. These drawings selectively illustrate the products or methods involved in the prior art or some embodiments of this disclosure. The basic information of these drawings is as follows:

[0016] Figure 1 This is a flowchart of one embodiment of a gesture-based method for controlling a display device disclosed herein. Detailed Implementation

[0017] The following will further describe the technical means or effects involved in this disclosure. Obviously, the provided embodiments (or implementation methods) are only some of the implementation methods covered by this disclosure, and not all of them. Based on the embodiments in this disclosure and the explicit or implicit descriptions in the figures and text, all other embodiments that can be obtained by those skilled in the art without creative effort will be within the scope of protection claimed in this disclosure.

[0018] In existing methods for gesture-controlled large screens and similar scenarios, the performance of computer vision algorithms can be affected by factors such as lighting conditions and the speed of hand movements. Therefore, during image capture, some gesture images may be blurry, or the arm movement may be too fast, resulting in blurred gestures in the image. This can lead to delays and accidental touches when controlling large screens with gestures. For example, when using a gesture like waving to the right to turn pages, sometimes a quick rightward wave may not trigger a page-turning action on the display device, or the page may turn after a short delay. This can result in judgment errors or response delays.

[0019] In current gesture recognition processes, frames that are blurry or lack a gesture category are discarded. This can lead to information gaps in the accuracy and timeliness of gesture recognition during continuous processes.

[0020] To address this, this disclosure provides a gesture-based method for controlling display devices. This method can be applied in various industries and other scenarios requiring rapid and precise human-computer interaction through controlling large screens, such as emergency command and dispatch centers, public security command and dispatch centers, traffic command and dispatch centers, energy command and dispatch centers, and smart city command and dispatch centers. By controlling the large screen, the method controls the dispatch system, for example, switching distributed signal sources or taking over the mouse within a signal source, thereby enabling arbitrary operations on the content within the signal source. Command centers, as the central brain of command and dispatch control, play a crucial role in social governance and people's livelihood development, requiring high accuracy and speed in operation. The gesture-based method of this disclosure eliminates the need for any complex control devices or wearable sensors. It relies solely on the recognition of live human behavior to quickly and accurately take over and control the large screen in the command center. Simple air gestures efficiently enable rapid and precise interactive operations such as signal input, switching, and scaling between the user and the large screen content. Of course, this method can also be applied to general application scenarios with lower requirements, such as page turning in a PowerPoint presentation.

[0021] An exemplary system architecture for a gesture-based control display device disclosed herein can be applied. The system architecture may include a camera with a pan-tilt-zoom (PTZ) sensor, a server, and a display device. For example, the display device is a large screen. The PTZ camera is connected to the server via a serial cable and a USB cable, and the server is then connected to the display device via a network cable. Image information captured by the camera is transmitted to the server via the USB cable. The server processes, analyzes, and makes decisions based on the received image information, generating information or commands. The server may also send the information to a distributed scheduling and image management platform via the network port. The distributed scheduling and image management platform receives the information and displays corresponding operation feedback on the large screen.

[0022] Display devices generally require large screens, multiple colors, high brightness, and high resolution. For example, a display device is a large-screen display, referring to the large screen in a direct-view color television or a rear-projection television; typically, the diagonal size of the screen is over 40 inches. The display surface of a large-screen display can be flat or curved. Large-screen display devices can also be tiled, and there are no further restrictions.

[0023] In this embodiment, the camera with a gimbal is located directly above the large screen. The gimbal is the device that supports the camera.

[0024] The target user can interact with the server via a camera using gestures, and then the server interacts with the large screen to achieve gesture-based control of the large screen. The server can be a single server, a server cluster consisting of several servers, or a cloud computing center. The server can provide various services to the display device. For different applications on the display device, the server can be considered a backend server providing corresponding network services. Therefore, the method disclosed in this application can be considered to be primarily executed by the server side.

[0025] In one embodiment of this disclosure, an application scenario includes a large screen, a pan-tilt-zoom camera positioned above the large screen, and an operable area in front of the large screen. The operable area is roughly a ring-shaped region. The operator can control the large screen within this operable area. If outside the operable area, for example, if too far from the large screen, gesture recognition may fail, potentially leading to control errors. If too close to the large screen, the operator may not be able to observe the entire content, hindering screen operation. In this embodiment, the large screen is 10 meters wide, and the operable area is a ring-shaped region ranging from 3 to 12 meters from the large screen.

[0026] like Figure 1 The present disclosure illustrates a method for controlling a display device based on gestures, comprising:

[0027] S10: Obtain the skeletal node information of the operator and the skeletal node information of the operator's hand in the image;

[0028] S20: Based on the skeletal node information of the operator, generate a feature vector describing the operator's hand posture, match the feature vector describing the operator's hand posture with the gesture model in the gesture model library, and divide the image into frame images with gesture category and frame images without gesture category based on the matching result, and obtain the gesture category information in the frame images with gesture category.

[0029] S30: Based on the operator's skeletal node information and the gesture category information of the preceding and following frames of the non-gesture category frame image, obtain the gesture category information and hand position information in the non-gesture category frame image;

[0030] S40: Generate instructions to control the display device based on the gesture category information and hand position information of the frame image with gesture category and the gesture category information and hand position information of the frame image without gesture category.

[0031] S10: Obtain the skeletal node information of the operator and the skeletal node information of the operator's hand in the image;

[0032] Real-time skeletal node information of the operator is captured using a depth camera. This information includes the 3D coordinates of the joints and the connections between them. Images covering the operable area are acquired using the depth camera. Skeletal recognition is performed on these images to obtain the operator's and hand's skeletal node information, including the positions of each joint. The captured skeletal node data undergoes preprocessing, including denoising and smoothing, to improve accuracy and stability. Images within the predefined operable area, such as those acquired by the camera, are preprocessed, including grayscale conversion, denoising, and edge detection, to improve the efficiency and accuracy of subsequent processing. Any computer vision algorithm is used to detect skeletal nodes in the images, without restriction. These algorithms typically identify and track multiple key skeletal nodes of the human body, including the head and limbs, with the wrist joints included in the limbs. If necessary, the skeletal node information can be converted from 2D image coordinates to 3D spatial coordinates. The 3D skeletal node information captured by the depth camera is fused with the 2D skeletal node information detected by the computer vision algorithm to provide more complete and accurate skeletal node information of the operator, especially the hand.

[0033] The acquired images undergo preprocessing. Images within a preset range are captured using image acquisition devices such as cameras to obtain images containing the operator and their hands. These images are then processed with noise reduction and sharpening to improve image quality and facilitate subsequent gesture detection. Next, the hand region is detected using image processing techniques such as color space conversion, edge detection, and morphological processing to extract the hand area from the image. Within the hand region, key points such as fingertips, wrists, and joints are detected using deep learning algorithms.

[0034] S20: Based on the skeletal node information of the operator, generate a feature vector describing the operator's hand posture, match the feature vector describing the operator's hand posture with the gesture model in the gesture model library, and divide the image into frame images with gesture category and frame images without gesture category based on the matching result, and obtain the gesture category information in the frame images with gesture category.

[0035] Users perform gesture actions according to preset gesture specifications. Gesture actions include specific shapes, speeds, and directions. Based on the skeletal node information of the operator's hand, feature vectors describing the operator's hand posture are generated. Feature vector generation: Based on the positional information of key points, feature vectors describing the hand posture are generated. These feature vectors may include the coordinates, angles, and distances of key points. Matching the operator's feature vectors describing their hand posture with gesture models in a gesture model library: Gesture matching and classification: Establishing a gesture model library: During the training phase, using known gesture images and labels, a gesture model library is trained using deep learning algorithms (such as support vector machines and neural networks). These models contain feature vectors and corresponding labels for various gestures. Gesture matching: The extracted feature vectors are matched with models in the gesture model library. This can be achieved by calculating the distance or similarity between feature vectors. Gesture classification: Based on the matching results, the type of gesture in the image is determined. Typically, the model with the smallest distance or the highest similarity is selected as the recognition result.

[0036] Based on the matching results, the images are divided into frames with and without gesture categories, obtaining gesture category information from the frames with gesture categories. An algorithm processes the distance data to extract gesture feature information, such as shape, speed, and direction. Based on the extracted gesture feature information, a classifier (such as a support vector machine or neural network) is used to recognize the gesture. The classifier determines whether the current gesture matches a preset gesture based on a pre-defined gesture template or gesture samples in a database.

[0037] Based on gesture recognition, the system determines whether a gesture is complete by comparing the actual measured distance with a preset distance threshold or range. If the actual measured distance meets the preset threshold or range, the gesture is considered complete, and a corresponding response action is triggered.

[0038] In gesture recognition systems, to accurately identify and respond to user gestures, the system typically needs to process the video stream or image sequence to segment the hand region and count fingers or identify the gesture type. However, not all frames contain valid gestures. Some frames may simply show the user standing still, performing actions unrelated to gestures, or the hand not appearing in the frame. These frames are called "gesture-free frames."

[0039] Frames without gestures are those in a video stream or image sequence that do not contain gestures or whose gesture features are not obvious. These frames typically only contain background information, images of other non-gesture objects or other parts of the human body, without showing the complete shape or trajectory of the gesture. Frames with valid gestures are those in a video stream or image sequence that contain clear, complete gestures that meet the requirements of a specific gesture recognition algorithm. These frames have a clear gesture shape, trajectory, and feature points, enabling them to be accurately identified by the gesture recognition algorithm.

[0040] Extract positional information of key nodes such as the wrist from video or image sequences. Analyze the motion trajectories and relative position changes of these nodes in consecutive frames. Compare and match the extracted features with features in a known gesture pattern library. Machine learning algorithms (such as support vector machines, random forests, etc.) or deep learning models (such as convolutional neural networks, recurrent neural networks, etc.) can be used for pattern matching.

[0041] For situations requiring the capture of dynamic gesture characteristics, motion sensors (such as gyroscopes and accelerometers) can be used to assist in analysis. By calculating parameters such as the movement speed and acceleration of nodes, the type and intent of the gesture can be further determined. Combining gesture class information from preceding and following frames, contextual information is used to help determine the gesture type of the current frame without a gesture class. For example, if the previous frame is the start frame of a gesture and the following frame is the end frame of that gesture, then the current frame without a gesture class is determined to be a transition frame for that gesture.

[0042] S30: Based on the operator's skeletal node information and the gesture category information of the preceding and following frames of the non-gesture category frame image, obtain the gesture category information and hand position information in the non-gesture category frame image.

[0043] For frames lacking hand position information, hand position can be estimated using inter-frame interpolation or prediction. Interpolation is performed using the skeletal node information of the operator in the gesture-category frames preceding and following the non-gesture-category frame image to calculate the operator's hand skeletal node information in the non-gesture-category frame image. The operator's hand skeletal node information in the non-gesture-category frame image is then matched with gesture models in a gesture model library to obtain the operator's gesture category in the non-gesture-category frame image.

[0044] For frames lacking hand position information, the wrist node position of the operator in the non-gesture category frame image can be obtained based on the operator's skeletal node information and the skeletal node information of the operator's hand; and the hand position information of the operator in the non-gesture category frame image can be obtained based on the wrist node position of the operator in the non-gesture category frame image.

[0045] Compare the gesture category information in the gesture-category frames before and after the frame with no gesture category. If the gesture category information in the frames before and after belongs to the same gesture category, then the gesture information in the frame without a gesture category is also determined to be the same as the gesture category information in the frames before and after. If the gesture category information in the frames before and after belongs to two consecutive different gesture categories, then the gesture category information in the frame without a gesture category is determined to be the same as the gesture category information in the previous frame or the gesture category information in the next frame.

[0046] In video or image sequences, the system continuously tracks the positional information of key nodes such as the wrist. Algorithms such as optical flow and Kalman filtering can be used to optimize the tracking accuracy of node positions. For frames without gestures, interpolation algorithms can be used to calculate the positional information of their key nodes. Commonly used interpolation algorithms include linear interpolation and polynomial interpolation. By combining the positional information of preceding and following frames, the positional information of frames without gestures is corrected and optimized. Smoothing filters and denoising algorithms can be used to improve the accuracy and stability of positional information. The system enables gesture classification and positional information calculation for frames without gestures. It can process video or image sequences in real time and output gesture recognition results and positional information.

[0047] S40: Generate instructions to control the display device based on the gesture category information and hand position information in the frame images with and without gesture categories.

[0048] The gestures in the frame images with and without gesture categories are classified into Level 1 Response Gesture 1 and Level 2 Response Gesture 2. The displacement change data of Gesture 1 and Gesture 2 of the same hand of the operator are obtained between frames. When the displacement change data of Gesture 1 meets the condition for triggering Gesture 2, it is determined whether the displacement change data of Gesture 2 meets the condition for triggering the menu display. If it does, an instruction to control the display device is generated.

[0049] A camera (such as a color camera or depth camera) is used to capture images of the hand or gesture in real time. Image processing algorithms (such as depth map algorithms) are used to calculate the distance between the hand or gesture and the camera. For depth cameras, depth information can be directly acquired; for color cameras, specific algorithms (such as stereo vision, structured light, etc.) are needed to estimate the depth. A corresponding distance threshold is set based on the expected completion of the gesture. The distance between the hand or gesture and the camera is calculated in real time and compared with the set threshold. If the distance data is within the set threshold range, the gesture is considered to be proceeding as expected. If the distance data exceeds the set threshold range, the gesture is considered not to be completed as expected or to contain errors.

[0050] This disclosure, in its second aspect, proposes an apparatus for controlling a display device based on gestures, characterized by comprising: an acquisition unit for acquiring skeletal node information of the operator and skeletal node information of the operator's hand in an image; a matching unit for generating a feature vector describing the operator's hand posture based on the skeletal node information of the operator's hand, matching the feature vector describing the operator's hand posture with a gesture model in a gesture model library, and dividing the image into frame images with gesture categories and frame images without gesture categories based on the matching result, thereby obtaining gesture category information in the frame images with gesture categories; a judgment unit for acquiring gesture category information and hand position information in the frame images without gesture categories based on the operator's skeletal node information and the gesture category information of the preceding and following frames of the frame images without gesture categories; and a generation unit for generating instructions for controlling the display device based on the gesture category information and hand position information in the frame images with and without gesture categories.

[0051] In a third aspect, this disclosure provides a computer-readable medium storing a computer program, which is loaded and executed by a processing module to implement the steps of the acquisition method. Those skilled in the art will understand that all or part of the steps in the embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable medium, which may include various media capable of storing program code, such as flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0052] Within the scope of knowledge and ability of those skilled in the art, the various embodiments or technical features mentioned herein can be combined with each other as other optional embodiments without conflict. These finite number of optional embodiments, which are not listed one by one and are formed by combining a finite number of technical features, still fall within the scope of the technology disclosed herein and are also derived by those skilled in the art from the accompanying drawings and the foregoing.

[0053] In addition, the descriptions of most embodiments are based on different focuses. For further understanding of the parts not described in detail, reasonable inference can be made by referring to the relevant content of the prior art, other relevant descriptions in this document, or the inventive intent.

[0054] To reiterate, the embodiments listed above are typical and preferred embodiments of this disclosure, and are only used to describe and explain the technical solutions of this disclosure in detail to facilitate the reader's understanding. They are not intended to limit the scope or application of the protection claimed in this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure to obtain technical solutions should be covered within the scope of protection claimed in this disclosure.

Claims

1. A method of controlling a display device based on a gesture, the method comprising: The method comprises the following steps: Obtain the skeleton node information of the operator and the skeleton node information of the operating hand in the image; According to the skeleton node information of the operating hand, generate the feature vector describing the hand posture of the operator, match the feature vector describing the hand posture of the operator with the gesture model in the gesture model library, and divide the image into gesture category frame image and non-gesture category frame image according to the matching result, and obtain the gesture category information in the gesture category frame image; According to the skeleton node information of the operator and the gesture category information of the previous and next frames of the non-gesture category frame image, obtain the gesture category information and the position information of the hand in the non-gesture category frame image; According to the gesture category information and the position information of the hand in the gesture category frame image and the gesture category information and the position information of the hand in the non-gesture category frame image, generate the instruction for controlling the display device.

2. The method of claim 1, wherein, Further comprising: Capture the real-time skeleton node information of the operator through the depth camera, and the skeleton node information includes the three-dimensional coordinates of the joints and the connection relationship between the joints.

3. The method of claim 1, wherein, Interpolate the skeleton node information of the operator in the gesture category frame image of the previous and next frames of the non-gesture category frame image to calculate the hand skeleton node information of the operator in the non-gesture category frame image.

4. The method of claim 3, wherein, Match the hand skeleton node information of the operator in the non-gesture category frame image with the gesture model in the gesture model library to obtain the gesture category of the operator in the non-gesture category frame image.

5. The method of claim 1, wherein, According to the skeleton node information of the operator and the skeleton node information of the operating hand, obtain the wrist node position of the operator in the non-gesture category frame image; According to the wrist node position of the operator in the non-gesture category frame image, obtain the hand position information of the operator in the non-gesture category frame image.

6. The method of claim 1, wherein, Compare the gesture category information in the gesture category frame image of the previous and next frames of the non-gesture category frame image, if the gesture category information of the previous and next frames belongs to the same gesture category, it is judged that the gesture information in the non-gesture category frame image is also the same as the gesture category information of the previous and next frames.

7. The method of claim 6, wherein, If the gesture category information of the previous and next frames belongs to two continuous different gesture categories respectively, it is judged that the gesture category information in the non-gesture category frame image is the same as the gesture category information of the previous frame or the gesture category information of the next frame.

8. The method of claim 1, wherein, Classify the gesture of the gesture category frame image and the non-gesture category frame image into first response gesture one and second response gesture two, and obtain the displacement change data of gesture one and gesture two of the same operating hand of the operator between frames; When the displacement change data of gesture one reaches the condition of triggering gesture two, judge whether the displacement change data of gesture two reaches the condition of triggering menu display, if so, generate the instruction for controlling the display device.

9. An apparatus for controlling a display device based on a gesture, the apparatus comprising: The method comprises the following steps: An acquisition unit is configured to acquire the skeleton node information of the operator and the skeleton node information of the operating hand in the image; A matching unit is configured to generate the feature vector describing the hand posture of the operator according to the skeleton node information of the operating hand, match the feature vector describing the hand posture of the operator with the gesture model in the gesture model library, divide the image into gesture category frame image and non-gesture category frame image according to the matching result, and obtain the gesture category information in the gesture category frame image; The judging unit is configured to acquire gesture category information and hand position information in the frame image without gesture according to the skeleton node information of the operator and the gesture category information of the front and back frames of the frame image without gesture. The generating unit is configured to generate an instruction for controlling the display device according to the gesture category information and the hand position information of the frame image with gesture, and the gesture category information and the hand position information of the frame image without gesture.

10. A computer readable medium characterized by: The computer readable medium stores a computer program, and the computer program is loaded and executed by the processing module to implement the steps of the method in any one of claims 1 to 8.

Images