An interactive method, device, computing device and storage medium based on gesture recognition

Abstract

The present invention relates to the field of human-computer interaction technology, and discloses an interaction method, apparatus, computing device, and storage medium based on gesture recognition. The method comprises: capturing the user's hand motion data, obtaining the first gesture coordinates of the hand motion within the camera field of view interval; converting the first gesture coordinates into the second gesture coordinates within the screen display interval according to the corresponding mapping relationship; and performing interaction regarding the hand motion based on the second gesture coordinates; the mapping relationship comprises: mapping the starting interval segment or the ending interval segment of the camera field of view interval to the numerical interval of the edge area of ​​the screen display interval; and mapping the middle interval segment of the camera field of view interval to the numerical interval of the middle area of ​​the screen display interval. Buffering is achieved by reserving interval segments at the edge and establishing mappings to avoid discomfort in edge operations; center operations improve data accuracy; and reasonable division of areas reduces operation failures, improves comfort, experience, accuracy, and reliability, and improves system stability and usability.

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction technology, and in particular to an interaction method, apparatus, computing device and storage medium based on gesture recognition. Background Art

[0002] Currently, gesture recognition technology typically maps the camera's viewing frustum directly to the screen. However, this approach presents numerous challenges. For example, operating elements near the screen edge at a distance from the camera can be uncomfortable and create a poor user experience. Furthermore, gestures can easily fail due to the gesture moving outside the camera's range, impacting user experience and efficiency. Summary of the Invention

[0003] The present invention provides an interaction method, apparatus, computing device and storage medium based on gesture recognition to solve the problems existing in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An interaction method based on gesture recognition, comprising:

[0006] Capturing the user's hand motion data and obtaining the first gesture coordinates of the hand motion within the camera field of view;

[0007] Converting the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship;

[0008] performing interaction regarding the hand motion based on the second gesture coordinates;

[0009] The mapping relationship includes:

[0010] When the first gesture coordinates are located in the starting interval or the ending interval of the camera field of view interval, they are mapped to the edge area value interval of the screen display interval;

[0011] When the first gesture coordinates are located in the middle interval of the camera field of view interval, they are mapped to the middle area numerical interval of the screen display interval.

[0012] Optionally, converting the first gesture coordinates into second gesture coordinates within a screen display interval according to a corresponding mapping relationship includes:

[0013] The first gesture coordinates are converted to the second gesture coordinates based on the following formula:

[0014] Second gesture coordinates = (first gesture coordinates - minimum value of camera field of view interval) / (maximum value of camera field of view interval - minimum value of camera field of view interval) × (maximum value of screen display interval - minimum value of screen display interval) + minimum value of screen display interval.

[0015] Optionally, converting the first gesture coordinates into second gesture coordinates within a screen display interval according to a corresponding mapping relationship includes:

[0016] Based on the linear segmented mapping relationship, the camera field of view interval on the X-axis / Y-axis is divided into multiple first segment intervals, and the screen display interval on the X-axis / Y-axis is correspondingly divided into multiple second segment intervals; each of the first segment intervals and each of the second segment intervals have a one-to-one correspondence in terms of position and order.

[0017] Optionally, the starting interval segment and the ending interval segment are symmetrically distributed over the length of the camera field of view interval;

[0018] The starting interval segment and the edge area value interval of the screen display interval are in a linear proportional relationship.

[0019] Optionally, converting the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship further includes:

[0020] Perform noise reduction processing on the second gesture coordinates.

[0021] Optionally, the noise reduction processing includes:

[0022] Testing the noise jitter range during the conversion from the first gesture coordinates to the second gesture coordinates, and setting a change threshold based on the test results;

[0023] analyzing a data change value when the first gesture coordinates are converted into the second gesture coordinates, and determining whether the data change value exceeds the set change threshold;

[0024] When the data change value exceeds the set change threshold, the second gesture coordinates are saved and recorded.

[0025] Optionally, the noise reduction processing further includes:

[0026] When the data change value does not exceed the set change threshold, linear interpolation is performed between the first gesture coordinate and the second gesture coordinate to obtain a plurality of intermediate coordinate values;

[0027] Analyzing a data change value between each of the intermediate coordinate values ​​and the first gesture coordinate, and determining whether the data change value exceeds the set change threshold;

[0028] If there is no intermediate coordinate value whose data change value exceeds the set change threshold, the second gesture coordinate obtained by the current conversion is discarded and the original value is retained;

[0029] If the data change value of one or more intermediate coordinate values ​​exceeds the set change threshold, the intermediate coordinate value with the largest value is selected, updated as the new second gesture coordinate and saved.

[0030] The present invention further provides a gesture recognition device for implementing any of the above-mentioned gesture recognition-based interaction methods, comprising:

[0031] an acquisition unit, configured to capture hand motion data of the user and acquire first gesture coordinates of the hand motion within a camera field of view;

[0032] a processing unit, configured to convert the first gesture coordinates into second gesture coordinates within a screen display interval according to a corresponding mapping relationship;

[0033] An execution unit is configured to execute interaction related to the hand motion based on the second gesture coordinates.

[0034] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above gesture recognition-based interaction methods when executing the computer program.

[0035] The present invention further provides a storage medium comprising computer-executable instructions, wherein the computer-executable instructions are executed by a computer processor to implement any of the above-described interaction methods based on gesture recognition.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention provides an interaction method, apparatus, computing device, and storage medium based on gesture recognition. These methods achieve a buffering effect by reserving a starting interval and an ending interval at the edge of the camera's field of view and establishing a mapping relationship with the screen display interval, thereby avoiding user discomfort when operating at the edge. At the same time, data accuracy is improved by concentrating operations in a central area. Furthermore, reasonable area division reduces the possibility of operation failures caused by gestures moving out of the camera range, greatly improving operational comfort, enhancing user experience, ensuring the accuracy and reliability of gesture recognition, and improving system stability and usability.

[0038] The present invention has other features and advantages that will be apparent from or will be described in detail in the accompanying drawings and the following detailed description incorporated herein, which together serve to explain certain principles of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 It is a schematic diagram of the camera's viewing frustum range and screen range;

[0041] Figure 2 This is a flowchart of an interaction method based on gesture recognition provided by the present invention;

[0042] Figure 3 Schematic diagram of a camera field of view interval in a coordinate system in an interaction method based on gesture recognition provided by the present invention;

[0043] Figure 4 This is a schematic diagram of mapping between a camera field of view interval and a screen display interval in an interaction method based on gesture recognition provided by the present invention;

[0044] Figure 5 This is a logic diagram of the steps of data noise reduction in an interaction method based on gesture recognition provided by the present invention;

[0045] Figure 6 This is a structural block diagram of a gesture recognition device provided by the present invention.

[0046] Reference numerals: 10, acquisition unit; 20, processing unit; 30, execution unit. DETAILED DESCRIPTION

[0047] In order to explain in detail the possible application scenarios, technical principles, specific solutions that can be implemented, and the purpose and effects of this application, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of this application and are therefore only examples and are not intended to limit the scope of protection of this application.

[0048] References to "embodiments" herein mean that the specific features, structures, or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the word "embodiment" in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the various technical features mentioned in the embodiments can be combined in any manner to form a corresponding implementable technical solution.

[0049] Unless otherwise defined, the technical terms used herein have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms herein is only for describing specific embodiments and is not intended to limit this application.

[0050] In the description of this application, the term "and / or" is used to describe a logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and both A and B exist. In addition, the character " / " in this document generally indicates that the objects before and after are in a logical "or" relationship.

[0051] In this application, terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantity, priority or sequence relationship between these entities or operations.

[0052] Without further limitations, in this application, the words "include", "comprise", "have" or other similar expressions used in the sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those defined elements, but also other elements not explicitly listed, or elements inherent to such process, method or product.

[0053] Consistent with the understanding in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceed" are understood to exclude the number itself; expressions such as "above," "below," and "within" are understood to include the number itself. Furthermore, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this manner, such as "multiple groups," "multiple times," etc., unless otherwise specifically defined.

[0054] In the description of the embodiments of the present application, the space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, it should not be understood as a limitation on the embodiments of the present application.

[0055] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms "installed", "connected", "connected", "fixed", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For those skilled in the art of the present application, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0056] Please refer to Figure 1 An embodiment of the present invention provides an interaction method based on gesture recognition, which reserves a starting interval segment and an ending interval segment at the edge of the camera's field of view and establishes a mapping relationship with the screen display interval to achieve the effect of improving operation accuracy and comfort.

[0057] It's understandable that existing technologies simply map the camera's viewing cone directly to the screen, which can lead to a series of problems. For example, when the distance from the camera is far, the viewing cone reaches its maximum. At this time, to operate elements near the edge of the screen, the hand needs to slide to the edge of the camera's field of view. Operating at the edge of the field of view is not only uncomfortable but also lacks a good user experience. At the same time, the data accuracy of the edge area of ​​the viewing cone is much lower than that of the middle area of ​​the viewing cone. In addition, if the gesture moves out of the camera range, the operation will fail.

[0058] In this application, the starting interval and the ending interval reserved at the edge of the camera's field of view are equivalent to providing a buffer effect. When the user's operating position is still some distance away from the edge of the visual cone and falls into the starting interval or the ending interval, the user's operation is mapped to the edge of the screen through a preset mapping relationship, avoiding the user's discomfort when operating at the edge; at the same time, the data accuracy is improved by concentrating the operation in the central area; in addition, the reasonable division of the area reduces the situation where the gesture moves out of the camera range and causes the operation to fail, greatly improving the operating comfort, enhancing the user experience, ensuring the accuracy and reliability of gesture recognition, and improving the stability and availability of the system.

[0059] Please refer to Figure 2 Specifically, the gesture recognition-based interaction method provided in this embodiment includes:

[0060] S1. Capture the user's hand motion data and obtain the first gesture coordinates of the hand motion within the camera field of view.

[0061] In this step, the user's hand movement data is captured and the first gesture coordinates of the hand movement within the camera field of view are obtained; it can be understood that this process monitors the user's hand movement through the camera and converts the position of the hand in the real space into a coordinate value within the camera field of view.

[0062] S2. Convert the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship.

[0063] The mapping relationships include:

[0064] When the first gesture coordinates are located in the starting interval or the ending interval of the camera field of view, they are mapped to the edge area value interval of the screen display interval;

[0065] When the first gesture coordinates are located in the middle interval of the camera field of view, they are mapped to the middle area value interval of the screen display interval.

[0066] In one embodiment, converting the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship includes:

[0067] The first gesture coordinates are converted to the second gesture coordinates based on the following formula:

[0068] Second gesture coordinates = (first gesture coordinates - minimum value of camera field of view interval) / (maximum value of camera field of view interval - minimum value of camera field of view interval) × (maximum value of screen display interval - minimum value of screen display interval) + minimum value of screen display interval.

[0069] Optionally, converting the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship includes:

[0070] Based on the linear segmented mapping relationship, the camera field of view interval on the X-axis / Y-axis is divided into multiple first segment intervals, and the screen display interval on the X-axis / Y-axis is correspondingly divided into multiple second segment intervals; each first segment interval and each second segment interval have a one-to-one correspondence in terms of position and order.

[0071] It can be understood that the linear segmented mapping relationship and the one-to-one correspondence relationship can make the mapping smoother, thereby improving the accuracy and response speed of gesture recognition.

[0072] Furthermore, 20%-30% of the area at the edge of the camera's field of view can be reserved as a buffer zone, and the central 70%-80% area can be used as an operation area.

[0073] For example, please refer to Figure 3 and Figure 4 Taking the X-axis as an example, the area <20% is uniformly mapped to the leftmost side of the screen, and the area >80% is uniformly mapped to the rightmost side of the screen. Taking the X-axis as an example, the area 20%-80% is taken as the operation area and mapped to the screen coordinates. Assuming the camera X-axis resolution is 100 and the screen resolution is 1000.

[0074] The calculation process is as follows:

[0075] When the gesture position is at coordinate 80, the coordinates of 1000 on the right edge of the screen are obtained:

[0076] 1000=(80-20) / (80–20)*(1000-0)+0;

[0077] When the gesture is at coordinate 20, the coordinates at screen coordinate 0 are obtained:

[0078] 0=(20–20) / (80-20)*(1000-0)+0.

[0079] In this embodiment, a reasonable mapping relationship is used to improve the comfort and accuracy of user operation. When the user's hand is at different positions in the camera field of view, it can be accurately mapped to the corresponding position in the screen display area, avoiding the discomfort and inaccuracy of operation in the edge area.

[0080] Furthermore, this embodiment also includes: in the setting of the mapping relationship, according to different application scenarios and user needs, adjusting the division ratio of the camera field of view interval and the screen display interval, or using different functions for coordinate conversion to achieve the division method and mapping rules.

[0081] Furthermore, in this embodiment, the starting interval and the ending interval are symmetrically distributed in the length of the camera field of view interval;

[0082] The starting interval segment and the edge area value interval of the screen display interval are in a linear proportional relationship.

[0083] When the starting and ending segments are symmetrically distributed across the length of the camera's field of view, the user's hand movements, regardless of whether they are near the beginning or end of the camera's field of view, are mapped to the edge of the screen display in a similar manner. This allows users to have a certain expectation of the effects of operations at different locations, improving the predictability and consistency of operations. For example, once users become familiar with the mapping of operations at the starting point, they can quickly adapt to operations at the ending point, reducing the learning curve.

[0084] It can be understood that the starting interval segment and the edge area numerical interval of the screen display interval are in a linear proportional relationship, which can make the operation smoother and more natural. When the user operates near the edge area, the changes in hand movements can be reflected more evenly on the screen display without sudden jumps or discontinuities. This greatly improves the user experience and makes the user feel that the operation is smoother and more comfortable. At the same time, this linear proportional relationship also helps users control the position of gestures on the screen more accurately, improving the accuracy of the operation.

[0085] Furthermore, through clear symmetrical distribution and linear proportional relationships, the system becomes more stable and reliable when processing gesture coordinates at different locations. Based on these fixed relationships, the system can accurately map and convert gestures, reducing errors and anomalies caused by uncertainty. For example, the system maintains relatively stable performance in different usage environments, avoiding significant fluctuations due to slight changes in the user's hand position, thus improving the system's adaptability and robustness.

[0086] Furthermore, in this embodiment, converting the first gesture coordinates into second gesture coordinates within the screen display interval according to the corresponding mapping relationship further includes:

[0087] Perform noise reduction processing on the second gesture coordinates.

[0088] Please refer to Figure 5 , wherein the noise reduction processing includes:

[0089] Testing the noise jitter range during the conversion from the first gesture coordinates to the second gesture coordinates, and setting a change threshold based on the test results;

[0090] Analyze the data change value when the first gesture coordinates are converted to the second gesture coordinates, and determine whether the data change value exceeds a set change threshold;

[0091] When the data change value exceeds the set change threshold, the second gesture coordinates are saved and recorded;

[0092] When the data change value does not exceed the set change threshold, linear interpolation is performed between the first gesture coordinate and the second gesture coordinate to obtain multiple intermediate coordinate values;

[0093] Analyze the data change value between each intermediate coordinate value and the first gesture coordinate value to determine whether the data change value exceeds the set change threshold;

[0094] If there is no data change value of the intermediate coordinate value that exceeds the set change threshold, the second gesture coordinate obtained by the current conversion is discarded and the original value is retained;

[0095] If the data change value of one or more intermediate coordinate values ​​exceeds the set change threshold, the intermediate coordinate value with the largest value is selected, updated as the new second gesture coordinate and saved.

[0096] In this embodiment, by testing the noise jitter range and setting the change threshold, some tiny unnecessary coordinate changes that may be caused by noise can be effectively filtered out, thereby reducing the jitter of the control point, so that the final second gesture coordinates more accurately reflect the user's real hand movements, improving the accuracy of gesture recognition, and ensuring that the user's operation intentions can be more accurately captured and executed.

[0097] When the data change value does not exceed the threshold, linear interpolation is performed to supplement some transition information that may be lost due to discarding small changes, making the change of gesture coordinates smoother and more natural. During the user operation, the data change amplitude will not suddenly increase due to frequent discarding of small changes, thereby ensuring the smoothness of the operation and improving the consistency and comfort of the operation.

[0098] Furthermore, re-analyzing and processing the intermediate coordinate values ​​can, to a certain extent, avoid misjudgments that may occur due to a single threshold. If an intermediate coordinate value exceeds the threshold, the largest intermediate coordinate value is selected as the new second gesture coordinate and saved. This approach allows the system to more stably and reliably handle various complex gesture variations, improving the system's adaptability and robustness.

[0099] S3. Perform interaction regarding the hand motion based on the second gesture coordinates.

[0100] In this embodiment, the interactive operation includes screen operation interaction, such as cursor control, click operation, sliding operation or zoom operation. Among them, the second gesture coordinates are used to control the movement of the cursor on the screen. The user uses hand movements to accurately position the cursor to a specific icon, button or text area to achieve quick selection and operation. When the hand movement corresponds to the second gesture coordinate range, the click operation can be triggered. The user uses a second gesture coordinate sequence generated by continuous hand movement changes to achieve sliding of screen content, such as sliding up and down to browse web pages, sliding left and right to switch pictures or pages, etc. For example, the user can also separate or close two fingers to zoom in or out of the screen content according to the corresponding second gesture coordinate changes, making it convenient for the user to view details or browse the overall situation.

[0101] Please refer to Figure 6 Based on the above embodiments, the present invention provides a gesture recognition device for implementing any of the above gesture recognition-based interaction methods, including:

[0102] An acquisition unit 10 is configured to capture the user's hand motion data and obtain first gesture coordinates of the hand motion within a camera field of view;

[0103] The processing unit 20 is configured to convert the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship;

[0104] The execution unit 30 is configured to execute an interaction related to a hand movement based on the second gesture coordinates.

[0105] First, the acquisition unit 10 captures the user's hand motion data and obtains the first hand gesture coordinates within the camera's field of view. This process uses the camera to monitor the user's hand motion and converts the hand's position in real space into coordinate values ​​within the camera's field of view.

[0106] Next, the processing unit 20 converts the first gesture coordinates into the second gesture coordinates within the screen display interval according to the corresponding mapping relationship. This mapping relationship is set according to different situations. When the first gesture coordinates are located in the starting interval or the ending interval of the camera field of view interval, they are mapped to the numerical interval of the edge area of ​​the screen display interval; when the first gesture coordinates are located in the middle interval of the camera field of view interval, they are mapped to the numerical interval of the middle area of ​​the screen display interval. At the same time, this embodiment also uses the following formula for conversion:

[0107] That is, the second gesture coordinates = (first gesture coordinates - minimum value of the camera field of view interval) / (maximum value of the camera field of view interval - minimum value of the camera field of view interval) × (maximum value of the screen display interval - minimum value of the screen display interval) + minimum value of the screen display interval. Furthermore, based on a linear segmented mapping relationship, the camera field of view interval on the X-axis is divided into multiple first segmented intervals, and the screen display interval on the X-axis is correspondingly divided into multiple second segmented intervals, with each first segmented interval corresponding to each second segmented interval in terms of position and order.

[0108] Finally, the execution unit 30 performs interaction regarding the hand motion based on the second gesture coordinates to realize recognition and response to the gesture.

[0109] Based on the above embodiments, this embodiment further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any of the above gesture recognition-based interaction methods.

[0110] The present invention also provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to implement any of the above interaction methods based on gesture recognition.

[0111] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concepts of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. An interactive method based on gesture recognition, characterized in that: include: Capturing the user's hand motion data and obtaining the first gesture coordinates of the hand motion within the camera field of view; Converting the first gesture coordinates into second gesture coordinates within the screen display interval according to a corresponding mapping relationship; performing interaction regarding the hand motion based on the second gesture coordinates; The mapping relationship includes: When the first gesture coordinates are located in the starting interval or the ending interval of the camera field of view interval, they are mapped to the edge area value interval of the screen display interval; When the first gesture coordinates are located in the middle interval of the camera field of view interval, they are mapped to the middle area numerical interval of the screen display interval; The converting the first gesture coordinates into second gesture coordinates within the screen display interval according to the corresponding mapping relationship includes: The first gesture coordinates are converted to the second gesture coordinates based on the following formula: Second gesture coordinates = (first gesture coordinates - minimum value of camera field of view interval) / (maximum value of camera field of view interval - minimum value of camera field of view interval) × (maximum value of screen display interval - minimum value of screen display interval) + minimum value of screen display interval; The converting the first gesture coordinates into second gesture coordinates within the screen display interval according to the corresponding mapping relationship includes: Based on the linear segmented mapping relationship, the camera field of view interval on the X-axis / Y-axis is divided into a plurality of first segmented intervals, and the screen display interval on the X-axis / Y-axis is correspondingly divided into a plurality of second segmented intervals, with each first segmented interval corresponding to each second segmented interval in terms of position and order; The starting interval and the ending interval are symmetrically distributed over the length of the camera field of view interval; The starting interval segment and the edge area value interval of the screen display interval are in a linear proportional relationship.

2. The interactive method based on gesture recognition according to claim 1, characterized in that: The converting the first gesture coordinates into second gesture coordinates within the screen display interval according to the corresponding mapping relationship also includes: Perform noise reduction processing on the second gesture coordinates.

3. The interactive method based on gesture recognition according to claim 2, characterized in that: The noise reduction process includes: Testing the noise jitter range during the conversion from the first gesture coordinates to the second gesture coordinates, and setting a change threshold based on the test results; analyzing a data change value when the first gesture coordinates are converted into the second gesture coordinates, and determining whether the data change value exceeds the set change threshold; When the data change value exceeds the set change threshold, the second gesture coordinates are saved and recorded.

4. The interactive method based on gesture recognition according to claim 3, characterized in that: The noise reduction process further includes: When the data change value does not exceed the set change threshold, linear interpolation is performed between the first gesture coordinate and the second gesture coordinate to obtain a plurality of intermediate coordinate values; Analyzing a data change value between each of the intermediate coordinate values ​​and the first gesture coordinate, and determining whether the data change value exceeds the set change threshold; If there is no intermediate coordinate value whose data change value exceeds the set change threshold, the second gesture coordinate obtained by the current conversion is discarded and the original value is retained; If the data change value of one or more intermediate coordinate values ​​exceeds the set change threshold, the intermediate coordinate value with the largest value is selected, updated as the new second gesture coordinate and saved.

5. A gesture recognition device, characterized in that: The method for implementing the gesture recognition-based interaction method according to any one of claims 1 to 4 comprises: an acquisition unit, configured to capture hand motion data of the user and acquire first gesture coordinates of the hand motion within a camera field of view; a processing unit, configured to convert the first gesture coordinates into second gesture coordinates within a screen display interval according to a corresponding mapping relationship; An execution unit is configured to execute interaction related to the hand motion based on the second gesture coordinates.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the gesture recognition-based interaction method according to any one of claims 1 to 4 is implemented.

7. A storage medium containing computer-executable instructions, characterized in that: The computer executable instructions are executed by a computer processor to implement the gesture recognition-based interaction method according to any one of claims 1 to 4.

Images