Gesture recognition method and apparatus, device and storage medium

By integrating image acquisition and comparison technology in wrist wearable devices, identifying wrist veins and skin texture features, the problems of inconvenient operation and poor versatility of existing gesture recognition technologies are solved, and efficient and convenient AR and VR equipment are achieved operate.

WO2024234816A1PCT designated stage expired Publication Date: 2024-11-21ZTE CORP
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/082208
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-18
Filing Date
2024-03-18
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Gesture recognition technology in existing augmented reality (AR) and virtual reality (VR) spaces has problems such as inconvenient operation, low gesture recognition rate and poor versatility. Especially when cameras detect gestures, they are affected by ambient light and perspective angles, and are professional handheld devices. Limited versatility.

Method used

Using the combination of wrist image acquisition and control components, the wrist image is collected and the pre-saved reference image is compared to the gesture, and the wrist veins and skin texture characteristics are used to realize gesture recognition, and embedded in the wrist wearable device to achieve non- Efficient gesture operation with contact and non-direct vision.

Benefits of technology

It realizes simple and efficient operation and is not affected by ambient light. It has strong versatility. Users can operate AR and VR devices at will and comfortably without requiring their wrists to be within the equipment monitoring range.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024082208_21112024_PF_FP_ABST
    Figure CN2024082208_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present disclosure provides a gesture recognition method and apparatus, a device and a storage medium. The gesture recognition apparatus comprises a wrist image acquisition component and a control component; the wrist image acquisition component is configured to acquire a current wrist image and transmit same to the control component; and the control component is configured to compare the wrist image with at least one pre-stored reference image to respond to a gesture corresponding to a reference image matched with the wrist image.
Need to check novelty before this filing date? Find Prior Art

Description

Gesture recognition method, device, equipment and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to patent application No. 202310566301.X filed with the China Patent Office on May 18, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to, but is not limited to, the field of human-computer interaction technology. Background Art

[0004] Currently, in augmented reality (AR) and virtual reality (VR) spaces, there are various methods for manipulating targets, each with its own advantages and disadvantages. For example, detecting the human eye focusing on a target is slow; cameras detect human gestures and map them to point out targets in virtual space, but this method requires users to hold their hands up for long periods of time, making it inconvenient to operate. The camera captures hand movement images, which are affected by ambient light and the camera's viewing angle, resulting in a low gesture recognition rate; and the use of specialized handheld devices for operation is less versatile.

[0005] Summary of the Invention

[0006] The present disclosure provides a gesture recognition method, apparatus, device, and storage medium.

[0007] According to a first aspect of the present disclosure, a gesture recognition device is provided, comprising: a wrist image acquisition component and a control component; the wrist image acquisition component is configured to acquire a current wrist image and transmit it to the control component; the control component is configured to compare the wrist image with at least one pre-stored reference image and respond to a gesture corresponding to the reference image that matches the wrist image.

[0008] A second aspect of the present disclosure provides a gesture recognition method, comprising: acquiring a current wrist image; comparing the wrist image with at least one pre-stored reference image, and responding to a gesture corresponding to the reference image that matches the wrist image.

[0009] A third aspect of the present disclosure provides an electronic device, comprising: at least one processor; a memory on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in the second aspect; and at least one I / O interface connected between the processor and the memory, configured to implement information interaction between the processor and the memory.

[0010] A fourth aspect of the present disclosure provides a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to the second aspect is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] FIG1 is a schematic structural diagram of a gesture recognition device provided in an embodiment of the present disclosure;

[0012] FIG2 is a schematic structural diagram of a wrist wearable device provided in an embodiment of the present disclosure;

[0013] FIG3 is a flow chart of a gesture recognition method provided in an embodiment of the present disclosure;

[0014] FIG4 is a flowchart of a method for controlling an AR device or a VR device with gestures provided in an embodiment of the present disclosure;

[0015] FIG5 is a schematic diagram of a wrist provided in an embodiment of the present disclosure;

[0016] FIG6 is a schematic structural diagram of a gesture recognition device provided in an embodiment of the present disclosure;

[0017] FIG7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0019] As used in this disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0020] The terms used in the present disclosure are only used to describe specific embodiments and are not intended to limit the present disclosure.As used in the present disclosure, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0021] When the terms “comprising” and / or “made of…” are used in the present disclosure, it specifies the existence of the stated features, integers, steps, operations, elements and / or components, but does not preclude the existence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0022] Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meanings as those commonly understood by those skilled in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined in this disclosure.

[0023] An embodiment of the present disclosure provides a gesture recognition device. FIG1 is a structural diagram of the gesture recognition device 1 . The gesture recognition device mainly includes: a wrist image acquisition component 10 and a control component 11 .

[0024] Among them, the wrist image acquisition component 10 is configured to acquire the current wrist image and transmit it to the control component 11; the control component 11 is configured to compare the wrist image with at least one pre-saved reference image and respond to the gesture corresponding to the reference image that matches the wrist image.

[0025] In some embodiments, the gesture recognition device 1 is embedded in the wrist wearable device 2, and when worn, the wrist image acquisition component 10 faces the side where the wrist is located. Figure 2 shows a schematic diagram of the structure of a wrist wearable device, which is an example of a wrist wearable device. In this example, the wrist wearable device 2 is a smart watch or a smart bracelet. The gesture recognition device 1 is embedded in the back of the dial of the smart watch (the back of the dial faces the user's wrist when the user wears the smart watch) or embedded in the inside of the strap of the smart watch (the inside of the strap faces the user's wrist when the user wears the smart watch). Alternatively, the gesture recognition device 1 can be embedded in the inside of the smart bracelet (the inside of the smart bracelet faces the user's wrist when the user wears the smart bracelet). Embedding the gesture recognition state in a wrist wearable device such as a smart watch allows it to be operated and used at any time, ensuring ease of use. It should be understood that this is only an example and there is no limitation on the form of the wrist wearable device. It only needs to be able to facilitate the acquisition of the user's wrist image.

[0026] In some embodiments, as shown in FIG2 , the wrist image acquisition component 10 includes an image sensor 101 and a light-emitting element 102. The control component 11 is configured to control the light-emitting element 102 to emit light and to turn on the image sensor 101. The light-emitting element 102 may be, for example, a light-emitting diode (LED), which may emit near-infrared light or white light; the image sensor 101 may be, for example, a camera. For example, the dashed line in FIG2 illustrates the angle at which the image sensor 101 captures the image. The wrist wearable device 2 is exemplified by a smartwatch. The smartwatch includes a dial 21 and a strap 22. The front 23 of the dial 21 is equipped with a display screen, while the back 24 of the dial is embedded with the image sensor 101 and light-emitting element 102. To facilitate capture, the camera maintains a certain distance from the surface of the wrist skin when capturing wrist images. The camera's position is adjusted as needed to capture a clear image of the wrist. The embedded position of the image sensor 101 shown in FIG2 is for example only; it can also be embedded deeper in the dial, as needed. In addition, for aesthetics and wearing comfort, a transparent shell can be provided at the position where the image sensor 101 is embedded, so as to provide a good wearing experience when in contact with the wrist skin without affecting the acquisition effect of the image sensor 101.

[0027] The power supply in the wrist wearable device 2 is connected to the power supply terminal of the gesture recognition device 1 to power the gesture recognition device 1. For example, the power supply in the wrist wearable device 2 is connected to the power supply terminal of the light-emitting element and the power supply terminal of the image sensor respectively to ensure the normal operation of the light-emitting element and the image sensor.

[0028] In some embodiments, the control unit 11 is further configured to, before capturing the current wrist image, enter a gesture detection state according to a control instruction and control the wrist image capture unit 10 to start. The method of starting the wrist image capture unit 10 is not limited, and can be voice-activated or by clicking a start button.

[0029] In some embodiments, the control component 11 is configured to capture at least one reference image before capturing the current wrist image, and obtain the gesture corresponding to each reference image. Reference images corresponding to the wrist are captured for different gestures to obtain a mapping relationship between the gestures and the reference images. For example, an image of the wrist in a clenched fist state is captured as the reference image corresponding to the clenched fist gesture; an image of the wrist in an open palm state is captured as the reference image corresponding to the open palm gesture, and so on. In the clenched fist state, the five fingers are in a folded state, and in the open palm state, the five fingers are in an extended state.

[0030] In some embodiments, the control component 11 is configured to obtain feature values ​​of the wrist image, compare the feature values ​​of the wrist image with the feature values ​​of each reference image, and obtain a reference image whose similarity exceeds a preset threshold value as the reference image that matches the wrist image. If the number of reference images whose similarity exceeds the preset threshold value is greater than or equal to two, the reference image with the greatest similarity is selected as the reference image that matches the wrist image.

[0031] When light-emitting element 102 emits infrared light, the image captured by wrist image acquisition component 10 includes wrist vein features. This image of the veins is formed by utilizing the absorption of near-infrared light by hemoglobin in flowing blood. Hand gestures are controlled by the contraction and expansion of different muscles in the arm. For example, when a hand gesture is a fist or an open palm, the contraction and expansion of these muscles can affect the position of wrist veins. In particular, the movement of muscles and tendons in these gestures can cause noticeable changes in the position and thickness of the subcutaneous veins at the wrist. Different vein images correspond to different gestures, enabling gesture recognition through vein images.

[0032] When the light-emitting element 102 emits white light, the image collected by the wrist image acquisition component 10 includes wrist skin texture features. The gestures of the human hand are controlled by the contraction and expansion changes of different muscles in the arm. For example, the gesture is making a fist or opening the palm, and the contraction and expansion of different muscles will affect the changes in the wrist skin texture. In particular, because gestures such as making a fist or opening the palm involve changes in muscles or tendons, the skin texture at the wrist shows obvious position changes. Different skin textures correspond to different gestures, making it possible to recognize gestures through wrist skin images.

[0033] In the disclosed embodiment, by capturing the current wrist image, comparing the wrist image with a pre-saved reference image, and responding to the gesture corresponding to the matching reference image, the method of recognizing gestures through wrist images is realized by utilizing the characteristic that the corresponding wrist images in different gesture states are also different. The operation is simple and efficient, and it does not rely on ambient light and professional equipment, and has strong versatility.

[0034] Furthermore, the control component stores a mapping relationship between gestures and operating instructions, and obtains the operating instructions corresponding to the recognized gestures from the mapping relationship to operate the target in the operated device (such as an AR device, VR device, smart TV, smart projector, etc.). Alternatively, the control component stores a mapping relationship between the combination of gestures and other sensor parameters and operating instructions, and obtains the operating instructions corresponding to the recognized gesture and the combination of current sensor parameters from the mapping relationship to operate the target in the operated device. By combining with other sensor parameters, it can match multiple operating instructions and implement multiple operations on the target in the operated device. The other sensor parameters can be parameters detected by an accelerometer, gravity sensor, etc., indicating that the gesture recognition device is in a vertical or horizontal state, parameters indicating that the gesture recognition device is in motion or a stationary state, etc.

[0035] The application of this gesture recognition device does not require the device and the user's wrist to be within the monitoring range of the operated device, and the operation is free and comfortable. By using the gesture recognition device provided by the embodiment of the present disclosure, the operated device can be conveniently operated in a non-contact and non-direct-view state, and it can be worn in the form of an embedded wrist wearable device, which is convenient for users to carry with them and use at any time.

[0036] Based on the same concept, the present disclosure provides a gesture recognition method. This method can be applied to the gesture recognition device described above and can be executed by a control component in the gesture recognition device. FIG3 shows a flow chart of the gesture recognition method. The method can include steps 301 and 302.

[0037] In step 301, a current wrist image is acquired.

[0038] In some embodiments, before acquiring the current wrist image, the method further includes acquiring at least one reference image and acquiring the gesture corresponding to each reference image. The gesture recognition device acquires reference images corresponding to the wrist under different gestures to obtain a mapping relationship between the gestures and the reference images. For example, an image of the wrist in a clenched fist state may be acquired as the reference image corresponding to the clenched fist gesture; an image of the wrist in an open palm state may be acquired as the reference image corresponding to the open palm gesture, and so on. Exemplarily, the reference image may include wrist vein features and / or wrist skin texture features.

[0039] In some embodiments, before acquiring the current wrist image, the method further includes: entering a gesture detection state in response to a control instruction and controlling the wrist image acquisition component to activate. The control instruction is not limited to the form of the control instruction, and may be entering the gesture detection state and controlling the wrist image acquisition component to activate in response to a voice command; or entering the gesture detection state and controlling the wrist image acquisition component to activate in response to a click of a control button, where the control button may be a physical button or a virtual button configured in an application.

[0040] In step 302 , the wrist image is compared with at least one pre-stored reference image, and a gesture corresponding to the reference image that matches the wrist image is responded to.

[0041] In some embodiments, the wrist image is compared with at least one pre-saved reference image, and the gesture corresponding to the reference image matching the wrist image is responded to, including: obtaining the feature value of the wrist image, comparing the feature value of the wrist image with the feature value of each reference image, obtaining a reference image whose similarity exceeds a preset threshold as the reference image matching the wrist image, and responding to the gesture corresponding to the reference image matching the wrist image.

[0042] When the number of reference images whose similarity exceeds a preset threshold is greater than or equal to 2, the reference image with the greatest similarity is selected as the reference image to be matched with the wrist image.

[0043] When the wrist image is a vein image, the eigenvalue of the wrist image indicates the location and thickness of the veins in the wrist image. The location and thickness of the veins in the reference images corresponding to different gestures are different, meaning that the eigenvalues ​​of the reference images for different gestures are different. When the wrist image is a wrist skin image, the eigenvalue of the wrist image indicates the location of the skin texture in the wrist image. The location of the skin texture in the reference images corresponding to different gestures are different, meaning that the eigenvalues ​​of the reference images for different gestures are different.

[0044] The wrist image is compared with the reference image to calculate a hash value of the wrist image and a hash value of the reference image. The similarity between the hash value of the wrist image and the hash value of the reference image is then calculated, and the reference image with the highest similarity, which is greater than a preset threshold, is selected as the reference image with the highest similarity. It should be noted that there are many ways to calculate the similarity between two images, and using hash values ​​for similarity calculation is merely an example and is not intended to be limiting.

[0045] Suppose there are four images, namely z1, z2, q1 and q2, and the similarities of these four images are shown in Table 1. The following example is given based on this table: Suppose the current wrist image is z1, the similarity between z1 and the reference image z2 is 0.86, and the similarities with the reference images q1 and q2 do not exceed 0.79. Assuming that 0.82 is used as the preset threshold, z2 meets the highest similarity and is greater than 0.82. The gesture corresponding to z2 is used as the gesture of the current wrist image. If it is known that the gesture of z2 is an open palm, then the gesture of z1 is also an open palm; Suppose the current wrist image is q1, the similarity between q1 and q2 is 0.93, and the similarities with z1 and z2 do not exceed 0.74. Assuming that 0.82 is used as the preset threshold, q2 meets the highest similarity and is greater than 0.82. The gesture corresponding to q2 is used as the gesture of the current wrist image. If it is known that the gesture of q2 is a fist, then the gesture of q1 is also a fist.

[0046] Table 1 Similarity between images

[0047] Illustratively, at least one of the reference images includes a reference image captured from the wrist in a clenched fist gesture and a reference image captured from the wrist in an open palm state. This may include reference images captured when the fist is clenched and the fist is at different angles to the wrist, and reference images captured when the palm is open and the palm is at different angles to the wrist. For example, a first reference image may be captured when the palm is open and the palm and wrist are aligned, a second reference image may be captured when the palm is open and bent toward the inside of the wrist, and a third reference image may be captured when the palm is open and bent toward the outside of the wrist. The capture process for the clenched fist and open palm states is similar.

[0048] Among them, when the fist is clenched, the muscles at the wrist contract, and the image of the wrist in the muscle contraction state is collected as the reference image corresponding to the fist gesture, while when the palm is open, the muscles at the wrist expand, and the image of the wrist in the muscle expansion state is collected as the reference image corresponding to the open palm gesture.

[0049] In some embodiments, a mapping relationship between a combination of gestures and other sensor parameters and an operating instruction is pre-stored. After obtaining a gesture corresponding to a reference image that matches the wrist image, the method further includes obtaining a combination of the gesture and the currently obtained other sensor parameters, obtaining an operating instruction corresponding to the combination from the mapping relationship, and controlling the operated device in accordance with the operating instruction. The other sensor parameters may be parameters detected by an accelerometer, gravity sensor, or the like indicating that the gesture recognition device is in a vertical or horizontal state, or parameters indicating that the gesture recognition device is in motion or at rest. This method allows for convenient non-contact, non-sighted operation of the operated device, and is wearable as an embedded wrist-worn device, making it easy for the user to carry and use at any time.

[0050] In an exemplary embodiment, taking the use of a gesture recognition device to control an AR device or a VR device as an example, FIG4 shows a flow chart of a method for controlling an AR device or a VR device with gestures, and the method flow may include steps 401 to 408 .

[0051] In step 401 , after calibration, baseline images of the wrist in the open palm and clenched fist states are captured as comparison data.

[0052] In step 402, the gesture detection state is entered, the wrist image acquisition component is started and the current wrist image is acquired.

[0053] In step 403 , the current wrist image is compared with a pre-taken reference image.

[0054] In step 404 , it is determined whether the current wrist image is similar to the reference image in the open palm state. If so, step 405 is executed; otherwise, step 406 is executed.

[0055] In step 405 , if the gesture is recognized as an open palm, step 408 is executed.

[0056] In step 406 , it is determined whether the current wrist image is similar to the reference image in the fist-clenching state. If so, step 407 is executed. If not, the process returns to step 402 .

[0057] In step 407 , the gesture is recognized as a fist, and step 408 is executed.

[0058] In step 408, the gesture is combined with the combination of the back of the hand state and the waving direction to determine the operation instruction, and the operation instruction is sent to the AR device or VR device; wherein the back of the hand state includes a vertical state or a horizontal state, and the waving direction includes a horizontal direction or a vertical direction.

[0059] For example, the mapping relationship between gestures and operation instructions is defined as shown in Table 2. Based on whether the recognized gesture is a clenched fist or an open palm, and in combination with the back of the hand state and the waving direction detected by the sensor, the operation of the spatial target of the AR device or VR device is defined.

[0060] Table 2 Mapping relationship between gestures and operation instructions

[0061] The mapping relationships between gestures and operation instructions listed in Table 2 are examples only. For example, a double-click in the open palm state (a double-click can be detected by two consecutive vibrations) can correspond to one operation instruction. In addition to the fist and open palm states, the index finger state (the index finger and the other fingers are in different states, for example, the index finger is straight and the other fingers are clenched; or the index finger is clenched and the other fingers are straight) can also correspond to another operation instruction when double-clicking in the index finger state (a double-click can be detected by two consecutive vibrations). It is also possible to detect images of both wrists simultaneously to obtain more operations.

[0062] In the disclosed embodiment, by collecting the current wrist image, comparing the wrist image with a pre-saved reference image, and responding to the gesture corresponding to the matching reference image, the characteristic that the corresponding wrist images are different under different gesture states is utilized to realize a human-computer interaction method of recognizing gestures through wrist images. The operation is simple and efficient, and does not rely on ambient light and professional equipment, and has strong versatility.

[0063] Furthermore, a mapping relationship between gestures and operation instructions is saved, and the operation instructions corresponding to the recognized gestures are obtained from this mapping relationship to operate the target in the operated device (such as an AR device, VR device, smart TV, smart projector, etc.). Alternatively, a mapping relationship between the combination of gestures and other sensor parameters and operation instructions is saved, and the operation instructions corresponding to the recognized gesture and the combination of current sensor parameters are obtained from this mapping relationship to operate the target in the operated device. By combining with other sensor parameters, multiple operation instructions can be matched, enabling multiple operations on the target in the operated device. The other sensor parameters can be parameters detected by an accelerometer, gravity sensor, etc., indicating that the gesture recognition device is in a vertical or horizontal state, parameters indicating that the gesture recognition device is in motion or at rest, etc.

[0064] The application of this gesture recognition method does not require the user's wrist to be within the monitoring range of the operated device, and the operation is free and comfortable. By using the gesture recognition method provided by the embodiment of the present disclosure, the operated device can be conveniently operated in a non-contact and non-direct-view state, and it can be worn in the form of an embedded wrist wearable device, which is convenient for users to carry with them and use at any time.

[0065] It should be noted that in the embodiment of the present disclosure, the wrist image and the reference image can be images taken from the inner side of the wrist (the wrist surface on the same side as the palm surface), and the wrist image and the reference image can also be images taken from the outer side of the wrist (the wrist surface on the same side as the back of the hand). Figure 5 shows a schematic diagram of the wrist.

[0066] The steps of the various methods above are divided only for clarity of description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this disclosure. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this disclosure.

[0067] The present disclosure provides a gesture recognition device. The implementation of this device can be found in the relevant description of the method embodiments and will not be repeated here. Figure 6 shows a schematic diagram of the structure of this device, which may include: an acquisition module 601 configured to acquire a current wrist image; a comparison module 602 configured to compare the wrist image with at least one pre-stored reference image and respond to the gesture corresponding to the reference image that matches the wrist image.

[0068] The functions or modules included in the apparatus provided in the embodiments of the present disclosure can be used to execute the method described in the method embodiment. Its implementation and technical effects can be referred to the description of the above method embodiment, and for the sake of brevity, they will not be repeated here.

[0069] It should be noted that all modules involved in this embodiment are logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovations of this disclosure, this embodiment does not include units that are not closely related to solving the technical problems proposed by this disclosure. However, this does not mean that other units do not exist in this embodiment.

[0070] 7 , an embodiment of the present disclosure provides an electronic device, comprising: at least one processor 701; a memory 702 on which at least one program is stored, and when the at least one program is executed by the at least one processor, the at least one processor implements the above method; and at least one I / O interface 703, connected between the processor and the memory, and configured to implement information interaction between the processor and the memory.

[0071] Among them, the processor 701 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 702 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read-write interface) 703 is connected between the processor 701 and the memory 702, and can realize information exchange between the processor 701 and the memory 702, including but not limited to a data bus (Bus), etc.

[0072] In some embodiments, the processor 701 , the memory 702 , and the I / O interface 703 are connected to each other via a bus, and further connected to other components of the computing device.

[0073] This embodiment further provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method provided in this embodiment is implemented. To avoid repeated description, the specific steps of the method are not repeated here.

[0074] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods applied for above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As is well known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable, and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0075] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0076] Those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present embodiment and to form different embodiments.

[0077] It is understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present disclosure, and the present disclosure is not limited thereto. Those skilled in the art may make various modifications and improvements without departing from the spirit and substance of the present disclosure, and such modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A gesture recognition device, include: Wrist image acquisition component and control component; The wrist image acquisition component is configured to acquire a current wrist image and transmit it to the control component; The control component is configured to compare the wrist image with at least one pre-stored reference image and respond to a gesture corresponding to the reference image that matches the wrist image.

2. The gesture recognition device according to claim 1, in, The gesture recognition device is embedded in the wrist wearable device, and the wrist image acquisition component faces the side where the wrist is located.

3. The gesture recognition device according to claim 1, in, The control component is further configured to enter a gesture detection state according to a control instruction before collecting the current wrist image, and control the wrist image collection component to start.

4. The gesture recognition device according to claim 1, in, The wrist image acquisition component includes an image sensor and a light emitting element; The control component is configured to control the light emitting element to emit light and control the image sensor to turn on.

5. The gesture recognition device according to claim 1, in, The control component is configured to acquire the at least one reference image and obtain the gesture corresponding to each of the reference images before acquiring the current wrist image.

6. The gesture recognition device according to claim 1, in, The control component is configured to obtain a feature value of the wrist image, compare the feature value of the wrist image with the feature value of each of the reference images, and obtain a reference image whose similarity exceeds a preset threshold as a reference image matching the wrist image.

7. A gesture recognition method, include: Get the current wrist image; The wrist image is compared with at least one pre-stored reference image, and a gesture corresponding to the reference image matching the wrist image is responded to.

8. The gesture recognition method according to claim 7, in, Before acquiring the current wrist image, the method further includes: The at least one reference image is acquired, and a gesture corresponding to each of the reference images is acquired.

9. The gesture recognition method according to claim 7, in, Before acquiring the current wrist image, the method further includes: Enter the gesture detection state according to the control command, and control the wrist image acquisition component to start.

10. The gesture recognition method according to claim 7, in, The step of comparing the wrist image with at least one pre-stored reference image and responding to a gesture corresponding to the reference image matching the wrist image includes: Acquire a feature value of the wrist image, compare the feature value of the wrist image with the feature value of each of the reference images, obtain a reference image whose similarity exceeds a preset threshold value as the reference image matching the wrist image, and respond to a gesture corresponding to the reference image matching the wrist image.

11. An electronic device, include: at least one processor; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 7 to 10; At least one I / O interface is connected between the processor and the memory and is configured to implement information interaction between the processor and the memory.

12. A computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 7 to 10.

Citation Information

Patent Citations

  • Gesture recognition method and apparatus

    CN104679229A

  • Device and method for detecting gestures on the skin

    CN105980961A

  • Instruction output method and device based on wrist or hand skin three-dimensional shape changes

    CN110703923A

  • Information processing device, information processing method, and program

    CN111837094A

  • Gesture recognition method and device, equipment and storage medium

    CN116665298A