Motion posture recognition device and method

Abstract

The invention provides a motion posture recognition device and method.The motion posture recognition device comprises at least two energy buttons, each energy button comprises a position sensor and a wireless communication module, and the energy buttons are used for collecting and transmitting position information in real time; and the posture recognition system is used for carrying out posture recognition according to the position information of all the energy buttons to obtain a motion posture recognition result. According to the technical scheme, efficient and accurate recognition of the motion posture is achieved.

Description

Background Art

[0002] With the rapid development of sensor technology and computer technology, significant progress has been made in human motion tracking and motion posture recognition technology. Traditional motion posture recognition devices mainly rely on optical, mechanical, acoustic, electromagnetic, or inertial posture tracking technology. Among them, although the optical posture tracking method has high accuracy, it is limited by cost, usage scenarios, and data processing complexity, making it difficult to be widely applied on embedded platforms or mobile devices. For the technology based on posture sensors, it mainly relies on manual extraction of feature values plus traditional machine learning algorithms such as KNN, SVM, etc. These methods require high professional knowledge and have limitations in feature value extraction. Summary of the Invention

[0003] This application provides a motion posture recognition device and method to achieve efficient and accurate recognition of motion postures.

[0004] In a first aspect, a motion posture recognition device is provided, including at least two energy buttons. Each of the energy buttons includes a position sensor and a wireless communication module. Among them,

[0005] The energy buttons are used to collect and transmit position information in real time;

[0006] It further includes:

[0007] A posture recognition system, which is used to perform posture recognition based on the position information of all the energy buttons to obtain a motion posture recognition result.

[0008] In the above technical solution, by setting energy buttons to collect and transmit position information in real time, and a posture recognition system to perform posture recognition based on the position information of all the energy buttons to obtain a motion posture recognition result, efficient and accurate recognition of motion postures is achieved.

[0009] In a specific feasible implementation, the posture recognition system includes:

[0010] A neural network module, which is used to construct a convolutional neural network;

[0011] A network training module, which is used to train the convolutional neural network to obtain a final neural network;

[0012] A posture recognition module, which is used to perform posture recognition using the final neural network to obtain a motion posture recognition result.

[0013] In a specific feasible implementation, the posture recognition system further includes:

[0014] A model application module, which is used to deploy the final neural network to a mobile terminal.

[0015] In a specific feasible implementation, the attitude recognition system further includes:

[0016] A data acquisition module, configured to receive the position information of all the energy buttons;

[0017] A preprocessing module, configured to preprocess the position information.

[0018] In a second aspect, there is provided a method for recognizing a motion attitude as described above, including the following steps:

[0019] Using the energy buttons to collect and transmit position information in real time; wherein, the number of the energy buttons is at least two, and each energy button includes a position sensor and a wireless communication module;

[0020] Using the attitude recognition system to perform attitude recognition based on the position information of all the energy buttons to obtain a motion attitude recognition result.

[0021] In the above technical solution, by setting the energy buttons for collecting and transmitting position information in real time, and the attitude recognition system for performing attitude recognition based on the position information of all the energy buttons to obtain a motion attitude recognition result, efficient and accurate recognition of the motion attitude is achieved.

[0022] In a specific feasible implementation, it further includes:

[0023] Using a neural network module to construct a convolutional neural network;

[0024] Using a network training module to train the convolutional neural network to obtain a final neural network;

[0025] Using an attitude recognition module to perform attitude recognition using the final neural network to obtain a motion attitude recognition result.

[0026] In a specific feasible implementation, it further includes:

[0027] Using a model application module to deploy the final neural network to a mobile terminal.

[0028] In a specific feasible implementation, it further includes:

[0029] Using the data acquisition module to receive the position information of all the energy buttons;

[0030] Using the preprocessing module to preprocess the position information.

[0031] In a third aspect, an electronic device is provided. The electronic device includes a processor coupled to a memory. At least one computer program is stored in the memory and is loaded and executed by the processor to enable the electronic device to implement any one of the motion posture recognition methods described above.

[0032] In the above technical solution, by providing energy buttons for real-time collection and transmission of position information, and a posture recognition system for performing posture recognition based on the position information of all the energy buttons to obtain a motion posture recognition result, efficient and accurate recognition of the motion posture is achieved.

[0033] In a fourth aspect, a computer-readable storage medium is provided. At least one computer program is stored in the computer-readable storage medium and is loaded and executed by a processor to enable the computer-readable storage medium to implement any one of the motion posture recognition methods described above.

[0034] In the above technical solution, by providing energy buttons for real-time collection and transmission of position information, and a posture recognition system for performing posture recognition based on the position information of all the energy buttons to obtain a motion posture recognition result, efficient and accurate recognition of the motion posture is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a structural block diagram of the motion posture recognition device provided by an embodiment of the present application;

[0036] Figure 2 It is a flow block diagram of the motion posture recognition method provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The present application will be further described in detail below with reference to the drawings and embodiments. Through these descriptions, the features and advantages of the present application will become clearer and more definite.

[0038] The special term "exemplary" here means "serving as an example, an embodiment or an illustration". Any embodiment described as "exemplary" here does not have to be construed as superior to or better than other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0039] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0040] To facilitate the understanding of the motion posture recognition device and method provided in the embodiments of the present application, its application scenario is first described. The motion posture recognition device and method provided in the embodiments of the present application are used to achieve efficient and accurate recognition of motion postures. With the rapid development of sensor technology and computer technology, significant progress has been made in human posture tracking and motion posture recognition technology. Traditional motion posture recognition devices mainly rely on optical, mechanical, acoustic, electromagnetic, or inertial posture tracking technologies. Among them, although the optical posture tracking method has high accuracy, it is limited by cost, usage scenarios, and data processing complexity, and it is difficult to be widely applied on embedded platforms or mobile devices. And the technology based on posture sensors mainly relies on manually extracting feature values plus traditional machine learning algorithms, such as KNN, SVM, etc. These methods have high requirements for professional knowledge and have limitations in feature value extraction. Therefore, the embodiments of the present application provide a motion posture recognition device and method to achieve efficient and accurate recognition of motion postures. The following will be described in detail with specific drawings by way of embodiments.

[0041] Reference Figure 1 and Figure 2 , Figure 1 is the structural block diagram of the motion posture recognition device provided in the embodiments of the present application; Figure 2 is the flow block diagram of the motion posture recognition method provided in the embodiments of the present application.

[0042] In Figure 1 , the embodiments of the present application provide a motion posture recognition device, including at least two energy buttons, and each of the energy buttons includes a position sensor and a wireless communication module, wherein,

[0043] the energy button is used to collect and transmit position information in real time;

[0044] It further includes:

[0045] a posture recognition system, which is used to perform posture recognition according to the position information of all the energy buttons to obtain a motion posture recognition result.

[0046] In the above technical solution, by setting the energy buttons to collect and transmit position information in real time; and the posture recognition system to perform posture recognition according to the position information of all the energy buttons to obtain a motion posture recognition result, efficient and accurate recognition of motion postures is achieved.

[0047] In a specific feasible implementation solution, the posture recognition system includes:

[0048] a neural network module, which is used to construct a convolutional neural network;

[0049] a network training module, which is used to train the convolutional neural network to obtain a final neural network;

[0050] An attitude recognition module, configured to use the final neural network for attitude recognition to obtain a motion attitude recognition result.

[0051] In a specific feasible implementation, the attitude recognition system further includes:

[0052] A model application module, configured to deploy the final neural network to a mobile terminal.

[0053] In a specific feasible implementation, the attitude recognition system further includes:

[0054] A data acquisition module, configured to receive the position information of all the energy buttons;

[0055] A preprocessing module, configured to preprocess the position information.

[0056] In Figure 2 this application embodiment provides a motion attitude recognition method as described above, including the following steps:

[0057] Use energy buttons to collect and transmit position information in real time; wherein, the number of the energy buttons is at least two, and each energy button includes a position sensor and a wireless communication module;

[0058] Use the attitude recognition system to perform attitude recognition according to the position information of all the energy buttons to obtain a motion attitude recognition result.

[0059] In the above technical solution, by setting energy buttons for collecting and transmitting position information in real time, and an attitude recognition system for performing attitude recognition according to the position information of all the energy buttons to obtain a motion attitude recognition result, efficient and accurate recognition of motion attitudes is achieved.

[0060] In a specific feasible implementation, it further includes:

[0061] Use a neural network module to construct a convolutional neural network;

[0062] Use a network training module to train the convolutional neural network to obtain a final neural network;

[0063] Use the attitude recognition module to use the final neural network for attitude recognition to obtain a motion attitude recognition result.

[0064] In a specific feasible implementation, it further includes:

[0065] Use the model application module to deploy the final neural network to a mobile terminal.

[0066] In a specific feasible implementation, it further includes:

[0067] Use the data acquisition module to receive the position information of all the energy buttons;

[0068] Use the preprocessing module to preprocess the position information.

[0069] The embodiment of the present application also provides an electronic device, which includes a processor, the processor is coupled with a memory, and at least one computer program is stored in the memory. The at least one computer program is loaded and executed by the processor to enable the electronic device to implement any one of the motion attitude recognition methods.

[0070] In the above technical solution, by setting energy buttons for real-time collection and transmission of position information, and an attitude recognition system for performing attitude recognition based on the position information of all the energy buttons to obtain a motion attitude recognition result, efficient and accurate recognition of the motion attitude is achieved.

[0071] The embodiment of the present application also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to enable the computer-readable storage medium to implement any one of the motion attitude recognition methods.

[0072] In the above technical solution, by setting energy buttons for real-time collection and transmission of position information, and an attitude recognition system for performing attitude recognition based on the position information of all the energy buttons to obtain a motion attitude recognition result, efficient and accurate recognition of the motion attitude is achieved.

[0073] Those skilled in the art of the present application know that the present application can be implemented as a system, a method, or a computer program product.

[0074] Therefore, the present disclosure can be specifically implemented in the following forms: it can be completely hardware, can be completely software (including firmware, resident software, microcode, etc.), or can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" in this article. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable media contains computer-readable program code.

[0075] Any combination of one or more computer-readable media may be employed. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present document, a computer-readable storage medium may be any tangible medium that contains or stores a program which can be used by or in connection with an instruction execution system, apparatus, or device.

[0076] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application. On this basis, various substitutions and improvements can be made to the present application, and all of these fall within the protection scope of the present application.

Claims

1. A motion posture recognition device, characterized in that, Comprising: At least two energy buttons, each of the energy buttons including a position sensor and a wireless communication module, wherein The energy buttons are configured to collect and transmit position information in real time; Further comprising: An attitude recognition system configured to perform attitude recognition based on the position information of all the energy buttons to obtain a motion attitude recognition result.

2. The motion attitude recognition device according to claim 1, wherein The attitude recognition system includes: A neural network module configured to construct a convolutional neural network; A network training module configured to train the convolutional neural network to obtain a final neural network; An attitude recognition module configured to perform attitude recognition using the final neural network to obtain a motion attitude recognition result.

3. The motion posture recognition device according to claim 2, wherein The attitude recognition system further includes: A model application module configured to deploy the final neural network to a mobile terminal.

4. The motion attitude recognition device according to claim 3, wherein The attitude recognition system further includes: A data acquisition module configured to receive the position information of all the energy buttons; A preprocessing module configured to preprocess the position information.

5. The described motion posture recognition method is characterized in that, Including the following steps: Using the energy buttons to collect and transmit position information in real time; wherein the number of the energy buttons is at least two, and each of the energy buttons includes a position sensor and a wireless communication module; Using the attitude recognition system to perform attitude recognition based on the position information of all the energy buttons to obtain a motion attitude recognition result.

6. The motion posture recognition method according to claim 5, wherein, Further comprising: Using the neural network module to construct a convolutional neural network; Using the network training module to train the convolutional neural network to obtain a final neural network; Using the attitude recognition module to perform attitude recognition using the final neural network to obtain a motion attitude recognition result.

7. The motion posture recognition method according to claim 6, characterized in that Further comprising: Using the model application module to deploy the final neural network to a mobile terminal.

8. The motion posture recognition method according to claim 7, wherein Further comprising: Using the data acquisition module to receive the position information of all the energy buttons; Using the preprocessing module to preprocess the position information.

9. An electronic device, characterized in that, The electronic device includes a processor, the processor is coupled to a memory, and at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the motion attitude recognition method according to any one of claims 5 to 8.

10. A computer-readable storage medium, characterized in that, At least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor so that the computer-readable storage medium implements the motion attitude recognition method according to any one of claims 5 to 8.

Images