Patient automatic identification method and device in multi-person scene, equipment and medium

Abstract

The invention provides an automatic patient identification method and device in a multi-person scene, equipment and a medium, and relates to the technical field of smart medical treatment, and the specific implementation mode comprises the steps that a multi-person scene picture including a target patient is collected, and the posture of the target patient in the multi-person scene picture is a key posture; human body images in the multi-person scene picture are recognized, human body posture analysis is carried out on each recognized human body image, and multiple groups of human body posture data are obtained; matching the multiple groups of human body posture data with preset key postures of a target patient, and judging the human body image corresponding to the successfully matched human body posture data as the target patient; wherein the key posture of the target patient is specified action posture data different from other people. According to the invention, the problem that the existing rehabilitation equipment cannot accurately identify the patient in a scene in which multiple persons exist is solved, so that the target patient can be accurately identified and tracked in the scene in which multiple persons exist.

Description

Technical Field

[0001] The present application relates to the field of computer technology, specifically to the field of smart medical technology, and in particular to a method, device, equipment and medium for automatically identifying patients in a multi-person scenario. Background Art

[0002] In the current field of rehabilitation medicine, rehabilitation training programs and rehabilitation equipment are developing rapidly. From the initial picture-based training (patients imitate the sample pictures in the rehabilitation program), to the later mechanical guidance, and then to today's intelligent rehabilitation equipment, there have been great improvements in both technology and training effects, and at the same time, the user-friendliness has also been greatly improved. More and more patients are more willing to accept and use them for a long time, which also has a more positive feedback and guiding effect on the relevant development of the rehabilitation field.

[0003] With the development of science and technology and the improvement of productivity, today's rehabilitation equipment has become more intelligent: the data acquisition module uses a high-definition optical module, data processing is faster and more accurate, and the guidance methods and feedback are more colorful (including interesting body movement games, colorful picture effects, etc.). Although the degree of intelligence of rehabilitation equipment is getting higher and higher, there are still some technical flaws. For example, when there are multiple people in the field of view of the optical module of data acquisition, it is impossible to distinguish who is the patient. Therefore, it is affected by other people in the field of view as interference factors, and it is impossible to accurately track the patient. Summary of the invention

[0004] In view of the problem that the data acquisition module of existing rehabilitation equipment cannot accurately identify and track patients in a scenario with multiple people, a method, device, equipment and medium for automatic patient identification in a scenario with multiple people are provided.

[0005] According to a first aspect, a method for automatically identifying patients in a multi-person scenario is provided, comprising:

[0006] Collecting a multi-person scene picture including a target patient, wherein the body posture of the target patient is a key posture in the multi-person scene picture;

[0007] Recognize the human body images in the multi-person scene picture, and perform human body posture analysis on each recognized human body image to obtain multiple groups of human body posture data;

[0008] The multiple groups of human posture data are matched with the preset key postures of the target patient respectively, and the human body image corresponding to the successfully matched human posture data is determined to be the target patient; wherein the key posture of the target patient is the specified action posture data that distinguishes it from other people.

[0009] According to a second aspect, a patient automatic identification device in a multi-person scenario is provided, comprising:

[0010] A data acquisition module, used for acquiring a multi-person scene picture including a target patient, wherein the body posture of the target patient is a key posture in the multi-person scene picture;

[0011] A posture analysis module is used to identify human body images in the multi-person scene picture, and perform human body posture analysis on each identified human body image to obtain multiple groups of human body posture data;

[0012] The target recognition module is used to match the multiple groups of human posture data with the preset key postures of the target patient respectively, and determine the human body image corresponding to the successfully matched human posture data as the target patient; wherein the key posture of the target patient is the specified action posture data that distinguishes it from other people.

[0013] According to a third aspect, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a method such as any embodiment of a method for automatic patient identification in a multi-person scenario.

[0014] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, a method of any embodiment of the method for automatic patient identification in a multi-person scenario is implemented.

[0015] According to the scheme of the present application, the data acquisition and analysis processing module of the existing intelligent rehabilitation equipment is optimized: by presetting the key posture of the target patient in the human posture analysis to lock the target patient, and performing human posture data analysis on the original image based on the imaging of the optical camera, thereby obtaining a set (quantity > 1) of human posture data, and comparing each set of human posture data with the preset key posture of the target patient. If the comparison is successful, it is determined that the character corresponding to the set of human posture data is the target patient, and the set of human posture data is locked. Thereafter, only the character corresponding to the set of human posture data is tracked, eliminating the influence of other people as interference factors on the user, thereby achieving accurate identification and tracking of the target patient in a scenario where multiple people are present. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0017] Figure 1 is an exemplary system architecture diagram to which some embodiments of the present application may be applied;

[0018] Figure 2 is a flow chart of an embodiment of a method for automatic patient identification in a multi-person scenario according to the present application;

[0019] Figure 3 is a structural schematic diagram of an embodiment of a patient automatic identification device in a multi-person scenario according to the present application;

[0020] Figure 4 It is a block diagram of an electronic device used to implement the method for automatic patient identification in a multi-person scenario of an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the method for automatic patient identification in a multi-person scenario or an apparatus for automatic patient identification in a multi-person scenario of the present application can be applied.

[0024] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0025] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as video applications, live broadcast applications, instant messaging tools, email clients, social platform software, etc.

[0026] The terminal devices 101, 102, 103 here can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers and desktop computers, etc. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, multiple software or software modules for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0027] The server 105 may be a server that provides various services, such as a background server that provides support for the terminal devices 101, 102, and 103. The background server may analyze and process the received data such as eye movement characteristics, and feed back the processing results to the terminal device.

[0028] It should be noted that the automatic patient identification method in a multi-person scenario provided in the embodiment of the present application can be executed by the server 105 or the terminal devices 101, 102, 103. Accordingly, the automatic patient identification device in a multi-person scenario can be set in the server 105 or the terminal devices 101, 102, 103.

[0029] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0030] Continue to refer Figure 2 , shows a process 200 of an embodiment of a method for automatically identifying patients in a multi-person scenario according to the present application. The method for automatically identifying patients in a multi-person scenario includes the following steps:

[0031] Step 201 : collecting a multi-person scene picture including a target patient, wherein the body posture of the target patient is a key posture in the multi-person scene picture.

[0032] Step 202, identifying human body images in the multi-person scene picture, and performing human body posture analysis on each identified human body image to obtain multiple groups of human body posture data.

[0033] Step 203, respectively matching the multiple groups of human posture data with the preset key postures of the target patient, and determining the human body image corresponding to the successfully matched human posture data as the target patient; wherein the key posture of the target patient is the specified action posture data that is different from that of other people.

[0034] Since the field of view of the optical module camera currently used for data collection is generally fixed, the specific parameters of the field of view are determined when the hardware is manufactured. Therefore, the field of view of the optical camera is fixed, and its imaging cannot be changed manually. Therefore, in this embodiment, the automatic patient identification method in a multi-person scenario runs on the execution subject (for example Figure 1 The server or terminal device shown in the figure can accurately identify the target patient in the scene where multiple people are present in the data acquisition module of the rehabilitation equipment, eliminate the interference of other people on the target patient in the original picture collected by the image acquisition module, accurately lock the target patient, and thus track and analyze the data of the target patient. This embodiment performs human posture data analysis on the original multi-person scene picture based on the imaging of the optical camera, obtains the human posture data corresponding to each human image in the multi-person scene picture, and compares it with the preset key posture data of the target patient, screens out the human posture data with the highest similarity to the preset key posture data of the target patient, and determines the human image corresponding to the human posture data as the target patient, locks the target patient, thereby realizing the positioning of the target patient, and then tracks and analyzes the image data of the target patient, thereby improving the accuracy and reliability of the intelligent rehabilitation equipment and realizing accurate and efficient patient identification and monitoring.

[0035] After obtaining the multi-person scene picture, it is first necessary to analyze the multi-person scene picture to determine multiple human body images in the multi-person scene. In some optional implementations of this embodiment, the human body images in the multi-person scene picture are identified, including: extracting human body contour features in the multi-person scene picture, and taking the maximum image area enclosed by the human body contour features as the human body image.

[0036] In the specific implementation, after obtaining the original multi-person scene picture, it is necessary to pre-process the picture first, including filtering low-frequency noise from the original picture and enhancing specific high-frequency components to improve the contrast and details of the picture, and obtain an enhanced high-quality picture. Next, determine the approximate position of the human body: extract the human body contour features in the enhanced high-quality picture, and perform background subtraction on the enhanced high-quality picture frame to separate the moving human body from the environmental background to determine the number of human body images; finally, the maximum image area enclosed by the determined human body contour features is used as the human body image. Among them, the human body contour feature extraction can be achieved by detecting the key features in the face area, such as the eyes, eyebrows, nose, mouth and chin, through the model, so as to extract the human body contour features.

[0037] In some optional implementations of the present embodiment, human posture analysis is performed on each identified human body image to obtain multiple sets of human posture data, including: for each of the human body images, posture features in the human body image are extracted, and all the obtained posture features constitute the human posture data of the human body image to obtain multiple sets of human posture data; the posture features include the position, angle and direction of the human skeletal joints.

[0038] In the specific implementation, the posture features in each human body image identified are extracted, and the human body posture analysis is performed respectively. The feature extraction can be performed by the human body posture recognition algorithm. The human body posture recognition algorithm mainly relies on computer vision and deep learning technology. By capturing the human body motion information in the image or video, the position and motion trajectory of the key points are extracted, thereby realizing the recognition and analysis of the human body posture. Specifically, firstly, the features related to the human body posture are extracted from the pre-processed high-quality pictures. These features may include the outline, joint points, texture information, etc. of the human body; then the key point detection is performed, and the position of the human body key point is found in the picture by using deep learning and other technologies. The human body key points correspond to the position, angle and direction of each skeletal joint of the human body, such as shoulders, knees, ankles, etc.; after obtaining the position of the key points, the relative position and angle between the key points are calculated to obtain multiple groups of human body posture data.

[0039] After obtaining multiple groups of human posture data, they are matched with preset key postures of the target patient respectively. In some optional implementations of this embodiment, the human body image corresponding to the successfully matched human posture data is determined as the target patient, including:

[0040] Determining the number of human body images in the multi-person scene picture, and calculating the similarity between each group of human body posture data and the key posture;

[0041] If the number of human body images = 2, the human body image corresponding to the human body posture data having a similarity value greater than a first set threshold is determined as the target patient;

[0042] If the number of human body images is greater than 2, at least two groups of human body posture data whose similarity values ​​are greater than a second set threshold are selected, and the at least two groups of human body posture data are matched with the preset standard posture of the target patient, and the human body image corresponding to the successfully matched human body posture data is determined to be the target patient; wherein, the standard posture of the target patient is the standard posture corresponding to any specified posture in the rehabilitation training item corresponding to the target patient; and the first set threshold is greater than the second set threshold.

[0043] In this embodiment, the key posture data of the target patient is designated action posture data that is different from other people. Specifically, the key posture data is set according to the specific situation of the patient, and the target patient has designated action postures that are different from other people, for example, waving one arm, raising both hands, waving both hands, and other special actions agreed with the patient in advance.

[0044] When the data is compared for similarity, the number of human images in the multi-person scene picture is first determined. When the number of human images is small, for example, the number of images does not exceed 2, the similarity value is compared with the set first threshold value, so as to quickly lock the one with the highest similarity value. When the number of human images exceeds 2, in order to further improve the accuracy of recognition, the present embodiment performs two-layer screening. First, all similarity values ​​are preliminarily screened through the set second threshold value to filter out the parts with small similarity values. Next, the remaining human posture data with larger similarity values ​​and closer similarity values ​​are matched with the preset standard posture of the target patient, and the human image corresponding to the successfully matched human posture data is determined to be the target patient. Among them, the standard posture of the target patient is the standard posture corresponding to any specified posture in the rehabilitation training item corresponding to the target patient. In specific implementation, when presetting the key posture of the target patient, the key posture is set to any specified posture of the target patient in his rehabilitation training items, such as raising both hands; when presetting the standard posture of the target patient, the standard posture is set to the standard posture corresponding to any specified posture of the target patient in his rehabilitation training items; the human body posture data after the first round of screening is then accurately matched with the preset standard posture in the second round, so that the target patient is identified after screening, thereby ensuring the accuracy of identification and avoiding misidentification.

[0045] Among them, the first set threshold value is greater than the second set threshold value; in specific implementation, the first set threshold value can be set to 90%. Since it is easier to screen the target patient when the number of human body images is small, only one with a larger similarity value needs to be screened out; the second set threshold value can be set to 80%. First, a part of the data is preliminarily screened out from multiple groups of data, and then the target patient is further screened and located through matching of standard postures.

[0046] In order to further improve the analysis and calculation efficiency and reduce the amount of calculation, the method of the embodiment of the present invention also includes: after determining the target patient, placing the human body image of the target patient in a preset target frame, and tracking and analyzing the human body image in the preset target frame.

[0047] In some optional implementations of this embodiment, the target patient is guided to move by a set guiding method until the human body image of the target patient is placed in the preset target frame. In specific implementation, after locking the target patient, the target patient can be guided to move by image and / or voice guidance until the human body image of the target patient in the multi-person scene picture is located in the preset target frame. In this way, the tracking range of the target patient can be narrowed to the preset frame, thereby facilitating the analysis and tracking of the target patient's image, reducing the amount of calculation, and improving the efficiency of calculation and analysis.

[0048] In some optional implementations of this embodiment, the image acquisition device can also be driven to adjust the field of view direction and zoom ratio according to the current position of the target patient in the multi-person scene picture, so that the position of the target patient in the multi-person scene picture is within the preset target frame. In specific implementation, the image acquisition device can adjust the field of view direction and zoom ratio through the software processing of digital zoom, without making any adjustments to the hardware structure of the image acquisition device itself.

[0049] The patient automatic identification method in a multi-person scenario according to an embodiment of the present invention can be applied to rehabilitation training for patients with PD, stroke, etc., and mainly includes the following steps:

[0050] 1. Preset the key posture P-kt of the target patient in the training plan to identify and lock the target role.

[0051] 2. During the training preparation phase, the optical acquisition module performs imaging to obtain image A.

[0052] 3. The data analysis module performs posture analysis on image A and obtains several sets of posture data (PD1, PD2, PD3, PD4...).

[0053] 4. Compare all the posture data obtained with the preset key posture P-kt, and obtain two sets of data with similarity > 80%, namely: PD1 similarity 81.45%; PD3 similarity 98%.

[0054] 5. According to the comparison rules, the similarity of PD3 is much greater than that of PD1, so PD3 is determined to be the target patient and PD3 is locked;

[0055] 6. In subsequent training, only PD3 is tracked, and the posture data obtained after analysis is handed over to other modules for display.

[0056] In a specific embodiment, the execution process of the patient automatic identification method adopted by the rehabilitation training device is as follows:

[0057] (1) Patient Zhang San comes to the rehabilitation center for rehabilitation training;

[0058] (2) The staff selects Option 1 based on Zhang San’s actual situation and presets the key posture as “raising both hands”;

[0059] (3) Zhang San moves into the camera's field of view, and there is a staff member accompanying him in his recovery.

[0060] (4) The training preparation phase begins. The optical camera starts to capture data and Zhang San raises his hands high.

[0061] (5) The posture analysis module analyzes the camera imaging images and obtains two sets of posture data: PD1 and PD2.

[0062] (6) After comparing the posture data PD1 and the two hands raised, the similarity reaches 96%, and the similarity of PD2 is 1%, so PD1 is determined to be the posture data of patient Zhang San. At this time, the posture analysis module locks PD1.

[0063] (7) The training preparation phase ends and the training officially begins. The subsequent posture analysis module only tracks and analyzes the data of PD1. It is observed that the posture displayed on the big screen is consistent with Zhang San's movements.

[0064] (8) After a period of time, patient Zhang San successfully completed rehabilitation training.

[0065] Further references Figure 3 As an implementation of the methods shown in the above figures, the present application provides an embodiment of a patient automatic identification device in a multi-person scenario. The device embodiment is similar to Figure 2 Corresponding to the method embodiment shown in FIG. 1 , in addition to the features described below, the device embodiment may also include Figure 2 The device can be applied to various electronic devices.

[0066] like Figure 3 As shown, the patient automatic identification device 300 in a multi-person scene of this embodiment includes: a data acquisition module 301, used to collect multi-person scene pictures including a target patient, wherein the body posture of the target patient in the multi-person scene picture is a key posture; a posture analysis module 302, used to identify the human body images in the multi-person scene picture, and perform human body posture analysis on each identified human body image respectively to obtain multiple groups of human body posture data; a target recognition module 303, used to match the multiple groups of human body posture data with the preset key postures of the target patient respectively, and determine the human body image corresponding to the successfully matched human body posture data as the target patient; wherein the key posture of the target patient is the specified action posture data that is different from that of other people.

[0067] In this embodiment, the specific processing of the eye movement feature data acquisition module 301, the posture analysis module 302 and the target recognition module 303 of the patient automatic recognition device 300 in a multi-person scenario and the technical effects brought by them can be referred to respectively. Figure 2 The relevant descriptions of step 201, step 202 and step 203 in the corresponding embodiment are not repeated here.

[0068] In some optional implementations of this embodiment, the posture analysis module 302 extracts the human body contour features in the multi-person scene image, and uses the maximum image area enclosed by the human body contour features as the human body image.

[0069] In some optional implementations of the present embodiment, the posture analysis module 302 extracts the posture features in each of the human body images, and constructs the human body posture data of the human body image with all the posture features obtained to obtain multiple sets of human body posture data; the posture features include the position, angle and direction of the human body skeletal joints.

[0070] In some optional implementations of the present embodiment, the target recognition module 303 determines the number of human body images in the multi-person scene picture, and calculates the similarity between each group of the human body posture data and the key posture respectively; if the number of the human body images = 2, the human body image corresponding to the human body posture data whose similarity value is greater than the first set threshold is determined as the target patient; if the number of the human body images is greater than 2, at least two groups of human body posture data whose similarity value is greater than the second set threshold are selected, and the at least two groups of human body posture data are matched with the preset standard posture of the target patient, and the human body image corresponding to the successfully matched human body posture data is determined as the target patient; wherein, the standard posture of the target patient is the standard posture corresponding to any specified posture in the rehabilitation training item corresponding to the target patient; the first set threshold is greater than the second set threshold.

[0071] In some optional implementations of the present embodiment, the automatic patient identification device 300 in a multi-person scene also includes a tracking analysis module, which is used to place the human body image of the target patient in a preset target frame after determining the target patient, and to track and analyze the human body image in the preset target frame. Among them, the target patient can be guided to move so that the human body image of the target patient is placed in the preset target frame through a set guidance method. Alternatively, according to the current position of the target patient in the multi-person scene picture, the image acquisition device is driven to adjust the field of view direction and zoom ratio so that the position of the target patient in the multi-person scene picture is within the preset target frame.

[0072] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0073] like Figure 4 , is a block diagram of an electronic device according to a patient automatic identification method in a multi-person scenario according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0074] like Figure 4 As shown, the electronic device includes: one or more processors 401, a memory 402, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to an interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 401 is taken as an example.

[0075] The memory 402 is a non-transient computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable at least one processor to perform the method for automatically identifying patients in a multi-person scenario provided in the present application. The non-transient computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the method for automatically identifying patients in a multi-person scenario provided in the present application.

[0076] The memory 402 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the method for automatic patient identification in a multi-person scenario in the embodiment of the present application (for example, the attached Figure 3The processor 401 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 402, that is, the automatic patient recognition method in the multi-person scenario in the above method embodiment is implemented.

[0077] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of an electronic device of the patient automatic identification method in a multi-person scenario, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the electronic device of the patient automatic identification method in a multi-person scenario via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] The electronic device of the method for automatic patient identification in a multi-person scenario may further include: an input device 403 and an output device 404. The processor 401, the memory 402, the input device 403 and the output device 404 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0079] The input device 403 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device of the patient automatic identification method in a multi-person scenario, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 404 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0080] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0081] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0083] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0084] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0085] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0086] The units involved in the embodiments described in the present application may be implemented by software or hardware. The units described may also be arranged in a processor, for example, it may be described as: a processor includes a data acquisition module, a posture analysis module and a target recognition module. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the data acquisition module unit may also be described as an "image acquisition module".

[0087] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the device: presets the key posture of the target patient in the human posture analysis to lock the target patient, and performs human posture data analysis on the original image based on the imaging of the optical camera, thereby obtaining a set (quantity>1) of human posture data, and compares each set of human posture data with the preset key posture of the target patient, thereby realizing accurate identification and tracking of the target patient in a scene where multiple people are present.

[0088] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for automatic patient identification in a multi-person scenario, characterized in that: include: Collecting a multi-person scene picture including a target patient, wherein the body posture of the target patient is a key posture in the multi-person scene picture; Recognize the human body images in the multi-person scene picture, and perform human body posture analysis on each recognized human body image to obtain multiple groups of human body posture data; The multiple groups of human posture data are matched with the preset key postures of the target patient respectively, and the human body image corresponding to the successfully matched human posture data is determined to be the target patient; wherein the key posture of the target patient is the specified action posture data that distinguishes it from other people.

2. The method for automatic patient identification in a multi-person scenario according to claim 1, characterized in that: Recognizing a human body image in the multi-person scene image includes: The human body contour features in the multi-person scene picture are extracted, and the maximum image area enclosed by the human body contour features is used as the human body image.

3. The method for automatic patient identification in a multi-person scenario according to claim 1, characterized in that: Perform human posture analysis on each recognized human image to obtain multiple sets of human posture data, including: For each human body image, the posture features in the human body image are extracted, and all the posture features obtained constitute the human body posture data of the human body image to obtain multiple groups of human body posture data; the posture features include the position, angle and direction of the human body skeletal joints.

4. The method for automatic patient identification in a multi-person scenario according to claim 1, characterized in that: Determining the human body image corresponding to the successfully matched human body posture data as the target patient includes: Determining the number of human body images in the multi-person scene picture, and calculating the similarity between each group of human body posture data and the key posture; If the number of the human body images is 2, the human body image corresponding to the human body posture data whose similarity value is greater than the first set threshold is determined as the target patient; If the number of the human body images is greater than 2, selecting at least two sets of human body posture data whose similarity values ​​are greater than a second set threshold, matching the at least two sets of human body posture data with a preset standard posture of a target patient, and determining the human body image corresponding to the successfully matched human body posture data as the target patient; The standard posture of the target patient is a standard posture corresponding to any specified posture in the rehabilitation training item corresponding to the target patient; and the first set threshold is greater than the second set threshold.

5. The method for automatic patient identification in a multi-person scenario according to claim 1, characterized in that: The method further comprises: After the target patient is determined, the human body image of the target patient is placed in a preset target frame, and the human body image in the preset target frame is tracked and analyzed.

6. The method for automatic patient identification in a multi-person scenario according to claim 5, characterized in that: Placing the human body image of the target patient in a preset target frame includes: The target patient is guided to move through a set guiding method so that the human body image of the target patient is placed in the preset target frame.

7. The method for automatic patient identification in a multi-person scenario according to claim 5, characterized in that: Placing the human body image of the target patient in a preset target frame includes: According to the current position of the target patient in the multi-person scene picture, the image acquisition device is driven to adjust the field of view direction and the zoom ratio so that the position of the target patient in the multi-person scene picture is within the preset target frame.

8. A patient automatic identification device in a multi-person scenario, characterized in that: include: A data acquisition module, used for acquiring a multi-person scene picture including a target patient, wherein the body posture of the target patient is a key posture in the multi-person scene picture; A posture analysis module is used to identify human body images in the multi-person scene picture, and perform human body posture analysis on each identified human body image to obtain multiple groups of human body posture data; The target recognition module is used to match the multiple groups of human posture data with the preset key postures of the target patient respectively, and determine the human body image corresponding to the successfully matched human posture data as the target patient; wherein the key posture of the target patient is the specified action posture data that distinguishes it from other people.

9. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, 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 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images