Multi-behavior recognition method and device, robot and storage medium
By integrating cameras, temperature measuring heads and interactive modules on robots in high-risk areas of hospitals, efficient monitoring and identification of personnel behavior is achieved, tasks that are difficult to achieve in the prior art are solved, and safety and convenience are improved.
Patent Information
- Application Number
- CN202411955139.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-27
- Publication Date
- 2025-05-06
AI Technical Summary
In high-risk areas of hospitals, it is necessary to monitor and temperature measurement of personnel behavior to identify the standardization of wearing masks and putting on and taking off protective supplies. The existing technology is difficult to achieve these tasks efficiently, and there is a risk of cross-infection.
A multi-behavior recognition method is designed to collect images and temperature information through the camera and temperature measuring head on the robot, and combine the interactive module to perform task interaction and reminder, identify and record whether the behavior of the person is in compliance with the specifications.
It realizes the efficient and efficient execution of mask wearing recognition, protective equipment on-and-off recognition and multi-person temperature measurement, avoids cross-infection and improves the convenience of personnel safety and behavior recognition.
Smart Images
Figure CN119942610A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of robotics technology, and in particular to a multi-behavior recognition method, device, robot and storage medium. Background Art
[0002] In some scenarios in hospitals, it is necessary to monitor the behavior and temperature of personnel in high-risk areas, identify the standardization of mask wearing, and identify the standardization of wearing and removing of protective equipment for medical staff. These scenario application requirements are inconvenient for personnel to perform these tasks. In order to solve these problems and avoid cross infection, it is urgent to develop a multi-behavior recognition intelligent sensor control robot that meets the needs of these hospital scenarios. Summary of the invention
[0003] In view of this, an object of the embodiments of the present invention is to provide a multi-behavior recognition method, device, robot and storage medium, which can improve the convenience of multi-behavior recognition.
[0004] In one aspect, an embodiment of the present invention provides a multi-behavior recognition method, the method comprising the following steps: In response to the received task instructions, the robot is controlled to move to a specified position; wherein the task instructions include mask wearing recognition tasks, protective equipment wearing and removing recognition tasks, and temperature measurement and detection tasks; Based on the task instruction, the interaction module and the corresponding perception module are called, the task interaction is performed on the target person through the interaction module, the detection information of the target person is collected through the perception module, and the task identification is performed on the detection information; wherein the perception module includes a camera and a temperature measuring head arranged on the robot, and the detection information includes image information collected by the camera and temperature information collected by the temperature measuring head; When the result of the task identification does not meet the preset specification conditions, the interactive module is called to remind and record the detection information of the target person.
[0005] Optionally, calling an interaction module and a corresponding perception module based on the task instruction, performing task interaction on a target person through the interaction module, collecting detection information of the target person through the perception module, and performing task identification on the detection information includes: S210, determining whether the task instruction is a mask wearing recognition task, if so, calling the camera to collect face images to determine whether the target person is wearing a mask; if not, executing S220; S220, determining whether the task instruction is a protective equipment donning and doffing identification task, if so, calling the interaction module to interact with the target person in the donning and doffing task, calling the camera to collect human body images, and determining whether the target person puts on and takes off the protective equipment in a standard order; if not, executing S230; S230, determining whether the task instruction is a temperature measurement task, and if so, calling a camera to collect temperature to determine whether the temperature of the target person is within a preset temperature range.
[0006] Optionally, calling a camera to collect a facial image to determine whether the target person wears a mask includes: Call the camera to collect the face image of the target person; Performing data preprocessing on the face image to obtain a preprocessed image; the data preprocessing includes face detection, grayscale conversion, and size normalization; Performing feature extraction on the preprocessed image to obtain facial features; The facial features are input into a detection model to obtain a mask wearing recognition result, where the recognition result is whether a mask is worn or not.
[0007] Optionally, calling the interaction module to perform dressing and undressing task interaction on the target person, calling the camera to collect human body images, and determining whether the target person dresses and undresses in a standard order, includes: Calling the voice module in the interactive module to give voice prompts for the steps of putting on and taking off protective equipment in sequence; The camera is called to collect human body images, and the dressing and taking-off behaviors of the target person are detected based on the collected human body images; The standard behavior corresponding to the putting on and taking off steps is obtained, and within a set time period after the voice prompt, the putting on and taking off behavior of the target person is compared with the standard behavior corresponding to the putting on and taking off steps to obtain a determined putting on and taking off detection result; the putting on and taking off detection result is that the putting on and taking off is performed in a standard order or not in a standard order.
[0008] Optionally, the method further comprises: When it is determined that the donning and doffing detection result is that the donning and doffing is performed in accordance with the standard sequence, a human body image of the target person is photographed to obtain a recorded image of the target person after completing each donning and doffing step; Report the test results and recorded images of the target personnel after completing each donning and doffing step.
[0009] Optionally, when the result of the task identification does not meet the preset specification conditions, calling the interaction module to remind and record the detection information of the target person includes: Obtain a configuration mode for a mask wearing recognition task, wherein the configuration mode includes a reminder mode and a mandatory mode; When it is detected that a target person is not wearing a mask or is wearing it irregularly, if the configuration mode is the reminder mode, the target person is authenticated. After the identity authentication is passed, the voice module is called to remind the target person to wear a mask, and the face image of the target person is captured for reporting; If the configuration mode is the mandatory mode, the voice module is called to remind the user to wear a mask, and the face image of the target person is captured for reporting.
[0010] Optionally, when the result of the task identification does not meet the preset specification conditions, calling the interaction module to remind and record the detection information of the target person includes: If it is determined that the temperature of the target person exceeds the preset temperature range, the temperature and facial image of the target person are displayed on the display screen of the interactive module and reported.
[0011] On the other hand, an embodiment of the present invention provides a multi-behavior recognition device, characterized in that the device includes: The first module is used to control the robot to move to a specified position in response to a received task instruction; wherein the task instruction includes a mask wearing recognition task, a protective equipment putting on and taking off recognition task, and a temperature measurement detection task; The second module is used to call the interaction module and the corresponding perception module based on the task instruction, perform task interaction on the target person through the interaction module, collect detection information of the target person through the perception module, and perform task identification on the detection information; wherein the perception module includes a camera and a temperature measuring head arranged on the robot, and the detection information includes image information collected by the camera and temperature information collected by the temperature measuring head; The third module is used to call the interactive module to remind and record the detection information of the target person when the result of the task identification does not meet the preset standard conditions.
[0012] On the other hand, an embodiment of the present invention provides a robot, comprising: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0013] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to perform the above method.
[0014] The embodiment of the present invention has the following beneficial effects: In this embodiment, the interactive module and the perception module corresponding to each task instruction work together to ensure the efficient execution of multiple tasks such as mask wearing recognition, protective equipment wearing and removing recognition, and multi-person temperature measurement, and also avoid cross infection and ensure personnel safety. The present invention can improve the convenience of multi-behavior recognition. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0016] Figure 1 It is a schematic diagram of the steps of a multi-behavior recognition method provided by an embodiment of the present invention; Figure 2 is a structural block diagram of a multi-behavior recognition device provided by an embodiment of the present invention; Figure 3 It is a structural block diagram of a robot provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present invention. They are only examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the attached claims.
[0018] It is understood that the terms "first", "second", etc. used in the present invention may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0019] The terms "at least one", "multiple", "each", "any", etc. used in the present invention, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.
[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.
[0021] like Figure 1 As shown, an embodiment of the present invention provides a multi-behavior recognition method, the method comprising the following steps: S100, in response to the received task instructions, controlling the robot to move to a specified position; wherein the task instructions include a mask wearing recognition task, a protective equipment putting on and taking off recognition task, and a temperature measurement detection task; S200, calling an interaction module and a corresponding perception module based on the task instruction, performing task interaction on a target person through the interaction module, collecting detection information of the target person through the perception module, and performing task identification on the detection information; wherein the perception module includes a camera and a temperature measuring head arranged on the robot, and the detection information includes image information collected by the camera and temperature information collected by the temperature measuring head; S300, when the result of the task identification does not meet the preset standard conditions, calling the interactive module to remind and record the detection information of the target person.
[0022] In the embodiment provided by the present invention, the functions of the robot include mask wearing recognition, protective equipment wearing and removing recognition, and multi-person temperature measurement. The camera on the upper body head of the robot is used for face recognition and protective equipment wearing and removing recognition, and the temperature measuring head on the upper body head of the robot is used for temperature detection; It should be noted that for temperature measurement tasks: the robot moves to the designated location to conduct temperature measurement for multiple people as needed. If the temperature measurement fails, the on-site equipment will broadcast a prompt tone, and the face recognition camera will capture the picture and report it to the platform.
[0023] For the mask wearing recognition task: It supports mask wearing monitoring mode and provides voice notifications when a mask is not worn or is worn improperly, and takes pictures and reports to the platform.
[0024] The tasks of identifying the wearing and taking off of protective equipment include: Intelligently identify and assess the medical staff's putting on and taking off of protective equipment to ensure that they put on and take off according to the steps.
[0025] Carry out intelligent identification of masks, hats, protective clothing, face masks, gloves, shoe covers, etc., strictly control and implement them according to regulations, provide good protection and avoid infection.
[0026] Intelligently and strictly control the order of putting on and taking off, ensure standardized actions are performed according to prescribed steps, avoid infection, and intelligent voice interaction to facilitate personnel operation.
[0027] The present invention ensures efficient execution of multiple tasks such as mask wearing recognition, protective equipment wearing and removing recognition, and multi-person temperature measurement through the collaborative work of the interaction module and the perception module corresponding to each task instruction, and also avoids cross infection and ensures personnel safety. It can improve the convenience of multi-behavior recognition.
[0028] In some embodiments, in S200, the calling of the interaction module and the corresponding perception module based on the task instruction, performing task interaction on the target person through the interaction module, collecting detection information of the target person through the perception module, and performing task identification on the detection information include: S210, determining whether the task instruction is a mask wearing recognition task, if so, calling the camera to collect face images to determine whether the target person is wearing a mask; if not, executing S220; S220, determining whether the task instruction is a protective equipment donning and doffing identification task, if so, calling the interaction module to interact with the target person in the donning and doffing task, calling the camera to collect human body images, and determining whether the target person puts on and takes off the protective equipment in a standard order; if not, executing S230; S230, determining whether the task instruction is a temperature measurement task, and if so, calling a camera to collect temperature to determine whether the temperature of the target person is within a preset temperature range.
[0029] It should be noted that if the task instruction is not a mask wearing recognition task, a protective equipment putting on and taking off recognition task, or a temperature measurement and detection task, it will be reported as an unknown task.
[0030] In some embodiments, in S210, calling a camera to collect a facial image and determining whether the target person wears a mask includes: S211, calling a camera to acquire a facial image of a target person; S212, performing data preprocessing on the face image to obtain a preprocessed image; the data preprocessing includes face detection, grayscale conversion, and size normalization; S213, extracting features from the preprocessed image to obtain facial features; S214, input the facial features into a detection model to obtain a mask wearing recognition result, where the recognition result is whether a mask is worn or not.
[0031] Specifically, the process of mask recognition is as follows: Data collection: collect face images and perform face quality inspection to ensure that the collected face images meet various verification conditions (lighting, posture, illumination, blur, etc.), so as to obtain effective and analyzable faces for the device front end as input for detection. Data preprocessing: including face detection, grayscale conversion, size normalization, etc., to prepare for subsequent analysis.
[0032] Feature extraction: Extract facial features to determine whether a person is wearing a mask.
[0033] Detection model: The detection model uses the yolov5 deep learning algorithm training model to realize mask detection. Specifically, the detection model adopts a recognition method based on occluded face images. First, the occluded face images are transformed by wavelet, and then a feature rough set is established. The detail feature vectors are effectively connected according to the feature weighted fusion algorithm, and then identification is performed based on the connectivity. Actual test results show that this method can accurately detect whether a mask is worn.
[0034] Result output: The recognition results include not wearing a mask and wearing a mask.
[0035] In some embodiments, in S220, calling the interaction module to perform dressing and undressing task interaction on the target person, calling the camera to collect human body images, and determining whether the target person dresses and undresses in a standard order includes: S221, calling the voice module in the interactive module to give voice prompts for the steps of putting on and taking off the protective equipment in sequence; S222, calling a camera to collect human body images, and detecting the dressing and taking-off behavior of the target person based on the collected human body images; S223, obtaining the standard behavior corresponding to the putting on and taking off steps, and comparing the putting on and taking off behavior of the target person with the standard behavior corresponding to the putting on and taking off steps within a set time period after the voice prompt, to obtain a determined putting on and taking off detection result; the putting on and taking off detection result is putting on and taking off in accordance with the standard sequence or not putting on and taking off in accordance with the standard sequence.
[0036] In some embodiments, after S220, the method further includes: S224, when it is determined that the donning and doffing detection result is that the donning and doffing is performed in accordance with the standard sequence, photographing the human body image of the target person to obtain a recorded image of the target person after completing each donning and doffing step; S225, reporting the detection results and the recorded images of the target person after completing each putting on and taking off step.
[0037] Specifically, the testing process for putting on and taking off protective equipment is as follows: Protective equipment mainly includes masks, hats, protective clothing, face masks, gloves, shoe covers, etc. This process mainly uses intelligent identification of medical staff wearing protective equipment to ensure that medical staff wear protective equipment according to the steps, strictly control the implementation according to the regulations, do a good job of protection, avoid infection, and use intelligent voice interaction to facilitate personnel operation.
[0038] The main functions of this process are as follows: Voice prompts and guides the behavior of medical staff, and then detects the behavior of medical staff; For example, a voice prompt is given to wear a mask, and then the system detects whether this action is completed. If a mask is detected, the next step of detection is carried out; if no mask is detected within 1 minute, a voice prompt is given to wear a mask.
[0039] The order of wearing protective clothing for testing; The order of testing protective clothing is to test masks, hats, protective clothing, face shields, gloves, and shoe covers in turn. Take photos after completing each step of the test; The order of removing protective clothing for testing; The order of taking off protective clothing for testing is the opposite of the order of putting on protective clothing. The order of taking off protective clothing for testing is shoe covers, gloves, face masks, protective clothing, hats, and masks. After completing each step of the test, take photos for record.
[0040] After completing the test of the process of putting on protective equipment or the process of taking off protective equipment, the test results and the photos retained after each step of the test will be reported to the platform.
[0041] In some embodiments, in S300, when the result of the task identification does not meet the preset specification conditions, calling the interaction module to remind and record the detection information of the target person includes: Obtain a configuration mode for a mask wearing recognition task, wherein the configuration mode includes a reminder mode and a mandatory mode; When it is detected that a target person is not wearing a mask or is wearing it irregularly, if the configuration mode is the reminder mode, the target person is authenticated. After the identity authentication is passed, the voice module is called to remind the target person to wear a mask, and the face image of the target person is captured for reporting; If the configuration mode is the mandatory mode, the voice module is called to remind the user to wear a mask, and the face image of the target person is captured for reporting.
[0042] Specifically, the mask wearing recognition task supports the configuration of reminder mode and forced mode.
[0043] Reminder mode: When you are not wearing a mask, you need to do identity verification, and you will be reminded to wear a mask after passing the identity verification.
[0044] Forced mode: When you are not wearing a mask, identity authentication cannot be performed and you will be reminded to wear a mask.
[0045] Supports face recognition function when wearing a mask.
[0046] In some embodiments, in S300, when the result of the task identification does not meet the preset specification conditions, calling the interaction module to remind and record the detection information of the target person includes: If it is determined that the temperature of the target person exceeds the preset temperature range, the temperature and facial image of the target person are displayed on the display screen of the interactive module and reported.
[0047] In the embodiments provided by the present invention, the mask wearing recognition task and the protective equipment putting on and taking off recognition task performed by the sensor control robot are both implemented based on the deep learning algorithm, and the specific process is as follows: For mask wearing recognition: If the task is to identify the wearing of a mask, turn on the face recognition camera of the robot's upper body environment perception module to detect whether the person is wearing a mask. If the person is wearing a mask, this is normal and does not need to be reported to the platform. If it is detected that a person is not wearing a mask, the voice module in the interactive module will prompt the person to wear a mask, capture the picture and report it to the platform.
[0048] For identification of putting on and taking off protective equipment: There is a prescribed procedure for putting on and taking off protective clothing. The purpose of identifying the putting on and taking off of protective equipment is to ensure that medical staff put on and take off protective clothing in accordance with the regulations and in order. If they do not put on and take off protective clothing according to the regulations, a voice prompt will be given to put on and take off protective clothing according to the regulations.
[0049] For temperature measurement: If it is a temperature measurement task, turn on the temperature measuring head of the robot's upper body environmental perception module. If the temperature is detected to be higher than 37.3°, the actual temperature and the image of the corresponding person will be displayed on the display screen of the interactive module and reported to the platform.
[0050] See also Figure 2 , an embodiment of the present invention provides a multi-behavior recognition device, the device comprising: The first module is used to respond to the sampling instruction received by the interaction module, read the target point in the sampling instruction, and plan the optimal path from the current starting point of the robot to the target point; wherein the sampling instruction includes the target point and the sampling duration; The second module is used to control the motion module to autonomously move to the target point based on the optimal path, read the sampling duration in the sampling instruction, and control the multi-behavior identifier to perform sampling according to the set sampling duration.
[0051] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0052] refer to Figure 3 An embodiment of the present invention further provides a robot, the robot comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method in the above embodiment when executing the computer program.
[0053] It can be understood that the contents of the above method embodiments are all applicable to this embodiment, the functions specifically implemented by this embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0054] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above method is implemented.
[0055] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0056] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 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 may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.
[0057] The embodiments described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Those skilled in the art can appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.
[0058] Those skilled in the art will appreciate that the technical solutions shown in the figures do not limit the embodiments of the present invention and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0059] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0060] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0061] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0062] It should be understood that in the present invention, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0063] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0064] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0065] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0066] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store programs.
[0067] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the embodiments of the present invention is not limited thereby. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the embodiments of the present invention shall be within the scope of the rights of the embodiments of the present invention.
Claims
1. A multi-behavior recognition method, characterized in that: The method comprises the following steps: In response to the received task instructions, the robot is controlled to move to a specified position; wherein the task instructions include mask wearing recognition tasks, protective equipment wearing and removing recognition tasks, and temperature measurement and detection tasks; Based on the task instruction, the interaction module and the corresponding perception module are called, the task interaction is performed on the target person through the interaction module, the detection information of the target person is collected through the perception module, and the task identification is performed on the detection information; wherein the perception module includes a camera and a temperature measuring head arranged on the robot, and the detection information includes image information collected by the camera and temperature information collected by the temperature measuring head; When the result of the task identification does not meet the preset specification conditions, the interactive module is called to remind and record the detection information of the target person.
2. The method according to claim 1, characterized in that The step of calling an interaction module and a corresponding perception module based on the task instruction, performing task interaction on a target person through the interaction module, collecting detection information of the target person through the perception module, and performing task identification on the detection information includes: S210, determining whether the task instruction is a mask wearing recognition task, if so, calling the camera to collect face images to determine whether the target person is wearing a mask; if not, executing S220; S220, determining whether the task instruction is a protective equipment donning and doffing identification task, if so, calling the interaction module to interact with the target person in the donning and doffing task, calling the camera to collect human body images, and determining whether the target person puts on and takes off the protective equipment in a standard order; if not, executing S230; S230, determining whether the task instruction is a temperature measurement task, and if so, calling a camera to collect temperature to determine whether the temperature of the target person is within a preset temperature range.
3. The method according to claim 2, characterized in that The calling of the camera to collect facial images and determine whether the target person wears a mask includes: Call the camera to collect the face image of the target person; Performing data preprocessing on the face image to obtain a preprocessed image; the data preprocessing includes face detection, grayscale conversion, and size normalization; Performing feature extraction on the preprocessed image to obtain facial features; The facial features are input into a detection model to obtain a mask wearing recognition result, where the recognition result is whether a mask is worn or not.
4. The method according to claim 2, characterized in that: The calling of the interaction module to perform dressing and undressing task interaction on the target person, calling the camera to collect human body images, and determining whether the target person dresses and undresses in a standard order, includes: Calling the voice module in the interactive module to give voice prompts for the steps of putting on and taking off protective equipment in sequence; The camera is called to collect human body images, and the dressing and taking-off behaviors of the target person are detected based on the collected human body images; The standard behavior corresponding to the putting on and taking off steps is obtained, and within a set time period after the voice prompt, the putting on and taking off behavior of the target person is compared with the standard behavior corresponding to the putting on and taking off steps to obtain a determined putting on and taking off detection result; the putting on and taking off detection result is that the putting on and taking off is performed in a standard order or not in a standard order.
5. The method according to claim 4, characterized in that The method further comprises: When it is determined that the donning and doffing detection result is that the donning and doffing is performed in accordance with the standard sequence, a human body image of the target person is photographed to obtain a recorded image of the target person after completing each donning and doffing step; Report the test results and recorded images of the target personnel after completing each donning and doffing step.
6. The method according to claim 1, characterized in that When the result of the task identification does not meet the preset standard conditions, calling the interactive module to remind and record the detection information of the target person includes: Obtain a configuration mode for a mask wearing recognition task, wherein the configuration mode includes a reminder mode and a mandatory mode; When it is detected that a target person is not wearing a mask or is wearing it irregularly, if the configuration mode is the reminder mode, the target person is authenticated. After the identity authentication is passed, the voice module is called to remind the target person to wear a mask, and the face image of the target person is captured for reporting; If the configuration mode is the mandatory mode, the voice module is called to remind the user to wear a mask, and the face image of the target person is captured for reporting.
7. The method according to claim 2, characterized in that When the result of the task identification does not meet the preset standard conditions, calling the interactive module to remind and record the detection information of the target person includes: If it is determined that the temperature of the target person exceeds the preset temperature range, the temperature and facial image of the target person are displayed on the display screen of the interactive module and reported.
8. A multi-behavior recognition device, characterized in that: The device comprises: The first module is used to control the robot to move to a specified position in response to a received task instruction; wherein the task instruction includes a mask wearing recognition task, a protective equipment putting on and taking off recognition task, and a temperature measurement detection task; The second module is used to call the interaction module and the corresponding perception module based on the task instruction, perform task interaction on the target person through the interaction module, collect detection information of the target person through the perception module, and perform task identification on the detection information; wherein the perception module includes a camera and a temperature measuring head arranged on the robot, and the detection information includes image information collected by the camera and temperature information collected by the temperature measuring head; The third module is used to call the interactive module to remind and record the detection information of the target person when the result of the task identification does not meet the preset standard conditions.
9. A robot, characterized in that: The robot comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to perform the method according to any one of claims 1 to 7 when executed by the processor.