Robot-based intelligent physical examination auxiliary method and system

Abstract

The present invention discloses a robot-based intelligent physical test auxiliary method and system, which belongs to the field of robot technology. The technical problem to be solved is how to reduce the error of the deployment site and the manual input, and improve the accuracy and efficiency of the test items. The physical test scene is photographed by a robot equipped with a motion system, a computing storage unit, a camera, and a camera height angle adjustment unit. Based on the test task, the robot performs the following operations: for the scene image at each shooting angle, the scene image is used as input and the scene image is subjected to target recognition through a preconfigured target recognition model. If the number of annotation points existing in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, and the camera shoots at the target camera angle.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a robot-based intelligent physical measurement assistance method and system. Background Art

[0002] Currently, the smart physical fitness test project for middle school students is developing rapidly. The smart physical fitness test project is a sports measurement and analysis system based on intelligent technology. It combines sensors, data analysis, cloud computing and other technologies to monitor and evaluate human movement status in real time.

[0003] The advantage of smart fitness testing is that it provides objective, accurate, and real-time data, helping athletes and coaches better understand their performance and physical condition. It can also help sports organizations and schools better manage and plan training programs, improve training effectiveness, and prevent sports injuries.

[0004] The general steps for setting up the physical test site are to confirm the location of the test site, set up the camera and adjust the height and angle, take screenshots with all cameras, and mark the points according to the serial number requirements (for example, in the long jump event, the first camera needs to mark the four points of the standing area and the two end points of the take-off line in the picture; the second camera needs to mark the four vertices of the long jump area), and save the pixel coordinates of the marked points in order.

[0005] To improve detection accuracy and uniform deployment, most manufacturers now specify the relative position and angle between the camera and the test site. However, in actual deployment, various errors are inevitable, resulting in increased detection errors.

[0006] How to reduce errors and manual effort in deployment sites and improve the accuracy and efficiency of test projects are technical issues that need to be addressed. Summary of the Invention

[0007] The technical task of the present invention is to address the above shortcomings and provide a robot-based intelligent physical measurement assistance method and system to solve the technical problem of how to reduce the error of deployment site and manual input, and improve the accuracy and efficiency of test items.

[0008] In a first aspect, the present invention provides a robot-based intelligent body measurement assistance method, wherein a body measurement scene is photographed by a robot equipped with a motion system, a computing and storage unit, a camera, and a camera height angle adjustment unit. The method comprises the following steps:

[0009] Configure the physical test project scene: For each test equipment in the physical test project scene, configure a marking pattern with a marking function on the test equipment, and use the center point of the marking pattern as the marking point. Preset the pixel position of the marking point in the image captured by the camera as the target pixel position;

[0010] Configure the test task: Assign each robot a serial number that serves as an identifier, specify the number of annotation points to be captured, and the target pixel position of each annotation point. Summarize the serial number, number of annotation points, and target pixel position of each robot to form a test task, and then send the test task to each robot.

[0011] Camera posture adjustment: For each robot, after receiving the test task, the robot performs the following based on the test task: Under the control of the camera height angle adjustment unit, adjust the shooting angle of the camera. At each shooting angle, the camera shoots the physical test scene to obtain a scene image. For each frame of the scene image at each shooting angle, the scene image is used as input and the pre-trained target recognition model is used to perform target recognition on the scene image to obtain each annotation point in the scene image and the pixel position of the annotation point in the current scene image. If the number of annotation points in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, the camera height angle adjustment unit stops regulating, and the camera shoots at the target camera angle;

[0012] Execute test tasks: Run the physical test project, and each camera shoots at the corresponding target camera angle.

[0013] Preferably, all robots under the same physical test item are connected to the same local area network.

[0014] Preferably, the robot is equipped with a laser radar system, which performs distance measurement and obstacle detection during the movement of the robot. When the robot moves to the target position, when the laser radar system detects an obstacle, an alarm message is generated and an alarm is sounded;

[0015] Based on the alarm information, the physical test project scene and test tasks are reconfigured, and based on the new test project scene and test tasks, the robot performs camera posture adjustment.

[0016] Preferably, when executing a test task, if the test equipment is offset, the physical test item scene and the test task are reconfigured, and the robot performs camera posture adjustment based on the new test item scene and the test task.

[0017] In a second aspect, the present invention provides a robot-based intelligent physical examination assistance system, comprising a management platform and a robot equipped with a motion system, a computing and storage unit, a camera, and a camera height angle adjustment unit. The management platform and the robot cooperate to execute the robot-based intelligent physical examination assistance method as described in any one of the first aspects.

[0018] The management platform is used to perform the following:

[0019] Configure the physical test project scene: For each test equipment in the physical test project scene, configure a marking pattern with a marking function on the test equipment, and use the center point of the marking pattern as the marking point. Preset the pixel position of the marking point in the image captured by the camera as the target pixel position;

[0020] Configure the test task: Assign each robot a serial number that serves as an identifier, specify the number of annotation points to be captured, and the target pixel position of each annotation point. Summarize the serial number, number of annotation points, and target pixel position of each robot to form a test task, and then send the test task to each robot.

[0021] Correspondingly, the robot is used to perform the following:

[0022] Camera posture adjustment: Camera posture adjustment: For each robot, after receiving the test task, the robot performs the following based on the test task: Under the control of the camera height angle adjustment unit, adjust the shooting angle of the camera. At each shooting angle, the camera shoots the physical test scene to obtain a scene image. For each frame of the scene image at each shooting angle, the scene image is used as input and the pre-trained target recognition model is used to perform target recognition on the scene image to obtain each annotation point in the scene image and the pixel position of the annotation point in the current scene image. If the number of annotation points in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, the camera height angle adjustment unit stops regulating, and the camera shoots at the target camera angle;

[0023] Execute test tasks: Run the physical test project, and each camera shoots at the corresponding target camera angle.

[0024] Preferably, all robots under the same physical test project are connected to the same local area network, and test tasks are uniformly issued through the management platform.

[0025] Preferably, the robot is equipped with a laser radar system, which performs distance measurement and obstacle detection during the movement of the robot. When the robot moves to the target position, when the laser radar system detects an obstacle, an alarm message is generated and an alarm is sounded;

[0026] Based on the alarm information, the management platform is used to reconfigure the physical measurement project scenes and test tasks. Based on the new measurement project scenes and test tasks, the robot is used to perform camera posture adjustment.

[0027] Preferably, when executing a test task, if the test equipment is offset, the management platform is used to reconfigure the physical test item scene and the test task, and the robot is used to perform camera posture adjustment based on the new test item scene and the test task.

[0028] The robot-based intelligent physical examination auxiliary method and system of the present invention have the following advantages:

[0029] 1. Eliminate the errors caused by artificial arrangement of the site, making the test results more accurate;

[0030] 2. Reduce labor input. Manual site layout requires at least two people, and more people are needed if time is tight. With the assistance of robots, only one staff member is needed to complete the task. Site layout and restoration are faster and more accurate.

[0031] 3. Thanks to the unification of the venue, there is no need to manually mark points (originally, after all cameras were placed, the test equipment's marking points in the screenshots needed to be manually marked according to the camera screenshots, and the marking points were sorted and saved), reducing the error of manual marking. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] The present invention will be further described below with reference to the accompanying drawings.

[0034] Figure 1 This is a flowchart of the robot-based intelligent physical examination assistance method in Example 1. DETAILED DESCRIPTION

[0035] The present invention will be further described below with reference to the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it. However, the embodiments given are not intended to limit the present invention. Unless there is a conflict, the embodiments of the present invention and the technical features in the embodiments may be combined with each other.

[0036] The embodiments of the present invention provide a robot-based intelligent physical examination auxiliary method and system for solving the technical problem of how to reduce errors in deployment sites and manual input, and improve the accuracy and efficiency of test items.

[0037] Example 1:

[0038] The present invention provides a robot-based intelligent physical examination auxiliary method, which shoots the physical examination scene through a robot equipped with a motion system, a computing and storage unit, a camera, and a camera height angle adjustment unit. The method includes four steps: configuring the physical examination item scene, configuring the test task, adjusting the camera posture, and executing the test task.

[0039] Step S100 configures the physical test project scene: for each test equipment in the physical test project scene, a marking pattern with an identification function is configured on the test equipment, and the center point of the marking pattern is used as the marking point, and the pixel position of the marking point in the image captured by the camera is preset as the target pixel position.

[0040] In this embodiment, all robots under the same test project are connected to the same local area network and run the scheduling service. The tablet runs the scheduling program to connect to each robot under the same test project, assign serial numbers to the robots, and select the test project.

[0041] The test equipment will be pre-affixed with marking patterns, and the robot will fine-tune the camera position based on the number of marking points for different items and the target pixel position of each marking point (which has been stored in the tablet's scheduling program in advance).

[0042] Step S200 configures the test task: assigns a serial number with an identification function to each robot, and specifies the number of annotation points that need to be photographed and the target pixel position of each annotation point for each robot. The serial number, number of annotation points and target pixel position of the annotation points of each robot are summarized to form a test task, and the test task is sent to each robot.

[0043] Step S300 camera posture adjustment: For each robot, after receiving the test task, the robot performs the following based on the test task: Under the control of the camera height angle adjustment unit, adjust the shooting angle of the camera. At each shooting angle, the camera shoots the physical test scene to obtain a scene image. For each frame of the scene image at each shooting angle, the scene image is used as input and the pre-trained target recognition model is used to perform target recognition on the scene image to obtain each annotation point in the scene image and the pixel position of the annotation point in the current scene image. If the number of annotation points in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, the camera height angle adjustment unit stops controlling, and the camera shoots at the target camera angle.

[0044] The target recognition model may use any existing network model or other model that can realize target recognition and position detection.

[0045] In this embodiment, test equipment is placed in a suitable place near the robot (such as a horizontal bar for pull-ups, a yoga mat for sit-ups), and the robot is given a site assignment on the tablet. The robot will automatically identify the test equipment through the camera based on the selected test item and its own serial number, and move to the relative position specified by this serial number (the relative position has been stored in advance in the scheduling program of the tablet).

[0046] Step S400 executes the test task: runs the physical test items, and each camera shoots at a corresponding target camera angle.

[0047] In this embodiment, the robot is equipped with a laser radar system, which performs distance measurement and obstacle detection during the movement of the robot. When the robot moves to the target position and detects an obstacle through the laser radar system, an alarm message is generated and an alarm is sounded.

[0048] Correspondingly, based on the alarm information, the physical test project scene and test tasks are reconfigured, and based on the new test project scene and test tasks, the robot performs camera posture adjustment.

[0049] As an improvement to this embodiment, when executing a test task, if the test equipment is offset, the physical test item scene and the test task are reconfigured, and based on the new test item scene and the test task, the robot performs camera posture adjustment.

[0050] The method of this embodiment relies on the assistance of a robot to achieve standardized testing scenarios, reducing errors caused by manual site layout and making testing more accurate and efficient. The robot's automatic site layout enables rapid switching between test items, enabling a single machine to serve multiple purposes. The robot identifies test equipment and quickly sets up the site, reducing manual effort. Fine-tuning the camera position based on marked points further ensures testing accuracy.

[0051] Example 2:

[0052] The present invention provides a robot-based intelligent physical examination auxiliary system, including a management platform and a robot. The robot is equipped with a motion system, a computing and storage unit, a camera, and a camera height angle adjustment unit. The management platform and the robot cooperate to execute the method disclosed in Example 1.

[0053] The management platform is used to perform the following:

[0054] (1) Configuring the physical test project scene: For each test equipment in the physical test project scene, configure a marking pattern with a marking function on the test equipment, and use the center point of the marking pattern as the marking point. Preset the pixel position of the marking point in the image captured by the camera as the target pixel position;

[0055] (2) Configure the test task: assign a serial number that serves as an identification to each robot, and specify the number of annotation points that each robot needs to capture and the target pixel position of each annotation point. Summarize the serial number, number of annotation points, and target pixel position of each robot to form a test task, and send the test task to each robot.

[0056] All robots in the same test project are connected to the same local area network and run the scheduling service. The scheduling program is run on a tablet to connect to each robot in the same test project, assign serial numbers to the robots, and select the test project.

[0057] The test equipment will be pre-affixed with marking patterns, and the robot will fine-tune the camera position based on the pixel positions of the marking points of different items (which have been stored in the tablet's scheduling program in advance).

[0058] Correspondingly, the robot is used to perform the following:

[0059] (1) Camera posture adjustment: For each robot, after receiving the test task, the robot performs the following based on the test task: Under the control of the camera height angle adjustment unit, adjust the shooting angle of the camera. At each shooting angle, the camera shoots the physical test scene to obtain a scene image. For each frame of the scene image at each shooting angle, the scene image is used as input and the pre-trained target recognition model is used to perform target recognition on the scene image to obtain each annotation point in the scene image and the pixel position of the annotation point in the current scene image. If the number of annotation points in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, the camera height angle adjustment unit stops regulating, and the camera shoots at the target camera angle;

[0060] (2) Execute the test task: run the physical test project, and each camera shoots at the corresponding target camera angle.

[0061] The target recognition model may use any existing network model or other model that can realize target recognition and position detection.

[0062] In this embodiment, test equipment is placed in a suitable place near the robot (such as a horizontal bar for pull-ups, a yoga mat for sit-ups), and the robot is given a site assignment on the tablet. The robot will automatically identify the test equipment through the camera based on the selected test item and its own serial number, and move to the relative position specified by this serial number (the relative position has been stored in advance in the scheduling program of the tablet).

[0063] In this embodiment, the robot is equipped with a laser radar system, which performs distance measurement and obstacle detection during the movement of the robot. When the robot moves to the target position and detects an obstacle through the laser radar system, an alarm message is generated and an alarm is sounded.

[0064] Correspondingly, based on the alarm information, the management platform reconfigures the physical test project scenarios and test tasks, and based on the new test project scenarios and test tasks, the robot is used to perform camera posture adjustment.

[0065] As an improvement to this embodiment, when executing a test task, if the test equipment is offset, the management platform is used to reconfigure the physical test item scene and the test task, and the robot is used to perform camera posture adjustment based on the new test item scene and the test task.

[0066] The present invention has been shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the means in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the scope of protection of the present invention.

Claims

1. A robot-based intelligent physical examination assistance method, characterized in that: The body measurement scene is photographed by a robot equipped with a motion system, a computing and storage unit, a camera, and a camera height angle adjustment unit, and the method comprises the following steps: Configure the physical test project scene: For each test equipment in the physical test project scene, configure a marking pattern with a marking function on the test equipment, and use the center point of the marking pattern as the marking point. Preset the pixel position of the marking point in the image captured by the camera as the target pixel position; Configure the test task: Assign each robot a serial number that serves as an identifier, specify the number of annotation points to be captured, and the target pixel position of each annotation point. Summarize the serial number, number of annotation points, and target pixel position of each robot to form a test task, and then send the test task to each robot. Camera posture adjustment: For each robot, after receiving the test task, the robot performs the following based on the test task: Under the control of the camera height angle adjustment unit, adjust the shooting angle of the camera. At each shooting angle, the camera shoots the physical test scene to obtain a scene image. For each frame of the scene image at each shooting angle, the scene image is used as input and the pre-trained target recognition model is used to perform target recognition on the scene image to obtain each annotation point in the scene image and the pixel position of the annotation point in the current scene image. If the number of annotation points in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, the camera height angle adjustment unit stops regulating, and the camera shoots at the target camera angle; Execute test tasks: Run the physical test project, and each camera shoots at the corresponding target camera angle.

2. The robot-based intelligent physical examination assistance method according to claim 1, characterized in that: All robots under the same physical test item are connected to the same local area network.

3. The robot-based intelligent physical examination assistance method according to claim 1, characterized in that: The robot is equipped with a laser radar system, which performs distance measurement and obstacle detection during the robot's movement. When the robot moves to the target position and detects an obstacle through the laser radar system, an alarm message is generated and an alarm is sounded; Based on the alarm information, the physical test project scene and test tasks are reconfigured, and based on the new test project scene and test tasks, the robot performs camera posture adjustment.

4. The robot-based intelligent physical examination assistance method according to claim 1, characterized in that: When performing a test task, if the test equipment is offset, the physical test item scene and test task are reconfigured, and the robot performs camera posture adjustment based on the new test item scene and test task.

5. A robot-based intelligent physical examination auxiliary system, characterized in that: The system includes a management platform and a robot equipped with a motion system, a computing and storage unit, a camera, and a camera height and angle adjustment unit. The management platform is used to perform the following: Configure the physical test project scene: For each test equipment in the physical test project scene, configure a marking pattern with a marking function on the test equipment, and use the center point of the marking pattern as the marking point. Preset the pixel position of the marking point in the image captured by the camera as the target pixel position; Configure the test task: Assign each robot a serial number that serves as an identifier, specify the number of annotation points to be captured, and the target pixel position of each annotation point. Summarize the serial number, number of annotation points, and target pixel position of each robot to form a test task, and then send the test task to each robot. Correspondingly, the robot is used to perform the following: Camera posture adjustment: For each robot, after receiving the test task, the robot performs the following based on the test task: Under the control of the camera height angle adjustment unit, adjust the shooting angle of the camera. At each shooting angle, the camera shoots the physical test scene to obtain a scene image. For each frame of the scene image at each shooting angle, the scene image is used as input and the pre-trained target recognition model is used to perform target recognition on the scene image to obtain each annotation point in the scene image and the pixel position of the annotation point in the current scene image. If the number of annotation points in the current scene image is consistent with the number of annotation points specified in the test task, and the pixel position of each annotation point in the current scene image is consistent with the target pixel point position specified in the test task, the current camera angle is the target camera angle, the camera height angle adjustment unit stops regulating, and the camera shoots at the target camera angle; Execute test tasks: Run the physical test project, and each camera shoots at the corresponding target camera angle.

6. The robot-based intelligent physical examination auxiliary system according to claim 5, characterized in that: All robots under the same physical test project are connected to the same local area network, and test tasks are uniformly issued through the management platform.

7. The robot-based intelligent physical examination auxiliary system according to claim 5, characterized in that: The robot is equipped with a laser radar system, which performs distance measurement and obstacle detection during the robot's movement. When the robot moves to the target position and detects an obstacle through the laser radar system, an alarm message is generated and an alarm is sounded; Based on the alarm information, the management platform is used to reconfigure the physical measurement project scenes and test tasks. Based on the new measurement project scenes and test tasks, the robot is used to perform camera posture adjustment.

8. The robot-based intelligent physical examination auxiliary system according to claim 5, characterized in that: When executing a test task, if the test equipment is offset, the management platform is used to reconfigure the physical test project scene and test task, and the robot is used to perform camera posture adjustment based on the new test project scene and test task.

Images