4d millimeter wave radar intelligent detection and control method for pedestrian and automatic door leaf

Abstract

The application discloses a 4D millimeter wave radar intelligent detection and control method for pedestrians and automatic door leaves, and comprises the following steps: starting a millimeter wave radar, completing relevant configuration initialization, and starting a Free RTOS real-time operating system to perform task scheduling; collecting 4D data through multiple door opening and closing operations; the 4D point cloud data comprises the distance, speed, azimuth angle and pitch angle of a moving object in the radar irradiation range; performing door leaf behavior feature recognition learning according to the collected data, and selecting a working mode suitable for the current environment; the millimeter wave radar receives point cloud data in real time, judges whether there is pedestrian movement in combination with the door leaf behavior features, and decides whether to perform a door opening and closing operation according to the judgment result. The application effectively reduces the system cost; the robustness is strong: in a traditional automatic door system, the interference of door leaf movement on detection needs to be avoided as much as possible, the application can accurately distinguish pedestrian movement from door leaf movement through feature learning and intelligent discrimination, and can effectively solve such problems.

Description

Technical Field

[0001] This invention belongs to the field of millimeter-wave radar technology, specifically a 4D millimeter-wave radar intelligent detection and control method for pedestrians and automatic door panels. Background Technology

[0002] Traditional infrared detection typically has a detection range of only a few meters, making it unsuitable for large-area scenarios. It cannot effectively distinguish between pedestrians, objects, and animals, potentially leading to false triggers and missed triggers. Strong light or other infrared sources can also affect its performance. Millimeter-wave radar technology samples high-frequency electromagnetic waves to detect and track objects within its radiation range. Millimeter-wave radar accurately provides information on the distance, speed, and trajectory of detected targets, is robust to lighting and weather conditions, and is suitable for complex environments and large-scale dynamic scenarios. Currently, there are detection systems on the market that combine infrared sensors with millimeter-wave radar. The far-field range is detected by a single millimeter-wave radar, while one or more infrared sensors detect the near-field area. This type of system is costly and has poor environmental adaptability. Millimeter-wave radar detects objects within its radiation range by scanning with a beam, accurately obtaining information such as the position, speed, and orientation of moving objects. However, if millimeter-wave radar is used to scan the near-field area, it is difficult to distinguish the movement of a door panel (the door panel's own movement easily triggers the automatic door sensor system to open the door). Therefore, millimeter-wave radar is generally used only to detect the far-field area. Summary of the Invention

[0003] This invention proposes a 4D millimeter-wave radar intelligent detection and control method for pedestrians and automatic door panels, aiming to improve the detection accuracy and control efficiency of automatic door systems and reduce overall costs.

[0004] The technical solution to achieve the purpose of this invention is: a 4D millimeter-wave radar intelligent detection and control method for pedestrians and automatic door panels, the specific steps of which are as follows:

[0005] Step 1: Start the millimeter-wave radar, complete the relevant configuration initialization, and start the Free RTOS real-time operating system for task scheduling;

[0006] Step 2: Collect 4D data through multiple door opening and closing operations; the 4D point cloud data includes the distance, speed, azimuth angle, and elevation angle of moving objects within the radar illumination range;

[0007] Step 3: Based on the collected data, perform door behavior feature recognition and learning, and select a working mode suitable for the current environment;

[0008] Step 4: The millimeter-wave radar receives point cloud data in real time, combines it with the door's behavioral characteristics to determine whether there is pedestrian movement, and decides whether to perform the door opening and closing operation accordingly.

[0009] Preferably, the working mode is determined by the learning results of door leaf behavior feature recognition. Door leaf behavior feature recognition specifically refers to different installation environments and different types of automatic doors, that is, different working modes correspond to different door leaf types' motion parameters and motion features.

[0010] Preferably, the specific steps for learning and recognizing door behavior features based on the collected data to select a suitable working mode for the current environment are as follows:

[0011] Step 3.1: Millimeter-wave radar enters feature recognition learning mode: When the environment tends to be steady, the door opening operation is performed and the automatic door status is marked as open. When the signal-to-noise ratio of the point cloud data is less than the environmental noise threshold, it is determined that the environment tends to be steady. In feature recognition learning mode, the door status flag is updated while performing each door opening and closing operation on the door leaf. The door status flag includes open and closed.

[0012] Step 3.2: Perform door opening and closing operations according to the door status flag. When the flag is open, perform the door closing operation, and when the flag is closed, perform the door opening operation. After each door opening and closing operation is completed, the counter is incremented by 1. At the same time, the collected data is processed to obtain the door leaf motion feature data.

[0013] Step 3.3: Repeat step 3.2 until the count reaches the set number of times. Then, calculate the weighted arithmetic average of the door movement characteristic data and compare it with the preset data to determine the door type.

[0014] Step 3.4: Determine the threshold size for behavioral feature data based on the learning data results and door type.

[0015] Preferably, the specific method for millimeter-wave radar to receive point cloud data in real time, combine it with door behavior characteristics, determine whether there is pedestrian movement, and decide whether to perform door opening / closing operations is as follows:

[0016] Step 4.1: After completing the radar working mode selection and control parameter confirmation, enable the millimeter-wave radar beam scanning function to acquire point cloud data in real time;

[0017] Step 4.2: Analyze the point cloud data to detect the presence of moving objects. If no moving objects are found, return to Step 4.1 and continue scanning. If moving objects are found, proceed to the next step.

[0018] Step 4.3: Calculate the object's position based on the 4D point cloud data and determine whether the moving object is in the far field region. If yes, proceed to step 4.6; otherwise, proceed to step 4.4.

[0019] Step 4.4: Analyze the point cloud data to see if the moving object is close to the automatic door. If the moving object has not entered the near field area, return to step 4.1. If it is in the near field area, proceed to step 4.5.

[0020] Step 4.5: Determine if the object's motion matches the door's behavior characteristics: Based on the object's trajectory, speed, and azimuth parameters, determine if the object's motion characteristics match the door's motion characteristics in the current mode. If not, return to step 4.1; if yes, proceed to step 4.7.

[0021] Step 4.6: Calculate the estimated time for the moving object to reach the door. If the time is less than a preset threshold, proceed to step 4.7; otherwise, return to step 4.1.

[0022] Step 4.7: The radar controls the automatic door servo motor to perform the door opening operation.

[0023] Preferably, the azimuth angle of the beam scanning area is -90° to 90°, and the elevation angle ranges from -60° to 60°.

[0024] Preferably, the estimated time for the moving object to reach the door is... Where y and v are the perpendicular distance and relative velocity between the moving object and the door, respectively, and T s To correct the time coefficient.

[0025] Compared with existing technologies, the significant advantages of this invention are: high detection accuracy: compared with traditional infrared detection systems, it significantly improves the accuracy and functionality of human body detection and has better environmental adaptability; lower cost: compared with detection systems combining infrared and millimeter-wave radar, this invention effectively reduces system costs; strong robustness: traditional automatic door systems need to avoid interference from door movement on detection as much as possible. This invention, through feature learning and intelligent discrimination, can accurately distinguish between pedestrians and door movement, effectively solving such problems.

[0026] The present invention will now be described in further detail with reference to the accompanying drawings. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the intelligent detection and control process of automatic doors based on 4D millimeter-wave radar provided by the present invention.

[0028] Figure 2 This is a flowchart illustrating the operation of a 4D millimeter-wave radar in acquisition mode.

[0029] Figure 3 This is a schematic diagram of the intelligent control workflow of 4D millimeter-wave radar.

[0030] Figure 4 This is a diagram showing people approaching in the far field.

[0031] Figure 5 This is a diagram showing people approaching the near-field area.

[0032] Figure 6This is a state machine diagram of an automatic door panel. Detailed Implementation

[0033] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0034] The present invention provides a 4D millimeter-wave radar intelligent detection and control system for pedestrians and automatic doors. First, it should be noted that the millimeter-wave radar used in this technical solution consists of a radar radio frequency front-end, a radar data processing board, a communication module, and a storage module. The collection and processing of radar data are integrated into one process, so that the data can be processed and analyzed immediately after the millimeter-wave radar has collected the data and then the automatic door can be controlled.

[0035] like Figure 1 As shown in the figure, the present invention discloses a 4D millimeter-wave radar intelligent detection and control method for pedestrians and automatic door panels, which specifically includes the following steps:

[0036] Step 1: Start the millimeter-wave radar, complete the relevant configuration initialization, and start the Free RTOS real-time operating system for task scheduling.

[0037] Specifically, Free RTOS is an open-source real-time operating system specifically designed for embedded systems. It boasts advantages such as small size and high efficiency, strong portability, multi-tasking support, a rich community ecosystem, and technical support.

[0038] Specifically, in this embodiment, data acquisition and processing are performed in two different tasks, which are uniformly scheduled using the task scheduler under FreeRTOS.

[0039] Step 2: Considering that the automatic door system may be applied in different environments (different door types, heights, opening and closing speeds, etc.), collect 4D data through multiple door opening and closing operations to provide a foundation for subsequent feature recognition.

[0040] Specifically, 4D point cloud data includes the distance, speed, azimuth, and pitch angles of moving objects within the radar illumination range.

[0041] Step 3: Based on the collected data, perform door behavior feature recognition and learning, and select a working mode suitable for the current environment.

[0042] Specifically, in this embodiment, the working mode is determined by the learning results of door behavior feature recognition. Door behavior feature recognition mainly applies to different installation environments and different types of automatic doors. That is, different working modes correspond to the motion parameters and motion characteristics of different door types (such as double doors or single doors, smooth doors or swing doors).

[0043] In a further embodiment, such as Figure 2 As shown, the specific steps for learning and recognizing door behavior features based on collected data to select a suitable working mode for the current environment are as follows:

[0044] Step 3.1: Millimeter-wave radar enters feature recognition learning mode: When the environment tends to be steady (clutter is filtered out by CFAR), the door opening operation is performed, and the automatic door status is marked as open.

[0045] Specifically, the radar system determines whether the environment is approaching a steady state by checking whether the signal-to-noise ratio of the point cloud data is greater than the environmental noise. When the signal-to-noise ratio of the point cloud data is less than the environmental noise threshold, it is approaching a steady state.

[0046] Specifically, in the feature recognition learning mode, the system updates the door status flag while performing each door opening and closing operation.

[0047] Step 3.2: After the environment stabilizes, perform door opening and closing operations according to the door status indicators. When the indicator is "Open," perform a closing operation; when the indicator is "Closed," perform a closing operation. After each door opening and closing operation, increment the counter by 1. Simultaneously, process the collected data to obtain door movement characteristic data, such as speed, acceleration, and start / stop delay.

[0048] Step 3.3: Repeat step 3.2 until the count reaches 5 times. Then, take the weighted arithmetic mean of these 5 sets of data and compare it with the preset data to determine the door type.

[0049] Furthermore, the door type can be customized using a DIP switch.

[0050] Step 3.4: Determine the threshold size of behavioral feature data based on the learning data results and door type, and initialize the door opening and closing control module.

[0051] Specifically, the behavioral feature data threshold is used for subsequent door leaf behavioral feature recognition. The door leaf movement is determined by comparing the data with the threshold.

[0052] Step 4: The millimeter-wave radar receives point cloud data in real time, combines it with the door's behavioral characteristics to determine whether there is pedestrian movement, and decides whether to perform the door opening and closing operation accordingly.

[0053] Furthermore, the system has a reserved debugging interface, and the host computer can control the system through the command line, including but not limited to data acquisition, adjustment of control parameters, and control of automatic door opening and closing.

[0054] Specifically, in this embodiment, command-line control and debugging operations are performed using the Free RTOS real-time operating system to ensure that the normal operation of the program is not affected.

[0055] In a further embodiment, such as Figure 3 As shown, the intelligent control workflow of millimeter-wave radar consists of the following steps:

[0056] Step 4.1: After completing the radar working mode selection and control parameter confirmation, enable the millimeter-wave radar beam scanning function to acquire point cloud data in real time;

[0057] Furthermore, the beam scanning area is selected in the radar configuration. In this embodiment, the azimuth angle of the scanning area is -90° to 90°, and the elevation angle range is -60° to 60°. The point cloud data includes information such as the distance, velocity, and angle of the object, which is processed internally by the radar and then transmitted to the main control system.

[0058] Step 4.2: Analyze the point cloud data to detect the presence of moving objects. If no moving objects are found, return to Step 4.1 and continue scanning. If moving objects are found, proceed to the next step to extract the motion information of the target object.

[0059] Furthermore, the acquisition and analysis of point cloud data are two distinct tasks of this real-time system.

[0060] Step 4.3: Calculate the object's position based on the 4D point cloud data and determine if the moving object is in the far field region. If yes, proceed to step 4.6; otherwise, proceed to step 4.4. A diagram illustrating the approach of a person in the far field region is shown below. Figure 4 As shown;

[0061] Step 4.4: Analyze point cloud data to determine if a moving object is approaching the automatic door. If the moving object has not entered the near-field area, return to step 4.1; if it is within the near-field area, proceed to step 4.5. A diagram illustrating the approach of a person in the near-field area is shown below. Figure 5 As shown;

[0062] Step 4.5: Determine if the object's motion matches the door's behavior characteristics: Based on the object's trajectory, speed, azimuth, and other parameters, determine if the object's motion characteristics match the door's motion characteristics under the current mode (determined by the previously learned mode). If they match, return to step 4.1; otherwise, proceed to step 4.7.

[0063] Specifically, door leaf behavior characteristics refer to door leaf width, acceleration magnitude, acceleration, start-stop delay, etc.

[0064] Step 4.6: Calculate the estimated time for the moving object to reach the door. If the time is less than a preset threshold, proceed to step 4.7; otherwise, return to step 4.1.

[0065] Specifically, the estimated time for a moving object to reach the door. Where y and v are the perpendicular distance and relative velocity between the moving object and the door, respectively, and T s To correct for the time coefficient, this value is determined by the radar's installation height and angle.

[0066] Step 4.7: The radar controls the automatic door servo motor to perform the door opening operation.

[0067] Furthermore, to prevent misjudgments and omissions, it is necessary to determine whether a closing operation should be performed based on the status of the automatic door, such as... Figure 6 As shown, the door state changes are represented by a state machine. Using the door state to determine whether to perform a closing operation can minimize the possibility of people getting caught in the door, and also improve the accuracy of door motion feature recognition.

[0068] In practical applications, this solution uses an antenna-in-package (AIP) radar sensor chip, and the radar acquisition and signal analysis processing run under the Free RTOS system. In actual operation, parameters can be adjusted by command line control or by toggling DIP switches.

[0069] This embodiment proposes a 4D millimeter-wave radar intelligent detection and control method for pedestrians and automatic door panels. The following describes the debugging and control system via a host computer:

[0070] The host computer communicates with the radar system using UART. After serial port initialization and Free RTOS task allocation are completed, the host computer can collect point cloud data, modify threshold parameters, monitor program operation, and control the system to output door opening and closing signals.

[0071] Specifically, different commands sent by the host computer indicate the use of different control functions, and the radar system will perform different operations accordingly. For ease of debugging, this embodiment uses the "help" command to introduce the specific command set and its corresponding functions.

[0072] This invention covers key aspects such as pedestrian estimated arrival time prediction, pedestrian location tracking, door behavior feature recognition, and pedestrian departure detection. By recognizing door behavior features, it effectively distinguishes between pedestrian and door behavior characteristics. A 4D millimeter-wave radar detects different areas through beam scanning and processes the acquired 4D point cloud data (distance, velocity, azimuth, and elevation). When a pedestrian is detected approaching in the far field, their 4D point cloud data is analyzed to predict their estimated arrival time. If the time is less than a set threshold, the automatic door is triggered to open. The pedestrian location tracking function is applicable to situations such as pedestrians crossing or lingering. For example, if a pedestrian merely passes in front of the door, the automatic door will not open; however, if a pedestrian lingers in front of the door (e.g., waiting or making a phone call), the door will not close. Furthermore, the pedestrian departure detection function makes the automatic door's closing operation more precise. This invention relies solely on data collected by 4D millimeter-wave radar, achieving precise control of the automatic door's opening and closing operations by distinguishing between pedestrian and door point cloud data. While its cost is significantly lower than other millimeter-wave radar automatic door products, its performance is also superior to traditional infrared control systems.

[0073] The above-described embodiments are merely preferred embodiments of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A 4D millimeter wave radar intelligent detection and control method for pedestrians and automatic door leaves, characterized in that, The specific steps are: Step 1: Start the 4D millimeter wave radar, complete the related configuration initialization, and start the Free RTOS real-time operating system for task scheduling; Step 2: Collect 4D point cloud data through multiple door opening and closing operations; the 4D point cloud data includes the distance, speed, azimuth angle and elevation angle of the moving object within the irradiation range of the 4D millimeter wave radar; Step 3: According to the collected 4D point cloud data, the door leaf behavior feature recognition learning is performed, and the working mode suitable for the current environment is selected, and the specific steps are: Step 3.1: The 4D millimeter wave radar enters the feature recognition learning mode: when the environment tends to be stable, the door opening operation is performed, and the automatic door state is marked as opening; when the signal-to-noise ratio of the 4D point cloud data is less than the environmental noise threshold, it is determined that the environment tends to be stable; in the feature recognition learning mode, the door state flag is updated every time the door opening and closing operation is performed on the door leaf, and the door state flag includes opening and closing; Step 3.2: According to the door state flag, the door opening and closing operation is performed, the flag is opened, the door closing operation is performed, the flag is closed, the door opening operation is performed, and after completing each door opening and closing operation, the counter is incremented by 1, and the collected 4D point cloud data is processed to obtain the door leaf motion feature data; Step 3.3: Repeat step 3.2 until the count value reaches the set number, and the door leaf motion feature data is weighted and arithmetically averaged and compared with the preset data to determine the door leaf type; Step 3.4: According to the learning data result and the door leaf type, the behavior feature data threshold size is determined; Step 4: The 4D millimeter wave radar receives the 4D point cloud data in real time, combines the door leaf behavior feature, judges whether there is a pedestrian motion, and decides whether to perform the door opening and closing operation according to the judgment result, and the specific method is: Step 4.1: After completing the radar working mode selection and control parameter confirmation, the 4D millimeter wave radar beam scanning function is enabled to obtain 4D point cloud data in real time; Step 4.2: Analyze the 4D point cloud data to detect whether there is a moving object, if not, return to step 4.1 and continue scanning, if yes, go to the next step; Step 4.3: Calculate the object position according to the 4D point cloud data, and judge whether the moving object is in the far field area, if yes, go to step 4.6, if not, go to step 4.4; Step 4.4: Analyze the 4D point cloud data to determine whether the moving object is close to the automatic door, if the moving object has not entered the near field area, return to step 4.1, if it is in the near field area, go to step 4.5; Step 4.5: Judge whether the object motion conforms to the door leaf behavior feature: combine the object's motion trajectory, speed, azimuth angle parameters to judge whether the motion feature of the moving object conforms to the door leaf motion feature in the current mode; If not, return to step 4.1, if yes, go to step 4.7; Step 4.6: Calculate the estimated arrival time of the moving object to the door leaf, if the time is less than the preset threshold, go to step 4.7, otherwise, return to step 4.1; Step 4.7: The 4D millimeter wave radar controls the automatic door servo motor to perform the door opening operation.

2. The 4D millimeter wave radar intelligent detection and control method for pedestrian and automatic door leaf according to claim 1, characterized in that, The working mode is determined by the learning result of the door leaf behavior feature recognition, and the door leaf behavior feature recognition is specifically: different installation environments and different automatic door leaf types, i.e., different working modes correspond to different motion parameters and motion characteristics of different door leaf types.

3. The 4D millimeter wave radar intelligent detection and control method for pedestrian and automatic door leaf according to claim 1, characterized in that, The beam scanning area azimuth angle is -90° to 90°, and the elevation angle range is -60° to 60°.

4. The 4D millimeter wave radar smart detection and control method for pedestrian and automatic door leaf according to claim 1, characterized in that, Time of arrival of moving object at door leaf is predicted where y and v are the perpendicular distance and relative speed of the moving object and the door leaf, respectively, T s is the correction time coefficient.

Images