Vehicle door control method, device and equipment based on millimeter wave radar

Abstract

The invention relates to the technical field of electric vehicle intelligent control, and provides a vehicle door control method, device and equipment based on a millimeter wave radar, and the method comprises the steps: responding to a detection signal that a key enters an effective induction range, and triggering the millimeter wave radar to start; radar echo signals are received in real time, and pedestrian detection is carried out in a detection area defined in front of each vehicle door; if the pedestrian is detected in one or more detection areas, performing motion trail tracking on the pedestrian; the angle change between the motion trail and the vertical direction of the corresponding vehicle door and the change rate of the distance between the pedestrian and the vehicle door are obtained; and when the angle change and the distance change rate meet set conditions, the vehicle door is controlled to be opened. The problems that in the prior art, manual vehicle door operation is inconvenient, and the intelligent degree is low can be effectively solved.

Description

Technical Field

[0001] The present application relates to the field of automobile safety technology, and more specifically to a method, device, and apparatus for controlling a vehicle door based on millimeter-wave radar. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] While traditional methods of opening and closing car doors, including using physical keys and manually pulling the door, are widely accepted, they also have limitations. For example, manually opening the door can be inconvenient when carrying items. Alternatively, in inclement weather (such as rain or snow), when getting into the car is urgent, manual key or door opening can result in a poor user experience. To achieve automatic door opening without the need for keys or manual operation, a predefined action approach is currently used. This uses video or millimeter-wave radar to identify the user's movements in front of the vehicle, compares them to a library of standard actions, and uses this as a form of identity authentication for door opening control. Although millimeter-wave radar is unaffected by lighting conditions, the point cloud data it generates is highly sparse. This can lead to incomplete feature extraction, impacting the accuracy of action recognition and, consequently, the sensitivity of the response. Summary of the Invention

[0004] In view of this, the present invention provides a vehicle door control method, device and equipment based on millimeter-wave radar to achieve non-contact and non-sensing vehicle door opening.

[0005] A first aspect of the present invention provides a vehicle door control method based on millimeter-wave radar, comprising the following steps: In response to a detection signal indicating that the key has entered an effective sensing range, the millimeter-wave radar is triggered to start; Receive radar echo signals in real time and detect pedestrians within the detection area defined in front of each door; If a pedestrian is detected in one or more detection areas, the pedestrian's motion trajectory is tracked; the angle change between the motion trajectory and the vertical direction of the corresponding vehicle door, as well as the rate of change of the distance between the pedestrian and the vehicle door are obtained; When the angle change and the distance change rate meet the set conditions, the door is controlled to open.

[0006] In some embodiments, the set condition is: the angle between the motion trajectory and the vertical direction of the vehicle door continues to decrease, and the distance change rate is negative and within a set range.

[0007] In some embodiments, when tracking the motion trajectory of the pedestrian, a time window is set. If the angular change rate of the motion trajectory exceeds a set threshold within the time window, and the angle between the motion direction and the perpendicular direction of the vehicle door exceeds a set threshold, the pedestrian will no longer be tracked.

[0008] In some embodiments, the detection area is a rectangle, the width of the rectangle is set according to the width of an adult's body, and the length of the rectangle is set according to the adult's walking speed and the door opening.

[0009] In some embodiments, when tracking the motion trajectory of a pedestrian, the pedestrian's walking speed is also detected in real time. If the speed is lower than a set speed threshold, the time required for the pedestrian to reach the door movement space is predicted; based on this time and the time required for the door to open, the door opening time and opening speed are determined.

[0010] A second aspect of the present invention provides a vehicle door control method based on millimeter-wave radar, comprising the following steps: In response to a detection signal indicating that the key has entered an effective sensing range, the millimeter-wave radar is triggered to start; Receive radar echo signals in real time and detect pedestrians within the detection area defined in front of each door; If a pedestrian is detected in one or more detection areas, the specified motion parts are identified; The motion trajectory of the motion part is detected, and when the motion trajectory meets a preset condition, the corresponding vehicle door is controlled to open.

[0011] In some embodiments, an identification feature sequence of a prescribed action and preset conditions that need to be met are preset, wherein the identification feature sequence includes multiple consecutive positions that the action part needs to reach, and the conditions that need to be met include one or more of an action height condition, an action speed condition, an action time condition, and an action stability condition; when the detected action trajectory satisfies the set identification feature sequence and the preset conditions, the motion trajectory is determined to be valid, and the corresponding vehicle door is controlled to open.

[0012] A third aspect of the present invention provides a vehicle door control method based on millimeter-wave radar, characterized in that it includes the following steps: In response to a detection signal indicating that the key has entered an effective sensing range, the millimeter-wave radar is triggered to start; Receive radar echo signals in real time and detect pedestrians within the detection area defined in front of each door; If a pedestrian is detected in one or more detection areas, the pedestrian's motion trajectory is tracked; Obtain the angle change between the motion trajectory and the vertical direction of the corresponding door, as well as the rate of change of the distance between the pedestrian and the door; When the angle change and the distance change rate meet the set conditions, it is determined that the pedestrian has the intention to open the door; Identify the specified motion part of the pedestrian; detect the motion trajectory of the motion part, and when the motion trajectory meets the preset conditions, control the corresponding vehicle door to open.

[0013] A fourth aspect of the present invention provides a millimeter-wave radar-based door control device, comprising: a function trigger module, configured to trigger the millimeter-wave radar to start in response to a detection signal indicating that the key enters an effective sensing range; A pedestrian detection module is configured to receive radar echo signals in real time and detect pedestrians around the vehicle; a trajectory tracking module configured to track the pedestrian's movement trajectory when a pedestrian is detected, and if the pedestrian is approaching a vehicle, determine the vehicle door the pedestrian is heading towards and define a detection area in front of the vehicle door; The door control module is configured to continuously track the pedestrian's motion trajectory after detecting that the pedestrian has entered the detection area, obtain the angle change between the motion trajectory and the vertical direction of the door, and the rate of change of the distance between the pedestrian and the door. When the angle change and the rate of change of the distance meet the set conditions, the door is controlled to open.

[0014] A fifth aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the method described.

[0015] One or more of the above technical solutions use millimeter-wave radar for pedestrian detection and trajectory tracking. By identifying changes in the pedestrian's direction and speed by measuring the angle perpendicular to the vehicle door and the rate of change in distance from the vehicle door, they can reflect the pedestrian's intention to open the vehicle door, achieving contactless and sensorless door opening. Users only need to walk normally to the vehicle door to control the door opening. This avoids key operation, especially when holding objects or in harsh environments, greatly improving the user experience. Furthermore, the point cloud acquired in real time is relatively sparse, and the pedestrian's direction and speed changes can be calculated, improving the accuracy of control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0017] Figure 1 An example of an implementation environment of an embodiment of the present invention is shown; Figure 2A schematic diagram showing the arrangement of millimeter wave radars in an embodiment of the present invention is shown; Figure 3 A flow chart of a first millimeter-wave radar-based door control method provided by an embodiment of the present invention is shown; Figure 4 A schematic diagram of the detection area in the first door control method provided by an embodiment of the present invention is shown; Figure 5 A flow chart of a second millimeter-wave radar-based door control method provided in an embodiment of the present invention is shown; Figure 6 A schematic diagram showing a detection area in which a foot-stepping action is used as a prescribed action in a second vehicle door control method provided by an embodiment of the present invention; Figure 7 A schematic diagram showing a detection area in which a foot sweeping motion is used as a prescribed motion in a second vehicle door control method provided by an embodiment of the present invention; Figure 8 A schematic diagram of a detection area in which a foot-stepping action is used as a prescribed action in a third vehicle door control method provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0018] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0019] In the description of the embodiments of the present application, the term “including” and similar terms should be understood as open inclusion, that is, “including but not limited to.” The term “based on” should be understood as “at least partially based on.”

[0020] The "vehicle door" referred to in the embodiments of the present application may be a front hood, a tailgate, a rotating side door, a gull-wing door, a sliding door, etc., and is not specifically limited here.

[0021] Figure 1This section illustrates an example implementation environment for one or more embodiments of the present invention. This implementation environment includes a vehicle controller and a door control system connected to the vehicle controller. The door control system is connected to a millimeter-wave radar control module and a door actuator. When the vehicle network is in sleep mode, the millimeter-wave radar is disabled. When a valid smart car key or other authorized device enters the effective sensing range around the vehicle, the vehicle controller receives a valid signal from the key sensing module and sends a start command to the millimeter-wave radar module via the vehicle network. The millimeter-wave radar then enters operation and begins transmitting and receiving signals. The vehicle controller receives the radar echo signal in real time, analyzes the target's motion trajectory, speed, and direction within the detection area, and uses this information to determine whether to open the door. It then generates a door opening command, which is sent via the door control system to the door actuator. Upon receiving the command, the door actuator activates the motor, automatically opening the door. Simultaneously, the door control system sends signals to control modules such as speakers and lighting to trigger pre-set welcome options, such as playing soft music or illuminating the interior lights, creating a warm and comfortable atmosphere.

[0022] Figure 2 A schematic diagram illustrates the placement of millimeter-wave radars in one or more embodiments of the present invention. Millimeter-wave radars are located on the inside of the front bumper 101, the inside of the rear bumper 102, the inside of the front door interior panels or the front door sill 103 (symmetrically located on the left and right front), and the inside of the rear door interior panels or the rear door sill 104 (symmetrically located on the left and right rear). These radars are used to control the opening of the front hood, tailgate, front doors, and rear doors, respectively.

[0023] As described in the background technology, if the user is carrying items or is in a hurry to get on the car on rainy days, manually operating the key or door handle will bring a bad user experience. If a prescribed action is used for identity authentication, since the point cloud data generated by the millimeter-wave radar is highly sparse, the sparse point cloud data may lead to incomplete feature extraction, thereby affecting the accuracy of action recognition. In order to solve the above problems, the present invention performs identity authentication based on the motion trajectory. As long as the motion trajectory meets the set requirements, the door is controlled to open, wherein the motion trajectory can be a straight line approaching the door, or it can be a prescribed gesture or a prescribed foot movement. Judgment indicators are set for the motion trajectory, and the motion trajectory parameters required for these judgment indicators can also be accurately calculated based on the sparse point cloud, which solves the problem of insufficient accuracy caused by the sparsity of the point cloud. The above different motion trajectories are suitable for different scenarios: Scenario 1: The vehicle parking area is relatively open, and the driver or passengers do not need to detour to get on the vehicle, such as in the scenario of temporary parking to pick up people, taxi or ride-sharing pick-up, and business travel receptions. The vehicle is parked in spacious areas such as building entrances and factory entrances to facilitate passengers to get on the vehicle; Scenario 2: There are no restrictions on the vehicle parking area, and parking lots and underground garages are both acceptable, which is suitable for daily car use.

[0024] Figure [y1]3 shows a flow chart of a vehicle door control method based on millimeter-wave radar according to one or more embodiments of the present invention, applicable to scenario 1. The method is applied to a vehicle controller and includes the following steps: S101, in response to a detection signal indicating that the key has entered an effective sensing range, triggering the millimeter-wave radar to start; When a smart key or other authorized device enters the vehicle's effective sensing range (typically less than or equal to 5 meters), the vehicle controller sends a valid key sensing signal to the door control module. Upon receiving the valid signal from the key sensing module, the door control module sends a detection request signal to the millimeter-wave radar module, activating it to transmit millimeter-wave signals. This design ensures that the radar activates only when the user is about to approach the vehicle, reducing unnecessary energy consumption. Furthermore, the key sensing signal also provides identity verification, enhancing safety.

[0025] S102, receiving radar echo signals in real time and detecting pedestrians in the detection areas defined in front of each vehicle door; Once activated, the millimeter-wave radar module begins emitting high-frequency radio waves (millimeter waves). These beams reflect off obstacles, forming echo signals. The radar system processes these echo signals in real time, analyzing changes in frequency, phase, and amplitude to determine the presence and characteristics of objects within the designated detection area in front of the vehicle door. Millimeter-wave radar can identify the size and shape of target objects to a certain extent based on the intensity and distribution of reflected signals. The size and shape of other objects, such as electric vehicles and bicycles, differ significantly from those of pedestrians approaching the vehicle door. Pedestrian recognition is achieved by training radar data using machine learning or deep learning algorithms.

[0026] S103: If a pedestrian is detected in one or more detection areas, the movement trajectory of the pedestrian is tracked; When a pedestrian is detected within the detection area, the system uses advanced tracking algorithms (such as Kalman filtering) to continuously track the target's movement. By continuously tracking the pedestrian's trajectory, the system can more accurately determine their behavioral intentions, providing a basis for further operational decisions.

[0027] S104, obtaining the angle change between the motion trajectory and the vertical direction of the corresponding vehicle door, and the rate of change of the distance between the pedestrian and the vehicle door; The angular change in the pedestrian's trajectory relative to the vertical direction of the vehicle door, as well as the change in the distance between the pedestrian and the vehicle door per unit time, are two key parameters for determining whether the pedestrian is moving toward the vehicle door. For example, if the angle change approaches zero or decreases slightly, while the rate of change in distance remains negative (i.e., the pedestrian is gradually approaching the vehicle door), it indicates that the pedestrian is likely attempting to enter the vehicle. This refined analysis can effectively distinguish between a pedestrian's true intentions and accidental passing. In addition, the point cloud acquired in real time is relatively sparse, and the pedestrian's movement direction and speed changes can also be calculated, improving the accuracy of control.

[0028] S105: When the angle change and the distance change rate meet the set conditions, control the vehicle door to open.

[0029] Once the detected angle change and distance change rate meet pre-set conditions (e.g., the angle difference between the pedestrian's trajectory and the perpendicular direction of the door is less than a preset threshold, and the pedestrian's approach speed is within a certain range), the system will determine this is a valid door opening request. The door control module then receives the door opening signal from the millimeter-wave radar and automatically drives the motor or actuator to open the door. The system also considers the possibility of multiple people approaching simultaneously, prioritizing the authorized user closest to the door to prevent confusion and ensure safety.

[0030] This method uses millimeter-wave radar for pedestrian detection and trajectory tracking. By measuring changes in the angle perpendicular to the vehicle door and the rate of change in distance from the vehicle door, it identifies changes in the pedestrian's movement direction and speed, thereby indicating the pedestrian's intention to open the door. This enables contactless, sensorless door opening. Users simply walk up to the door to control its opening. This eliminates the need for key manipulation, especially when carrying objects or in harsh environments, significantly improving the user experience. Based on this method, any user can seamlessly enter the vehicle from any door as long as the key is nearby. Furthermore, compared to visual recognition solutions like cameras, millimeter-wave radar focuses more on detecting dynamic information about moving objects rather than static features. This means it doesn't capture personal information such as facial features, thus enabling intelligent door control while better protecting user privacy.

[0031] In step S103, in order to realize the opening of any door, a detection area is set for each door. The detection area can be defined as any shape as long as it is within the radar detection envelope. The detection area can be configured by software within the millimeter wave radar envelope range. In order to make the radar detection more effective, the center normal of the detection area width and the radar normal remain coincident.

[0032] However, the detection area should not be set too large. An overly large detection area could allow multiple moving objects to enter, such as two people entering the detection area simultaneously. This could affect motion tracking accuracy and increase the risk of false triggering. To improve the accuracy of non-sensing door opening, in some embodiments, the detection area is set as a rectangle, with the width of the rectangle set based on an adult's body width and the length based on the adult's walking speed and the door opening. By limiting the size of the detection area, the millimeter-wave radar can effectively detect a user approaching the door, improving recognition accuracy.

[0033] For example, Figure 4 As shown, a detection area 202 is set in front of radar 201. The detection area is a rectangle with a width of L1 and a length of L2, preferably L1 = 800mm and L2 = 2000mm. The 800mm width fully covers the width of an average adult body, while leaving some margin to accommodate differences in height and body shape, as well as the possibility of carrying items. This means that the system can effectively detect users approaching from the front or sideways, ensuring that the door opening action is not ineffective due to body deviation. The 2000mm length is based on an understanding of adult walking speed and the tendency to slow down when approaching a vehicle door. Under normal circumstances, people naturally slow down when approaching their destination. The average walking speed of an average adult is 4-6 km / h (1.11-1.67 m / s). When approaching a vehicle door, they slow down and move about 1 meter towards the door in approximately 1 second. Therefore, the system reserves sufficient "observation" distance (1000mm) and time (approximately 1 second) to fully recognize the user's approach before the door begins to open. This ensures that the door opens neither too late nor too early, enhancing overall fluidity. For the final 1000mm, the door opens synchronously, matching the user's movement. By the time the user reaches the door, the door's opening angle allows for easy entry, eliminating the need for extra waiting and providing a seamless boarding experience.

[0034] It's understood that while a rectangular detection area is described here, the shape and size can be flexibly adjusted to suit different vehicle models and usage scenarios. For example, a larger detection area may be required to cover more angles of approach paths for special designs like gull-wing or sliding doors, or a smaller detection area may be required to reduce false triggering in areas with limited space.

[0035] In step S103, the pedestrian's trajectory is tracked using a tracking algorithm such as a Kalman filter. By predicting the pedestrian's next position and updating it with newly detected data, the system ensures stable tracking of the pedestrian and avoids target loss and misjudgment. Trajectory prediction enables the prediction of the pedestrian's future trajectory. By analyzing the relationship between the trajectory and the vehicle door position, the system increases the confidence that the target is moving toward the vehicle door.

[0036] In step S104, the conditions that the angle change and the distance change rate must meet are: the angle between the motion trajectory and the vertical direction of the door continues to decrease, and the distance change rate is negative and within the set range. The angle change rate condition focuses on determining whether the user is adjusting the direction to face the door, while the distance change rate condition emphasizes that the user is approaching the door at an appropriate speed. Through the dual verification of directionality and speed, it can more accurately adapt to the user's actual behavior. Figure 4 As shown in the figure, assume that the system recognizes a moving target entering from side a and continuously tracks its position after entering. If the target approaches the door, moves at a decreasing speed, and does not touch the left or right side boundary (side b / d) within 500ms, it is considered a legal trigger and the door is controlled via CAN signals.

[0037] Monitoring the rate of change of angle helps determine whether the target user is adjusting their orientation toward the vehicle door. If the relative angle between the target object and the radar continues to decrease (i.e., the angle outward from the radar normal decreases), this indicates that the user is turning toward the vehicle door. Continuously monitoring the rate of change of angle reduces door opening errors caused by momentary angle misreadings. Furthermore, it can exclude objects that are moving but not toward the vehicle door, thereby reducing false triggering.

[0038] The distance change rate quantifies the speed at which the distance between the two vehicles changes. By setting a reasonable distance change rate threshold, the system can quickly identify that the target user is approaching the door at an appropriate speed. This means that once the user enters the detection range and begins to slow down, the system can react quickly and prepare to open the door. Combined with the aforementioned design of the detection area size, this improves the user experience of seamless door opening.

[0039] When a pedestrian crosses the road, his or her motion trajectory usually shows a change perpendicular to the direction of the car door or at a large angle. Based on this, by analyzing the angle change rate and speed direction change rate of the target object, if the angle change rate is large in a short period of time and the angle between the speed direction and the car door direction exceeds a certain threshold, it is judged as a pedestrian crossing the road. Specifically, when tracking the motion trajectory of the pedestrian, a time window is set. If the angle change rate of the motion trajectory exceeds the set threshold within the time window, and the angle between the motion direction and the perpendicular direction of the car door exceeds the set threshold, it will no longer be tracked. Technically, this embodiment effectively filters out those moving targets that do not have the intention to open the door by setting the time window and the angle change rate threshold, especially being able to distinguish between pedestrians crossing the road and other actions that are not intended to open the door.

[0040] To ensure that the door is already opened to the appropriate degree before the user arrives at the door, that is, the user's walking and door opening actions occur simultaneously without interference, the door opening timing and speed need to be determined based on the user's speed approaching the door. In some embodiments, the space and time required for the door to open to the set opening degree are determined, and recorded as the door movement space and opening time. When tracking the pedestrian's motion trajectory in step S103, the pedestrian's walking speed is also detected in real time. If the speed is below a set speed threshold, the time required for the pedestrian to reach the door movement space is predicted. It can be understood that this time is the time it takes for the vehicle to complete the opening action and open the door to the appropriate degree. Based on this time and the door opening time, the door opening time and speed are determined. In addition, during the control of the door opening, the pedestrian's speed is also monitored in real time. If the speed exceeds the set speed threshold, the door opening is not controlled.

[0041] The speed threshold is set because, under normal circumstances, even if a user approaches the door quickly in a hurry to board, they will inevitably slow down after entering the detection area before opening the door and boarding. Therefore, if the user's speed remains above the set threshold after entering the detection area, they are considered to have no intention of boarding. Furthermore, to ensure that the door is properly opened when the user arrives, the door opening speed should increase as the user approaches faster, based on the above method. For safety reasons, the door's related components and the surrounding environment should also be limited in speed.

[0042] Figure 5 The flowchart of a second millimeter-wave radar-based door control method provided by one or more embodiments of the present invention is shown. Different from the above embodiments, this method performs authentication based on motion trajectory and is applicable to scenario one or scenario two. The method is applied to a vehicle controller and specifically includes the following steps: S201: In response to a detection signal indicating that the key has entered an effective sensing range, triggering the millimeter-wave radar to start; This step describes the initial triggering conditions of the system, that is, when a legitimate key enters the preset effective sensing range around the vehicle, the millimeter-wave radar module is activated and begins to prepare for environmental monitoring.

[0043] S202: Receive radar echo signals in real time and detect pedestrians in the detection area defined in front of each door; After the radar is activated, it will continuously emit and receive electromagnetic waves, and by analyzing the echo signals, it can realize real-time monitoring and identification of pedestrians or other objects in the preset detection area.

[0044] S203: If a pedestrian is detected in one or more detection areas, identify the specified motion parts; Once a pedestrian is detected in the detection area, the target's motion trajectory is analyzed. The motion trajectory can be the motion trajectory of a specific part of the body, such as a gesture or foot movement.

[0045] S204: Detecting a motion trajectory of the motion part, and when the motion trajectory meets a preset condition, controlling the corresponding vehicle door to open.

[0046] In step S202, a detection area of ​​a set size is defined in front of each door. The size of the detection area is set according to the radar detection envelope range, as long as it can accurately identify the user's specified movement trajectory.

[0047] For example, the prescribed action is a stepping action, such as Figure 6 As shown, a detection area 302 is set in front of radar 301, with a width of L3 and a length of L4. The center normal of detection area 302 and the radar normal are aligned. It is recommended that L3 = L4 = 300mm. This area is large enough to cover the size of an adult male foot, which increases the overall detection success rate.

[0048] For example, the prescribed action is a sweeping action of the foot, such as Figure 7 As shown, a detection area 402 is set in front of the radar 401. The detection area 402 is divided into two rectangles. The width of the two rectangles is L5 and the length is L6. In order to make the radar detection have a better effect, the center normals of the two detection areas A and B and the radar normal are kept coincident.

[0049] In step S203, point cloud data is generated for the detected pedestrian, and the action part of the prescribed action is identified based on the point cloud data. For example, taking the foot as the action part, the specific method for identifying the action part of the prescribed action based on the point cloud data includes: (1) extracting pedestrian point cloud data at each moment from the continuous point cloud data, and removing ground points using a ground segmentation algorithm (such as plane fitting based on RANSAC); (2) converting the pedestrian point cloud data at each moment into a two-dimensional image; (3) preliminarily locating the position of the foot according to the position of the foot in the body part; (4) identifying the foot based on a pre-trained foot recognition model. The foot recognition model is obtained by training based on a convolutional neural network. The data set used for training includes an annotated data set, which includes feet wearing different types of shoes and feet in different orientations. The source of the data set can include an image converted from point cloud data, or an image containing the foot that has been grayscaled. More specifically, the confidence level of the foot recognition model's output is calculated, and foot targets at consecutive moments are captured based on continuous point cloud data. Based on the continuity of foot movements, the legitimacy of foot targets extracted at adjacent moments is assessed. This allows for the distinction between feet and similar objects (such as suitcases and animals).

[0050] In order to improve the accuracy of motion trajectory recognition, in step S204, the motion trajectory is detected according to the motion parts at consecutive moments. The identification feature sequence of the action and the preset conditions to be met are set. The identification feature sequence includes multiple consecutive positions that the motion parts need to reach. The conditions to be met include motion height conditions, motion speed conditions, motion time conditions and motion stability conditions, etc. When the motion height, motion speed and / or motion time all meet the set conditions, the motion trajectory is determined to be valid. Through conditional restrictions, the identification of the prescribed action can be improved and false triggering can be avoided. It can be understood that different prescribed actions have different identification feature sequences and condition settings. By comprehensively analyzing the target's motion height, speed and / or time, it can be more accurately judged whether the target has performed an effective door opening action.

[0051] For example, the prescribed action is a footstepping action, and the set identification feature sequence includes foot lift, footstepping, and foot lift again. The set conditions include the lift height and hovering time, as well as the footstepping dwell time. For example, the footstepping must last for at least 0.5 seconds and a total duration of 1-1.5 seconds. When foot targets detected from consecutive moments meet the above identification feature sequence, the complete "step down-dwell-lift" action trajectory is considered to be satisfied. Furthermore, when the action height, action time, and action stability all meet the set conditions, the action is considered valid.

[0052] For example, the prescribed action is a sweeping foot action, and the set identification feature sequence includes the foot moving to one side of the inspection area, the foot reaching the middle of the inspection area, the foot moving to the other side of the inspection area, the foot reaching the middle of the inspection area again, and the foot returning to the side of the starting action in the inspection area, for example, sweeping from point A area to point B area, and then sweeping from point B area to point A area (such as Figure 7 ). The set conditions include speed, rate of altitude change during the movement, and stability. For example, the movement speed must be 0.2-1.5 m / s, and the foot's trajectory must move from designated area A to B and then from B to A, with an azimuth change of >15°. Stability also requires maintaining a close distance change of <0.2 m for 5 consecutive frames of 0.5 seconds. If the foot target detected at consecutive moments meets the above sequence of identification features, the movement trajectory is considered to be satisfactory. Furthermore, if the speed, altitude change, and stability all meet the set conditions, the movement is considered valid.

[0053] Compared with the method of motion recognition using a standard motion library, the above method only needs to capture a few marker positions in the motion trajectory by setting a sequence of identification features to make motion standardization judgments. Therefore, there is no need to accurately identify the entire motion trajectory, which improves the sensitivity of detection.

[0054] It can be understood that the specific values ​​in the above conditions can be determined through calibration.

[0055] When multiple pedestrians are identified within the inspection area, priority is given to the target closest to the radar and the others are suppressed.

[0056] In special scenarios, there is a need to help others open the car door. For example, a passenger needs to get on the car from the back with items in hand, but it is inconvenient to open the door manually, or wants to open the tailgate, but the space in front of the tailgate is small and does not meet the distance for radar detection and recognition of foot movements. At this time, some embodiments set different actions for each door by establishing a complete set of standard action libraries, so as to identify user actions according to the specific requirements of different doors. Specifically, the standard action library includes the identification feature sequence corresponding to each door and the conditions that need to be met. The identified action trajectory is compared with multiple pre-stored identification feature sequences and the conditions that need to be met; if the comparison is successful, the corresponding door is controlled to open. Based on this, if you want to open the door for a passenger, the driver or other passengers can perform a specified action in front of the door on their side. In other embodiments, users can also customize the action trajectory to allow users to set the door opening action according to their personal habits, further improving the flexibility of the system and user satisfaction.

[0057] Figure 8 A flow chart of a third millimeter-wave radar-based door control method provided by one or more embodiments of the present invention is shown, which is applicable to scenario 1 or scenario 2. The method is applied to a vehicle controller and specifically includes: S301: In response to a detection signal indicating that the key has entered an effective sensing range, triggering the millimeter-wave radar to start; This step marks the start of system activity, that is, when a legitimate key enters the car's sensing area, the millimeter-wave radar is awakened and ready to start working.

[0058] S302: Receive radar echo signals in real time and detect pedestrians in the detection area defined in front of each door; After the radar is activated, it will continuously emit and receive electromagnetic waves, and by analyzing the echo signals, it can realize real-time monitoring and identification of pedestrians or other objects in the preset detection area.

[0059] S303: If a pedestrian is detected in one or more detection areas, the pedestrian's motion trajectory is tracked; Once a pedestrian is detected, the system will use tracking algorithms, such as Kalman filtering, to continuously monitor and record the pedestrian's movement trajectory to ensure that its movement path can be accurately tracked.

[0060] S304: Obtaining the angle change between the motion trajectory and the vertical direction of the corresponding door, and the rate of change of the distance between the pedestrian and the door; The angular change of the pedestrian's motion trajectory relative to the vertical direction of the vehicle door, as well as the change in the distance between the pedestrian and the vehicle door per unit time, are used to determine whether the pedestrian intends to get on the vehicle and to distinguish it from a situation where the pedestrian passes by accidentally.

[0061] S305: When the angle change and the distance change rate meet the set conditions, it is determined that the pedestrian has the intention to open the door; Based on the above analysis, if the angle continues to decrease (tending toward the door normal) and the rate of change of the distance is within the preset negative range, this indicates that the pedestrian is approaching the door quickly and directly, and the system infers that the pedestrian may intend to open the door.

[0062] S306: Identify the prescribed motion part of the pedestrian; the prescribed motion may be the hands or the feet.

[0063] S307: Detecting the motion trajectory of the motion part, and when the motion trajectory meets a preset condition, controlling the corresponding vehicle door to open.

[0064] The setting of preset conditions ensures that the car door will only open when the user performs the exact door opening action, which effectively prevents misoperation and accidental opening, especially when there are other moving objects around the vehicle. Through precise analysis of the motion trajectory, the system can accurately distinguish between user actions and unintentional interference, thereby enhancing the safety of the vehicle.

[0065] The above method first determines whether the pedestrian intends to get on the car based on the pedestrian's trajectory, and then performs authentication through prescribed actions, which further improves the accuracy of the judgment, can more accurately control the opening of the car door, avoid unnecessary misoperation, and solve the problem of illegal intrusion that may occur in public places.

[0066] The calculation and determination conditions of trajectory tracking, angle change and distance change rate in the above steps S303-S305 are the same as those in steps S103-S105. The process of motion trajectory detection and determination in steps S306-S307 is the same as that in steps S203-S204, and will not be repeated here.

[0067] Based on the above-mentioned first door control method, one or more embodiments of the present invention also provide a door control device based on millimeter-wave radar, including: a function trigger module, configured to trigger the millimeter-wave radar to start in response to a detection signal of a key entering an effective sensing range; a pedestrian detection module, configured to receive radar echo signals in real time and perform pedestrian detection around the vehicle; a trajectory tracking module, configured to track the pedestrian's motion trajectory when a pedestrian is detected, and if the pedestrian is approaching the vehicle, determine the door the pedestrian is heading towards and define a detection area in front of the door; a door control module, configured to continuously track the pedestrian's motion trajectory after detecting that a pedestrian has entered the detection area, obtain the angle change between the motion trajectory and the vertical direction of the door, and the rate of change of the distance between the pedestrian and the door, and control the door to open when the angle change and the rate of change of the distance meet the set conditions.

[0068] Based on the above-mentioned second door control method, one or more embodiments of the present invention also provide a door control device based on millimeter-wave radar, including: a function trigger module, configured to trigger the start of the millimeter-wave radar in response to the detection signal of the key entering the effective sensing range; a pedestrian detection module, configured to receive the radar echo signal in real time and perform pedestrian detection around the vehicle; a motion part recognition module, configured to identify the specified motion part when a pedestrian is detected in one or more detection areas; a door control module, configured to detect the motion trajectory of the motion part, and when the motion trajectory meets the preset conditions, control the corresponding door to open.

[0069] Based on the third vehicle door control method described above, one or more embodiments of the present invention further provide a vehicle door control device based on millimeter-wave radar, comprising: a function trigger module configured to trigger the activation of the millimeter-wave radar in response to a detection signal indicating that a key has entered an effective sensing range; a pedestrian detection module configured to receive radar echo signals in real time and detect pedestrians around the vehicle; a trajectory tracking module configured to track the motion trajectory of a pedestrian if a pedestrian is detected within one or more detection areas; a door opening intention control module configured to obtain the angular change between the motion trajectory and the vertical direction of the corresponding vehicle door, as well as the rate of change of the distance between the pedestrian and the vehicle door; when the angular change and the rate of change of the distance meet set conditions, determining that the pedestrian has the intention to open the door; a door opening control module configured to identify a specified motion part of the pedestrian; detect the motion trajectory of the motion part, and when the motion trajectory meets the preset conditions, control the corresponding vehicle door to open. One or more embodiments of the present invention further provide an electronic device that can be used to implement the vehicle door control method described in the above embodiments. The electronic device includes one or more processors, one or more memories coupled to the processors, and a communication module coupled to the processors.

[0070] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), or other magnetic and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM) or other volatile memories that do not persist during a power outage. A computer program may be stored in the ROM. When the processor executes the computer program, the above-described vehicle door control method is implemented.

[0071] In some embodiments, the program may be tangibly embodied in a computer-readable medium, which may be included in a device (such as a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable medium into RAM for execution. The computer-readable medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, or a hard disk. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the vehicle door control method described above.

[0072] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a server or terminal, the computer program instructions fully or partially generate the processes or functions described in the embodiments of the present application. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by the server or terminal, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, or magnetic tape), an optical medium (e.g., a digital video disk (DVD), etc.), or a semiconductor medium (e.g., a solid-state drive).

[0073] In addition, although adopting specific order to describe each operation, this should be understood as requiring such operation to be carried out with shown specific order or with sequential order, or requiring all illustrated operations to be carried out to obtain desired result.Under certain environment, multitasking and parallel processing may be advantageous.Similarly, although comprising some specific implementation details in the above discussion, these should not be interpreted as limiting the scope of the application.Some features described in the context of independent embodiment can also be implemented in a single implementation in combination.On the contrary, the various features described in the context of independent implementation also can be implemented in a plurality of implementations individually or in the mode of any suitable subcombination.

[0074] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A door control method based on millimeter wave radar, characterized in that: The following steps are involved: In response to a detection signal indicating that the key has entered an effective sensing range, the millimeter-wave radar is triggered to start; Receive radar echo signals in real time and detect pedestrians within the detection area defined in front of each door; If a pedestrian is detected in one or more detection areas, the pedestrian's motion trajectory is tracked; the angle change between the motion trajectory and the vertical direction of the corresponding vehicle door, as well as the rate of change of the distance between the pedestrian and the vehicle door are obtained; When the angle change and the distance change rate meet the set conditions, the door is controlled to open.

2. The vehicle door control method based on millimeter wave radar according to claim 1, characterized in that: The setting conditions are: the angle between the motion trajectory and the vertical direction of the door continues to decrease, and the distance change rate is negative and within a set range.

3. The vehicle door control method based on millimeter wave radar according to claim 1, characterized in that: When tracking the pedestrian's motion trajectory, a time window is set. If the angular change rate of the motion trajectory exceeds the set threshold within the time window, and the angle between the motion direction and the vertical direction of the car door exceeds the set threshold, the pedestrian will no longer be tracked.

4. The vehicle door control method based on millimeter wave radar according to claim 1, characterized in that: The detection area is rectangular, the width of the rectangle is set according to the width of an adult's body, and the length of the rectangle is set according to the adult's walking speed and the door opening.

5. The vehicle door control method based on millimeter wave radar as claimed in claim 4, characterized in that: When tracking the motion trajectory of a pedestrian, the pedestrian's walking speed is also detected in real time. If the speed is lower than the set speed threshold, the time required for the pedestrian to reach the door movement space is predicted; based on this time and the time required for the door to open, the door opening time and opening speed are determined.

6. A door control method based on millimeter wave radar, characterized in that: The following steps are involved: In response to a detection signal indicating that the key has entered an effective sensing range, the millimeter-wave radar is triggered to start; Receive radar echo signals in real time and detect pedestrians within the detection area defined in front of each door; If a pedestrian is detected in one or more detection areas, the specified motion parts are identified; The motion trajectory of the motion part is detected, and when the motion trajectory meets a preset condition, the corresponding vehicle door is controlled to open.

7. The vehicle door control method based on millimeter wave radar according to claim 6, characterized in that: An identification feature sequence of a prescribed action and preset conditions that need to be met are preset, wherein the identification feature sequence includes multiple consecutive positions that the action part needs to reach, and the conditions that need to be met include one or more of an action height condition, an action speed condition, an action time condition, and an action stability condition; when the detected action trajectory satisfies the set identification feature sequence and the preset conditions, the motion trajectory is determined to be valid, and the corresponding vehicle door is controlled to open.

8. A door control method based on millimeter wave radar, characterized in that: The following steps are involved: In response to a detection signal indicating that the key has entered an effective sensing range, the millimeter-wave radar is triggered to start; Receive radar echo signals in real time and detect pedestrians within the detection area defined in front of each door; If a pedestrian is detected in one or more detection areas, the pedestrian's motion trajectory is tracked; Obtain the angle change between the motion trajectory and the vertical direction of the corresponding door, as well as the rate of change of the distance between the pedestrian and the door; When the angle change and the distance change rate meet the set conditions, it is determined that the pedestrian has the intention to open the door; Identifying a prescribed motion part of the pedestrian; The motion trajectory of the motion part is detected, and when the motion trajectory meets a preset condition, the corresponding vehicle door is controlled to open.

9. A door control device based on millimeter wave radar, characterized in that: include: a function trigger module, configured to trigger the millimeter-wave radar to start in response to a detection signal indicating that the key enters an effective sensing range; A pedestrian detection module is configured to receive radar echo signals in real time and detect pedestrians around the vehicle; a trajectory tracking module configured to track the pedestrian's movement trajectory when a pedestrian is detected, and if the pedestrian is approaching a vehicle, determine the vehicle door the pedestrian is heading towards and define a detection area in front of the vehicle door; The door control module is configured to continuously track the pedestrian's motion trajectory after detecting that the pedestrian has entered the detection area, obtain the angle change between the motion trajectory and the vertical direction of the door, and the rate of change of the distance between the pedestrian and the door. When the angle change and the rate of change of the distance meet the set conditions, the door is controlled to open.

10. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein computer instructions are stored in the memory. When the computer instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 7.

Images