Channel gate control method and system

Abstract

The invention provides a channel gate control method and system, which is applied to the technical field of gate intelligent control, and is characterized in that radar data of a target vehicle and a front vehicle in a channel are acquired by using a radar sensor deployed at a gate opening, and the speed of the front vehicle is calculated from the radar data. And adaptively calculating a speed threshold and a distance threshold of the target vehicle by adopting a preset dynamic threshold adjustment strategy based on the speed of the front vehicle. The relative speed and the relative distance of the target vehicle relative to the front vehicle are calculated, the following judgment is carried out through the relative speed and the relative distance, and once the following behavior is judged, the system controls the gate machine to execute the corresponding action, such as delayed rod lifting or no rod lifting, so that the anti-following control is realized. According to the scheme, the radar sensor is adopted, the adverse effect of the light condition of the underground parking lot on a traditional photosensitive sensor can be effectively overcome, and the detection precision in a weak light or light change environment is improved.

Description

Technical Field

[0001] This application relates to the technical field of intelligent control of turnstiles, and particularly to a control method and system for channel turnstiles. Background Art

[0002] In order to achieve energy-saving operation, underground parking lots generally adopt a light-controlled lighting system. However, this energy-saving measure has also made the light environment in underground parking lots complex and unstable. Specifically, the lighting system in the underground parking lot frequently switches automatically, the overall light intensity is usually low, and there are easily areas with dim light and lighting dead spots. Traditional anti-tailgating technologies for channel turnstiles rely to a large extent on infrared or visible light sensors for vehicle detection and judgment of tailgating behavior.

[0003] However, these light-sensitive sensors are extremely vulnerable to environmental lighting conditions. In the complex environment of weak light and frequent light switching in underground parking lots, the detection accuracy of traditional sensors will decrease significantly, resulting in an increase in the misjudgment rate. For example, when the light suddenly dims, the infrared sensor may not be able to accurately identify the vehicle, which may cause misoperation or slow response of the turnstile, affecting not only the vehicle passing efficiency but also the reliability of the anti-tailgating function.

[0004] Therefore, in the harsh light conditions of the underground parking lot environment, how to effectively improve the accuracy and reliability of the anti-tailgating control of channel turnstiles while taking into account the demand for energy-saving operation has become an urgent technical problem to be solved.

[0005] In view of the above problems, the existing technology urgently needs to be improved. Summary of the Invention

[0006] In view of the deficiencies of the above-mentioned existing technology, this application provides a control method and system for channel turnstiles, which are applied to the technical field of intelligent control of turnstiles, and have the advantages of improving the accuracy and reliability of the anti-tailgating control of channel turnstiles in the harsh light environment of underground parking lots.

[0007] In a first aspect, a control method for a channel turnstile is applied to the turnstile entrance of an underground parking lot, and a radar sensor is deployed at the turnstile entrance. The method includes the steps of: S1: Obtain the radar data of the target vehicle and the vehicle in front in the channel, and calculate the speed of the vehicle in front according to the radar data; S2: Calculate the speed threshold and distance threshold of the target vehicle according to the speed of the vehicle in front and the preset dynamic threshold adjustment strategy; S3: Calculate the relative speed and relative distance of the target vehicle relative to the vehicle in front according to the radar data; S4: Compare the relative speed with the speed threshold, and compare the relative distance with the distance threshold. If the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is determined that a tailgating behavior has occurred. Otherwise, when the relative distance between the target vehicle and the vehicle ahead is less than the distance threshold, start timing. If the timing duration exceeds the preset time threshold, it is determined that a tailgating behavior has occurred; S5: If it is determined that a tailgating behavior has occurred, control the turnstile to perform corresponding actions.

[0008] A turnstile control method proposed in this application aims to solve the problem of determining tailgating behavior at the turnstile of an underground parking lot. First, in step S1, the radar data of the target vehicle and the vehicle ahead in the passage is obtained by using the radar sensor deployed at the turnstile, and the speed of the vehicle ahead is calculated from it. In step S2, based on the speed of the vehicle ahead, a preset dynamic threshold adjustment strategy is adopted to adaptively calculate the speed threshold and distance threshold of the target vehicle. This dynamic adjustment strategy enables the threshold to change according to the actual traffic conditions, improving the flexibility and accuracy of tailgating determination. In step S3, the radar data is used again to calculate the relative speed and relative distance of the target vehicle relative to the vehicle ahead. These relative quantities are the key parameters for judging tailgating behavior. In step S4, a tailgating determination is made. It sets two parallel determination conditions: First, if the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is immediately determined as tailgating. This situation usually corresponds to a fast tailgating closely following the vehicle ahead. Second, if the relative distance is less than the distance threshold, even if the relative speed does not meet the first condition, timing will be started. If the timing duration exceeds the preset time threshold, it is also determined as tailgating. This situation corresponds to a long-time tailgating slowly approaching the vehicle ahead. In step S5, once it is determined that a tailgating behavior has occurred, the system will control the turnstile to perform corresponding actions, such as delaying the raising of the rod or not raising the rod, so as to achieve anti-tailgating control. The entire solution uses a radar sensor to obtain vehicle movement data, and through dynamic thresholds and dual-condition determination, accurate and reliable tailgating behavior detection and turnstile control are achieved. By using a radar sensor, the adverse effects of the light conditions in the underground parking lot on traditional light-sensitive sensors can be effectively overcome, and the detection accuracy in low-light or light-changing environments can be improved. The dynamic threshold strategy and dual tailgating determination conditions enhance the system's ability to identify different types of tailgating behaviors and improve the intelligent level of anti-tailgating control.

[0009] Further, step S1 includes: S11: Periodically scan the target vehicle and the vehicle ahead in the passage at a preset sampling frequency to obtain the original radar data; S12: Perform denoising and smoothing preprocessing on the original radar data to obtain the radar data; S13: Track the vehicle ahead according to the radar data, establish a speed time series of the vehicle ahead, and calculate the speed of the vehicle ahead based on the speed time series.

[0010] A channel gate control method proposed in this application improves the accuracy and stability of calculating the speed of the vehicle ahead by effectively acquiring and preprocessing radar data and using tracking and time series analysis methods, providing more reliable speed parameters for subsequent following determination based on speed.

[0011] Further, step S13 includes: S131: Identify and associate multiple vehicles in the channel according to the radar data, assign a unique tracking ID to each vehicle, and record the position, speed, and angle information of each vehicle; S132: For the tracking ID of the vehicle ahead, predict the state of the vehicle ahead at the next moment using the position, speed, and angle information; S133: Establish a speed time series of the vehicle ahead according to the state of the vehicle ahead, where the speed time series records the speed values of the vehicle ahead at each moment within a preset time window; S134: Perform outlier detection on the speed time series, remove the outlier speed values in the speed time series that exceed the preset speed value range, and process the speed time series using median filtering to obtain the speed of the vehicle ahead.

[0012] A channel gate control method proposed in this application. In step S131, by identifying and associating multiple vehicles in the channel and assigning a unique tracking ID to each vehicle, effective management and differentiation of the vehicles in the channel are achieved, laying a foundation for subsequent tracking and speed calculation of the vehicle ahead. The position, speed, and angle information of the vehicle are recorded to provide data support for vehicle tracking and state prediction. In step S132, for the tracking ID of the vehicle ahead, the vehicle state at the next moment is predicted using the position, speed, and angle information of the vehicle. This prediction mechanism can improve the stability and continuity of vehicle tracking. Even when there is a short-term absence or interference in the radar data, effective tracking of the vehicle ahead can still be maintained. In step S133, based on the predicted state of the vehicle ahead, a speed time series of the vehicle ahead is established, and the speed values of the vehicle ahead at each moment within a preset time window are recorded, thereby forming a complete description of the speed change of the vehicle ahead and providing a data basis for subsequent speed calculation. In step S134, outlier detection is performed on the speed time series to remove significantly incorrect speed values, and median filtering is used to smooth the speed time series. Outlier detection can eliminate abnormal speed values caused by radar data noise or vehicle identification errors, and median filtering can further reduce the random fluctuations of speed data, improving the stability and accuracy of speed data. Through the above steps, this solution can calculate the speed of the vehicle ahead more accurately and reliably, thereby providing more accurate speed parameters for subsequent dynamic threshold adjustment and following determination, and improving the overall performance of the channel gate anti-following control system.

[0013] Further, step S2 includes: S21: Calculate an initial speed threshold and an initial distance threshold based on the speed of the vehicle ahead; S22: Collect ambient light intensity data in a preset area in front of the gate, and establish a first mapping relationship between the area position and the light intensity; S23: Determine the light intensity level of the area where the target vehicle is located according to the first mapping relationship, and select a corresponding dynamic threshold adjustment strategy according to the light intensity level; S24: Adjust the initial speed threshold and the initial distance threshold according to the selected dynamic threshold adjustment strategy to obtain the speed threshold and the distance threshold.

[0014] A channel gate control method proposed in this application realizes the environmental self-adaptability of the threshold dynamic adjustment strategy by integrating ambient light intensity information. This method makes the following determination no longer rely on a fixed threshold adjustment mode, but can be intelligently adjusted according to the actual light conditions, thereby improving the accuracy and reliability of following detection, reducing the false positive rate, and enhancing the overall performance of the gate control system in various light environments, especially in underground parking lots with complex or poor light conditions.

[0015] Further, step S21 includes: S211: The formula for calculating the initial speed threshold based on the speed of the vehicle ahead is: Initial speed threshold = speed threshold coefficient * speed of the vehicle ahead, where the speed threshold coefficient is 0.8; S212: The formula for calculating the initial distance threshold based on the speed of the vehicle ahead is: Initial distance threshold = distance threshold coefficient * speed of the vehicle ahead * safety time interval, where the distance threshold coefficient is 1.2 and the safety time interval is 2 seconds.

[0016] Further, step S23 includes: S231: Query the light intensity value corresponding to the position of the target vehicle according to the first mapping relationship; S232: Normalize the light intensity value to obtain a light intensity level, where the light intensity level includes three levels: strong light, medium light, and weak light; S233: Select the corresponding dynamic threshold adjustment strategy from a preset dynamic threshold adjustment strategy set according to the light intensity level. Among them, the dynamic threshold adjustment strategy set includes a strong light strategy, a medium light strategy, and a weak light strategy. The strong light strategy is to keep the initial speed threshold and the initial distance threshold unchanged. The medium light strategy is to reduce the initial speed threshold and the initial distance threshold by 10% respectively. The weak light strategy is to reduce the initial speed threshold and the initial distance threshold by 20% respectively.

[0017] Further, step S3 includes: S31: Obtain the first radar point cloud data of the target vehicle and the second radar point cloud data of the vehicle ahead in the radar data; S32: Extract the target vehicle contour information and the vehicle ahead contour information from the first radar point cloud data and the second radar point cloud data respectively; S33: According to the target vehicle contour information and the vehicle ahead contour information, use the least squares fitting to obtain the first driving trajectory line of the target vehicle and the second driving trajectory line of the vehicle ahead, and calculate the included angle between the first driving trajectory line and the second driving trajectory line; S34: When the included angle is less than or equal to a preset angle threshold, calculate the first speed vector of the target vehicle and the second speed vector of the vehicle ahead according to the radar data, decompose the first speed vector to obtain the first longitudinal speed, decompose the second speed vector to obtain the second longitudinal speed, and calculate the speed component difference between the first longitudinal speed and the second longitudinal speed to obtain the relative speed; S35: Calculate the longitudinal distance and the lateral distance between the target vehicle and the vehicle ahead based on the radar data, and calculate the relative distance between the target vehicle and the vehicle ahead based on the longitudinal distance and the lateral distance.

[0018] Further, step S35 includes: S351: Calculate the first centroid coordinate from the first radar point cloud data of the target vehicle and calculate the second centroid coordinate from the second radar point cloud data of the vehicle ahead based on the radar data; S352: Calculate the projection distance difference of the first centroid coordinate and the second centroid coordinate in the vehicle driving direction to obtain the longitudinal distance, and calculate the projection distance difference of the first centroid coordinate and the second centroid coordinate in the direction perpendicular to the vehicle driving direction to obtain the lateral distance; S353: Calculate the relative distance according to the formula: relative distance = sqrt(longitudinal distance^2 + lateral distance^2).

[0019] Further, step S5 includes: S51: If it is determined that a tailgating behavior occurs, obtain the current time and determine whether the current time is during the peak vehicle entry and exit period; S52: If the current time is during the peak vehicle entry and exit period, control the turnstile to raise the rod after a preset time delay; S53: If the current time is not during the peak vehicle entry and exit period, control the turnstile not to raise the rod and send a tailgating alarm to the management personnel.

[0020] In a second aspect, a turnstile control system is applied to the steps of any one of the above-mentioned turnstile control methods, and the system includes: Radar data acquisition module: used to acquire the radar data of the target vehicle and the vehicle ahead in the passage and calculate the speed of the vehicle ahead based on the radar data; Dynamic threshold calculation module: used to calculate the speed threshold and distance threshold of the target vehicle according to the speed of the vehicle ahead according to a preset dynamic threshold adjustment strategy; Data calculation module: used to calculate the relative speed and relative distance of the target vehicle relative to the vehicle ahead based on the radar data; Tailgating determination module: used to compare the relative speed with the speed threshold and compare the relative distance with the distance threshold. If the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is determined that a tailgating behavior occurs. Otherwise, when the relative distance between the target vehicle and the vehicle ahead is less than the distance threshold, start timing. If the timing duration exceeds a preset time threshold, it is determined that a tailgating behavior occurs; Turnstile control module: used to control the turnstile to perform corresponding actions if tailgating is determined to have occurred.

[0021] Beneficial effects: A channel turnstile control method and system proposed in this application utilize a radar sensor deployed at the turnstile entrance to obtain radar data of the target vehicle and the vehicle ahead in the channel, and calculate the speed of the vehicle ahead from it. Based on the speed of the vehicle ahead, a preset dynamic threshold adjustment strategy is adopted to adaptively calculate the speed threshold and distance threshold of the target vehicle. This dynamic adjustment strategy enables the threshold to change according to the actual traffic conditions, improving the flexibility and accuracy of tailgating determination. Again using the radar data, calculate the relative speed and relative distance of the target vehicle relative to the vehicle ahead, and perform tailgating determination through the relative speed and relative distance. It sets two parallel determination conditions: First, if the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is immediately determined as tailgating. This situation usually corresponds to fast tailgating closely following the vehicle ahead. Second, if the relative distance is less than the distance threshold, even if the relative speed does not meet the first condition, a timer will be started. If the timing duration exceeds the preset time threshold, it is also determined as tailgating. This situation corresponds to long-term tailgating slowly approaching the vehicle ahead. Once it is determined that tailgating has occurred, the system will control the turnstile to perform corresponding actions, such as delaying the raising of the rod or not raising the rod, thereby realizing anti-tailgating control. The entire solution utilizes a radar sensor to obtain vehicle movement data, and through dynamic thresholds and dual-condition determination, achieves accurate and reliable detection of tailgating behavior and turnstile control. By using a radar sensor, it can effectively overcome the adverse effects of the light conditions in the underground parking lot on traditional light-sensitive sensors and improve the detection accuracy in low-light or light-changing environments. The dynamic threshold strategy and dual tailgating determination conditions enhance the system's ability to identify different types of tailgating behaviors and improve the intelligent level of anti-tailgating control. Description of the Drawings

[0022] Figure 1 It is a flowchart of a channel turnstile control method proposed in this application.

[0023] Figure 2 It is a structural diagram of a channel turnstile control system proposed in this application.

[0024] Label description: 201, radar data acquisition module; 202, dynamic threshold calculation module; 203, data calculation module; 204, tailgating determination module; 205, turnstile control module. Detailed Implementation Manner

[0025] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and marked in the drawings here can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present application provided in the drawings below is not intended to limit the scope of the present application claimed, but only represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0026] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0027] In a dim underground parking lot environment with light-controlled lighting, when the existing access gate depends on a light-sensitive sensor for anti-tailgating detection, it faces the technical bottleneck that the detection accuracy is significantly reduced by the lighting conditions. Therefore, the present application proposes a method and system for controlling an access gate, which are specifically as follows: Please refer to Figure 1 , in a first aspect, a method for controlling an access gate, which is applied to the gate opening of an underground parking lot, and a radar sensor is deployed at the gate opening. The method includes the steps of: S1: Obtain the radar data of the target vehicle and the vehicle in front in the passage, and calculate the speed of the vehicle in front according to the radar data; S2: According to the speed of the vehicle in front, calculate the speed threshold and distance threshold of the target vehicle according to the preset dynamic threshold adjustment strategy; S3: Calculate the relative speed and relative distance of the target vehicle relative to the vehicle in front according to the radar data; S4: Compare the relative speed with the speed threshold, and compare the relative distance with the distance threshold. If the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is determined that a tailgating behavior has occurred. Otherwise, when the relative distance between the target vehicle and the vehicle in front is less than the distance threshold, start timing. If the timing duration exceeds the preset time threshold, it is determined that a tailgating behavior has occurred; S5: If it is determined that a tailgating behavior has occurred, control the access gate to perform corresponding actions.

[0028] Among them, in step S1, the radar sensor is deployed at the gate of the underground parking lot to scan the target vehicle and the vehicle in front in the passage, so as to obtain radar data. The radar data is then processed to calculate the speed of the vehicle in front. Among them, the target vehicle and the vehicle in front are adjacent vehicles front and back. Specifically, the target vehicle refers to the vehicle that needs to be detected and controlled currently, that is, the key object concerned by the system. It is the vehicle passing through the gate of the underground parking lot. The vehicle in front refers to the vehicle in front of the target vehicle, that is, the vehicle closest to the target vehicle when the target vehicle is driving in the passage.

[0029] The radar data is obtained by the radar sensor and at least includes: position information (i.e., the distances between the target vehicle, the vehicle in front and the radar sensor, and the angular positions of the target vehicle and the vehicle in front relative to the radar sensor), speed information (i.e., the speed magnitudes of the target vehicle and the vehicle in front, and the speed differences between the target vehicle and the vehicle in front relative to the vehicle in front), the reflection intensities of the radar signals on the target vehicle and the vehicle in front, the specific time when the radar data is collected, the unique tracking IDs assigned to the target vehicle and the vehicle in front, and the types of the target vehicle and the vehicle in front.

[0030] In step S2, the speed threshold and the distance threshold are calculated dynamically, and the calculation process is based on the speed of the vehicle in front and the preset dynamic threshold adjustment strategy. This dynamic adjustment strategy enables the thresholds to adapt to different traffic conditions.

[0031] In step S3, the relative speed and relative distance of the target vehicle relative to the vehicle in front are calculated based on the radar data, and these data provide a basis for the determination of the following behavior.

[0032] Step S4 performs the following determination. The determination logic includes two main conditions: First, when the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, the system immediately determines it as a following behavior. Second, even if the first condition is not met, as long as the relative distance is less than the distance threshold, the system starts timing. If the timing duration exceeds the preset time threshold, it is also determined as a following behavior.

[0033] In step S5, once it is determined that a following behavior occurs, the gate will perform corresponding control actions, such as delaying the raising of the rod or immediately raising the rod, so as to achieve anti-following control.

[0034] Specifically, the working principle of the access gate control method proposed in this application is as follows: First, the radar sensor accurately obtains the radar data of the target vehicle and the vehicle ahead in the access channel of the underground parking lot gate, overcoming the defect that the traditional photosensitive sensor is easily affected by the lighting conditions and ensuring the reliability of data acquisition. Based on the radar data, the system can calculate the speed of the vehicle ahead and, on this basis, flexibly set the speed threshold and distance threshold of the target vehicle through a dynamic threshold adjustment strategy. This dynamic threshold mechanism enables the trailing determination criterion to be adjusted according to the actual traffic situation, improving the accuracy and adaptability of the determination. Subsequently, the system uses the radar data again to calculate the relative speed and relative distance of the target vehicle relative to the vehicle ahead. These relative parameters directly reflect the following state between the two vehicles. The trailing determination step comprehensively considers the relative speed and relative distance and introduces a time threshold as an auxiliary determination condition, so as to effectively identify various types of trailing behaviors, including fast following and slow following. Finally, when the system determines that a trailing behavior has occurred, the gate control system will immediately respond and execute preset control actions, such as delaying the raising of the pole or prohibiting passage, so as to achieve the purpose of preventing vehicles from trailing through. Throughout the control process, the advantages of the radar sensor and the flexibility of the dynamic threshold strategy are utilized to improve the intelligent and reliable level of the anti-trailing control of the underground parking lot gate.

[0035] Further, step S1 includes: S11: Periodically scan the target vehicle in the channel at a preset sampling frequency to obtain the original radar data; S12: Perform denoising and smoothing preprocessing on the original radar data to obtain the radar data; S13: According to the radar data, track the vehicle ahead and establish a speed time series of the vehicle ahead. Based on the speed time series, calculate the speed of the vehicle ahead.

[0036] Among them, in step S11, the preset sampling frequency is set to ensure that the radar sensor can timely capture the dynamic information of the target vehicle and the vehicle ahead. For example, the sampling frequency can be set to 20Hz, that is, scan 20 times per second. Thus, continuous radar data of the target vehicle and the vehicle ahead can be obtained, providing a data basis for subsequent speed calculation.

[0037] In step S12, the original radar data may contain environmental noise and interference. To improve the data quality, it is necessary to preprocess the original radar data. The denoising process can use the median filtering method to effectively filter out the isolated noise points in the radar data. The smoothing preprocessing can use the moving average filtering method to reduce data fluctuations and obtain smooth radar data, improving the accuracy of subsequent speed calculation.

[0038] In step S13, the vehicle in front is tracked to ensure that the speed calculation is based on the vehicle in front, so as to avoid misjudging the speed of the target vehicle itself as the speed of the vehicle in front. The vehicle tracking can adopt the Kalman filter algorithm, which assigns a unique tracking ID to the vehicle in front based on the position, speed and angle information in the radar data, and predicts the motion state of the vehicle in front. The speed time series is established to record the speed value of the vehicle in front at each moment in a preset time window. For example, the time window can be set to 5 seconds to record the speed value of the vehicle in front in the past 5 seconds. By analyzing the speed time series, a more stable and reliable speed of the vehicle in front can be obtained.

[0039] In some specific embodiments, a radar sensor is installed at the entrance of a channel gate to scan vehicles entering the channel at a frequency of 20 Hz. The raw data obtained by the radar sensor is first denoised by a median filter to remove abnormal noise points. Then, a moving average filter with a window size of 3 is applied to smooth the data to reduce data fluctuations. In order to track the vehicle in front, a Kalman filter algorithm is used. The algorithm predicts and updates based on the vehicle's position and speed information, and assigns a unique ID to each tracked vehicle. For the vehicle in front, a speed time series with a length of 5 is established, and the speed values ​​within the most recent 5 sampling periods are recorded. In order to obtain the final speed of the vehicle in front, a median filter is applied to this speed time series to further eliminate instantaneous fluctuations in the speed data. In this way, an accurate and stable estimate of the speed of the vehicle in front can be obtained, providing reliable data support for subsequent determination of tailgating behavior.

[0040] Further, step S13 includes: S131: Based on the radar data, identify and associate multiple vehicles in the channel, assign a unique tracking ID to each vehicle, and record the position, speed, and angle information of each vehicle; S132: For the tracking ID of the front vehicle, use the position, speed and angle information to predict the state of the front vehicle at the next moment; S133: establishing a speed time series of the front vehicle according to the state of the front vehicle, the speed time series recording the speed value of the front vehicle at each moment within a preset time window; S134: performing outlier detection on the speed time series, eliminating outlier speed values ​​in the speed time series whose speed values ​​exceed a preset speed value range, and processing the speed time series using a median filter to obtain the speed of the vehicle ahead.

[0041] Among them, in step S131, vehicle recognition and association are achieved by analyzing radar point cloud data. The radar sensor scans the channel area to obtain point cloud data containing multiple target reflections. Through a clustering algorithm, such as the DBSCAN algorithm, the point cloud data is divided into multiple clusters, and each cluster is considered to correspond to a vehicle. To achieve vehicle association, a tracking ID mechanism is introduced, and newly entering vehicles in the channel are assigned new tracking IDs. In subsequent frames, by comparing the position, speed, and angle information of the vehicles, using, for example, the Kalman filtering algorithm, the vehicle clusters in the current frame are matched with the vehicles in the previous frame to maintain the continuity of the tracking IDs, thereby achieving effective tracking and differentiation of multiple vehicles in the channel.

[0042] In step S132, vehicle state prediction is achieved based on a vehicle motion model. The vehicle motion model can adopt a uniform motion model. The specific implementation process is as follows: Assume that the vehicle in front maintains a uniform linear motion in a short period of time. Using the position, speed, and angle information of the vehicle in front at the current moment, the state of the vehicle in front can be described by the position , speed , and angle . The prediction formula of the uniform motion model is: Position prediction: ; Speed prediction: ; Angle prediction: . Among them, represents the position coordinates of the vehicle in front on the two-dimensional plane, is the position of the vehicle in front in the horizontal direction (pointing east), the position of the vehicle in front in the vertical direction (pointing north). and represent the velocity components of the vehicle in front in the and directions; is the time interval between the current moment and the next moment; represents the position of the vehicle in front in the horizontal direction at the next moment, represents the position of the vehicle in front in the vertical direction at the next moment, and represent the velocity components of the vehicle in front in the and directions at the next moment.

[0043] By predicting the state of the vehicle in front, the influence of radar data noise and occlusion on vehicle tracking is reduced, and the robustness of tracking is improved.

[0044] In step S133, the speed time series is established to record the change of the speed of the vehicle ahead over time. The preset time window is set to 5 seconds, for example. The speed time series records the speed values of the vehicle ahead at certain time intervals within the past 5 seconds. The time interval is related to the radar data sampling frequency. For example, if the sampling frequency is 10 Hz, the time interval is 0.1 second. The speed time series provides a data basis for subsequent speed calculation and filtering processing.

[0045] In step S134, outlier detection and median filtering are used to improve the accuracy and stability of the speed calculation of the vehicle ahead. Outlier detection is achieved by setting a speed threshold range. For example, speed values exceeding ±30 m / s are considered outliers and removed. Median filtering is a non-linear filtering method that sorts the speed values in the speed time series and takes the middle value as the filtering result, effectively eliminating the influence of impulse noise and outliers on the speed data.

[0046] In some specific embodiments, the sampling frequency of the radar sensor is set to 10 Hz, the preset time window is set to 5 seconds, and the speed time series records the speed values of the vehicle ahead every 0.1 second within the past 5 seconds. The speed threshold range for outlier detection is set to ±30 m / s. The window size of the median filtering is set to 3, that is, the middle value of every 3 consecutive speed values in the speed time series is taken as the filtering result each time. The vehicle tracking algorithm uses Kalman filtering, and the motion model is a uniform motion model. Through these parameter settings, it can be ensured that the system can still accurately identify and track the vehicle ahead, obtain a reliable speed of the vehicle ahead, and achieve accurate following determination and gate control in the environment of weak light and frequent light switching in the underground parking lot.

[0047] Further, step S2 includes: S21: Calculate the initial speed threshold and the initial distance threshold according to the speed of the vehicle ahead; S22: Collect the ambient light intensity data in the preset area in front of the gate, and establish the first mapping relationship between the area position and the light intensity; S23: Determine the light intensity level of the area where the target vehicle is located according to the first mapping relationship, and select the corresponding dynamic threshold adjustment strategy according to the light intensity level; S24: Adjust the initial speed threshold and the initial distance threshold according to the selected dynamic threshold adjustment strategy to obtain the speed threshold and the distance threshold.

[0048] Among them, since in the underground parking lot environment, the light intensity changes greatly, which is likely to affect the driver's judgment and cause rear-end accidents. To solve this problem, the dynamic threshold adjustment strategy can be determined by the light intensity, so as to adjust the following determination and control the gate to perform corresponding actions, and more reliable anti-following control can be achieved.

[0049] Among them, in step S21, the initial speed threshold and the initial distance threshold are calculated based on the speed of the vehicle ahead. Specifically, the initial speed threshold can be set as a fixed ratio of the speed of the vehicle ahead. For example, it is obtained by multiplying the speed threshold coefficient 0.8. The initial distance threshold can be calculated based on the speed of the vehicle ahead and the safety time interval. For example, it is obtained by multiplying the distance threshold coefficient 1.2, the safety time interval of 2 seconds, and the speed of the vehicle ahead.

[0050] In step S22, in order to obtain the ambient light information, light intensity sensors can be deployed in a preset area in front of the turnstile. These sensors periodically collect light intensity data and record the collection locations. By analyzing the collected data, a first mapping relationship is established, which reflects the corresponding relationship between different area positions in front of the turnstile and the light intensity.

[0051] Specifically, the first mapping relationship includes a data structure table composed of area positions and light intensities. For example: Area position 1 -> Light intensity 1 Area position 2 -> Light intensity 2 ... Area position N -> Light intensity N N small areas are divided within the preset area in front of the turnstile. Each area has a unique position identifier, and the light intensity value corresponding to each area position is usually expressed in terms of the luminous flux per unit area (such as lux, lx).

[0052] In step S23, according to the first mapping relationship established in step S22, the light intensity level of the area where the target vehicle is located can be determined. The light intensity level can be divided into multiple levels, such as three levels: strong light, medium light, and weak light. Each light intensity level corresponds to a dynamic threshold adjustment strategy. For example, the strong light level can correspond to the strategy of keeping the initial threshold unchanged, the medium light level can correspond to the strategy of reducing the initial threshold by 10%, and the weak light level can correspond to the strategy of reducing the initial threshold by 20%.

[0053] In step S24, according to the dynamic threshold adjustment strategy selected in step S23, the initial speed threshold and the initial distance threshold are further adjusted, and the finally obtained speed threshold and distance threshold will be used for the determination of subsequent following behaviors.

[0054] This application is beneficial to controlling the target vehicle and the vehicle ahead to maintain a greater safety distance and a lower safety speed by reducing the initial speed threshold and the initial distance threshold in medium light and weak light, preventing the target vehicle from accelerating and colliding with the vehicle ahead after quickly passing through the turnstile.

[0055] Furthermore, step S21 includes: S211: The formula for calculating the initial speed threshold based on the speed of the vehicle ahead is as follows: Initial speed threshold = speed threshold coefficient * speed of the vehicle ahead, where the speed threshold coefficient is 0.8; S212: The formula for calculating the initial distance threshold based on the speed of the vehicle ahead is as follows: Initial distance threshold = distance threshold coefficient * speed of the vehicle ahead * safety time interval, where the distance threshold coefficient is 1.2 and the safety time interval is 2 seconds.

[0056] Among them, in step S211, the initial speed threshold is calculated by multiplying the speed threshold coefficient by the speed of the vehicle ahead. The speed threshold coefficient is set to 0.8, which means the initial speed threshold is set to 80% of the speed of the vehicle ahead. This setting ensures a certain proportional relationship between the initial speed threshold and the speed of the vehicle ahead.

[0057] In step S212, the initial distance threshold is calculated by multiplying the distance threshold coefficient, the speed of the vehicle ahead, and the safety time interval. The distance threshold coefficient is set to 1.2 and the safety time interval is set to 2 seconds. The calculation of the initial distance threshold comprehensively considers the speed of the vehicle ahead and the safety time, making the setting of the initial distance threshold more reasonable. For example, when the speed of the vehicle ahead increases, the initial distance threshold also increases, and vice versa. The introduction of the safety time interval ensures that the initial distance threshold can maintain a reasonable safety range at different vehicle speeds. The specific values of the speed threshold coefficient, the distance threshold coefficient, and the safety time interval can be adjusted according to the actual application scenarios and requirements. As a preferred implementation, the speed threshold coefficient is set to 0.8, the distance threshold coefficient is set to 1.2, and the safety time interval is set to 2 seconds. The setting of these values can ensure the effectiveness and reasonableness of the setting of the initial speed threshold and the initial distance threshold in various typical application scenarios.

[0058] Further, step S23 includes: S231: Query the light intensity value corresponding to the position of the target vehicle according to the first mapping relationship; S232: Normalize the light intensity value to obtain the light intensity level, where the light intensity level includes three levels: strong light, medium light, and weak light; S233: Select the corresponding dynamic threshold adjustment strategy from the preset dynamic threshold adjustment strategy set according to the light intensity level. The dynamic threshold adjustment strategy set includes a strong light strategy, a medium light strategy, and a weak light strategy. The strong light strategy is to keep the initial speed threshold and the initial distance threshold unchanged. The medium light strategy is to reduce the initial speed threshold and the initial distance threshold by 10% respectively. The weak light strategy is to reduce the initial speed threshold and the initial distance threshold by 20% respectively.

[0059] Among them, in step S231, the first mapping relationship can be established in advance. Specifically, a plurality of light intensity sensors, such as photoresistors or photodiodes, are deployed in a preset area in front of the turnstile. Ambient light intensity data is collected at different regional positions. The corresponding relationship between the regional position and the light intensity is recorded and stored in a database or a lookup table, thereby forming the first mapping relationship.

[0060] When the target vehicle enters the preset area in front of the turnstile, according to the current position information of the vehicle, such as the position coordinates obtained through radar data or vehicle detectors, the light intensity value corresponding to the vehicle position is queried in the first mapping relationship.

[0061] In step S232, the purpose of normalizing the light intensity value is to uniformly map different ranges of light intensity values to a fixed range of [0, 1] or [0, 100%], eliminating the differences in dimension and numerical range, which is convenient for subsequent level division and strategy selection. The normalization method can adopt linear transformation. For example, assuming that the original range of the light intensity value is [min_value, max_value], the calculation formula for the normalized light intensity level can be: Light intensity level = (Light intensity value - min_value) / (max_value - min_value) * 100%. The normalized light intensity level is divided into three levels: strong light, medium light, and weak light. For example, the normalized light intensity level above 70% can be divided into the strong light level, 30% to 70% into the medium light level, and below 30% into the weak light level.

[0062] In step S233, the preset dynamic threshold adjustment strategy set includes threshold adjustment strategies for different light intensity levels. The strong light strategy is not to adjust the initial speed threshold and the initial distance threshold, which is applicable when the lighting conditions are good. The driver is not easily affected by light, and even if passing through the turnstile quickly, there will be no acceleration due to misjudgment resulting in rear-end collisions. The medium light strategy is to reduce the initial speed threshold and the initial distance threshold by 10% respectively, which is applicable when the lighting conditions are medium, so that the target vehicle can maintain a relatively safe distance and a relatively safe driving speed from the vehicle in front. Even if the driver accelerates due to limited vision misjudgment, it is not easy to have a rear-end accident. The weak light strategy is to reduce the initial speed threshold and the initial distance threshold by 20% respectively, which is applicable when the lighting conditions are poor. Further reducing the threshold can significantly increase the safety distance and safe driving speed for preventing rear-end collisions, ensuring that following is not likely to occur.

[0063] Further, step S3 includes: S31: Obtain the first radar point cloud data and the second radar point cloud data of the target vehicle and the vehicle in front in the radar data; S32: Extract the target vehicle contour information and the leading vehicle contour information from the first radar point cloud data and the second radar point cloud data respectively; S33: According to the target vehicle contour information and the leading vehicle contour information, use the least squares fitting to obtain the first driving trajectory line of the target vehicle and the second driving trajectory line of the leading vehicle, and calculate the included angle between the first driving trajectory line and the second driving trajectory line; S34: When the included angle is less than or equal to the preset angle threshold, calculate the first velocity vector of the target vehicle and the second velocity vector of the leading vehicle according to the radar data, decompose the first velocity vector to obtain the first longitudinal velocity, decompose the second velocity vector to obtain the second longitudinal velocity, and calculate the velocity component difference between the first longitudinal velocity and the second longitudinal velocity to obtain the relative velocity; S35: Calculate the longitudinal distance and the lateral distance between the target vehicle and the leading vehicle according to the radar data, and calculate the relative distance between the target vehicle and the leading vehicle according to the longitudinal distance and the lateral distance.

[0064] Among them, in step S31, the radar sensor is configured to obtain the radar data of the target vehicle and the leading vehicle in the channel. The first radar point cloud data and the second radar point cloud data respectively correspond to the point cloud sets of the target vehicle and the leading vehicle in the radar data. The first radar point cloud data refers to the reflected point cloud data obtained when the radar device scans the target vehicle, including the contour, position and speed information of the vehicle. The second radar point cloud data refers to the reflected point cloud data obtained when the radar device scans the leading vehicle.

[0065] In step S32, the extraction of the contour information can be realized by the clustering and segmentation algorithms of the point cloud data. For example, the density-based clustering method can be used to identify the point set belonging to the vehicle contour from the point cloud data.

[0066] In step S33, the least squares fitting is used to extract the driving trajectory line of the vehicle from the vehicle contour information. Specifically, the points on the vehicle contour can be linearly fitted to obtain a straight line representing the driving direction of the vehicle. The calculation of the included angle can be obtained by calculating the slopes of the two straight lines and using the slope formula.

[0067] In step S34, the preset angle threshold is set to judge whether the target vehicle is in a trailing state. For example, the preset angle threshold can be set to a larger angle, such as 45 degrees or 60 degrees. When the included angle is less than this threshold, it can be considered that the target vehicle is driving behind the leading vehicle. The calculation of the velocity vector can be directly obtained based on the velocity information of the vehicle in the radar data. The longitudinal velocity can be obtained by projecting the velocity vector onto the driving direction of the vehicle.

[0068] If the included angle is greater than the preset angle threshold, it indicates that the target vehicle is not driving behind the leading vehicle, and it is determined as non-tailgating. In the case of non-tailgating, the gate can be directly controlled to lift the rod, allowing the target vehicle to pass quickly.

[0069] In step S35, the calculation of the longitudinal distance and the lateral distance can be based on the position information of the vehicles in the radar point cloud data. For example, the distance components of the centroids of the point clouds of two vehicles in the vehicle driving direction and the direction perpendicular to the driving direction can be calculated, and thus the longitudinal distance and the lateral distance can be obtained. The relative distance can be calculated according to the longitudinal distance and the lateral distance through the distance formula.

[0070] The technical solution proposed in this application can effectively extract the relative speed and relative distance information of vehicles from radar data, provide reliable data support for tailgating determination, solve the problem that traditional methods may not be able to accurately calculate the relative speed and distance in complex environments, and improve the accuracy and reliability of anti-tailgating control of the access gate.

[0071] Further, step S35 includes: S351: According to the radar data, calculate the first centroid coordinate from the first radar point cloud data of the target vehicle, and calculate the second centroid coordinate from the second radar point cloud data of the leading vehicle; S352: Calculate the projection distance difference of the first centroid coordinate and the second centroid coordinate in the vehicle driving direction to obtain the longitudinal distance, and calculate the projection distance difference of the first centroid coordinate and the second centroid coordinate in the direction perpendicular to the vehicle driving direction to obtain the lateral distance; S353: According to the formula: relative distance = sqrt(longitudinal distance^2 + lateral distance^2), calculate the relative distance.

[0072] Among them, in step S351, the radar data scanned by the radar sensor includes the point cloud data information of the target vehicle and the leading vehicle. The first centroid coordinate and the second centroid coordinate are obtained through mathematical calculations on the point cloud data of their respective vehicles, and the centroid coordinate represents the central position of the vehicle radar point cloud. Compared with directly using all the radar point cloud data of the vehicle, using the centroid coordinate can effectively reduce the noise interference in the radar data and improve the stability of the vehicle position information.

[0073] In step S352, the first centroid coordinate and the second centroid coordinate are projected onto the axis of the vehicle driving direction and the axis perpendicular to the vehicle driving direction. By calculating the projection distance difference on the two axes, the relative position relationship between the vehicles is decomposed into the longitudinal distance and the lateral distance. This decomposition method can more accurately describe the position relationship between the vehicles and provide more accurate distance components for the subsequent relative distance calculation.

[0074] In step S353, the longitudinal distance and the lateral distance are used as the two right-angled sides of a right triangle. Through the operation of taking the square root of the sum of their squares, they are synthesized into a comprehensive relative distance value. This calculation method is based on geometric principles and can accurately reflect the spatial distance between the target vehicle and the vehicle ahead.

[0075] Thus, the present application provides a relative distance calculation method based on centroid coordinates and distance component decomposition. This method can effectively improve the calculation accuracy of relative distance in complex environments and provide a strong guarantee for the anti-tailgating control of the access gate.

[0076] Further, step S5 includes: S51: If it is determined that a tailgating behavior has occurred, obtain the current time and determine whether the current time is during the peak vehicle access period; S52: If the current time is during the peak vehicle access period, control the gate to lift the rod after a preset delay time; S53: If the current time is not during the peak vehicle access period, control the gate not to lift the rod and send a tailgating alarm to the management personnel.

[0077] Among them, in step S51, the current time can be obtained via the system clock. To determine whether the current time is during the peak vehicle access period, the time ranges of the peak period and the non-peak period can be preset. For example, the morning peak period can be set from 7:00 am to 9:00 am, and the evening peak period can be set from 5:00 pm to 7:00 pm. The system compares the current time with the preset time range to determine whether it is during the peak period.

[0078] In step S52, when controlling the gate to lift the rod after a preset delay time, the preset time can be set according to the traffic flow and traffic efficiency requirements of the actual application scenario, such as 3 seconds, 5 seconds, or 10 seconds. After the gate control system receives the tailgating behavior determination signal and the peak period signal, it starts a delay timer. After the timing reaches the preset time, it then controls the gate to lift the rod.

[0079] In step S53, controlling the gate to immediately lift the rod means that after the gate control system receives the tailgating behavior determination signal and the non-peak period signal, it controls the gate not to lift the rod and sends a tailgating alarm to the management personnel, and the management personnel manually intervenes to lift the rod.

[0080] In some specific embodiments, for the trailing control of the access gate in the underground parking lot, the peak vehicle entry and exit periods are preset as the morning rush hour from 7:30 to 8:30 and the evening rush hour from 17:30 to 18:30 on weekdays. When the radar sensor detects a trailing behavior of the target vehicle, the trailing determination module outputs a trailing behavior determination signal. After receiving this signal, the gate control module reads the current time as 8:00 am. After judgment, 8:00 am is within the preset morning rush hour period, and the gate control module controls the gate to lift the rod with a 3-second delay. If the current time is 10:00 am, which is determined to be a non-peak period, the gate control module controls the gate not to lift the rod, sends a trailing alarm to the management personnel, and the manual intervention is required for the rod lifting operation. In this way, the gate control system can effectively relieve vehicle congestion during the peak period and try to avoid the phenomenon of malicious trailing during the non-peak period.

[0081] Please refer to Figure 2 , a passage gate control system, which is applied to the steps of a passage gate control method in any one of the above, and the system includes: Radar data acquisition module 201: used to acquire the radar data of the target vehicle and the vehicle in front in the passage, and calculate the speed of the vehicle in front according to the radar data; Dynamic threshold calculation module 202: used to calculate the speed threshold and distance threshold of the target vehicle according to the speed of the vehicle in front and in accordance with the preset dynamic threshold adjustment strategy; Data calculation module 203: used to calculate the relative speed and relative distance of the target vehicle relative to the vehicle in front according to the radar data; Trailing determination module 204: used to compare the relative speed with the speed threshold, and compare the relative distance and the distance threshold. If the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is determined that a trailing behavior has occurred. Otherwise, when the relative distance between the target vehicle and the vehicle in front is less than the distance threshold, timing is started. If the timing duration exceeds the preset time threshold, it is determined that a trailing behavior has occurred; Gate control module 205: used to control the gate to perform corresponding actions if it is determined that a trailing behavior has occurred.

[0082] Among them, the radar data acquisition module 201 can be configured to periodically scan the target vehicle and the vehicle in front in the passage by using a radar sensor, so as to acquire the original radar data. The original radar data is then subjected to noise removal and smoothing preprocessing to obtain accurate radar data. In order to calculate the speed of the vehicle in front, the radar data acquisition module further tracks the vehicle in front and establishes a speed time series of the vehicle in front. The speed time series records the speed values of the vehicle in front at each moment within a preset time window. By analyzing the speed time series, the speed of the vehicle in front can be accurately calculated.

[0083] The dynamic threshold calculation module 202 is configured to dynamically adjust the threshold for following determination based on the speed of the vehicle ahead. The module first calculates the initial speed threshold and the initial distance threshold based on the speed of the vehicle ahead. Considering the complexity of the lighting environment in the underground parking lot, the module also collects the ambient light intensity data of a preset area in front of the gate, and establishes the first mapping relationship between the area position and the light intensity. Using the first mapping relationship, the light intensity level of the area where the target vehicle is located is determined, and the corresponding dynamic threshold adjustment strategy is selected according to the light intensity level. The dynamic threshold adjustment strategy is used to adjust the initial speed threshold and the initial distance threshold to obtain the final speed threshold and distance threshold.

[0084] The data calculation module 203 is responsible for accurately calculating the relative speed and relative distance of the target vehicle relative to the vehicle ahead. The data calculation module 203 first extracts the radar point cloud data of the target vehicle and the vehicle ahead from the radar data, and extracts the vehicle contour information based on the radar point cloud data respectively. Through the vehicle contour information, the vehicle driving trajectory line is obtained by using the least squares fitting, and the included angle between the two driving trajectory lines is calculated. When the included angle is less than or equal to the preset angle threshold, the module calculates the vehicle speed vector, decomposes the speed vector to obtain the longitudinal speed, and calculates the speed component difference of the longitudinal speed to obtain the relative speed. At the same time, the module calculates the longitudinal distance and the lateral distance between the vehicles according to the radar data, and calculates the relative distance by combining the longitudinal distance and the lateral distance.

[0085] The following determination module 204 has the core function of determining whether a following behavior occurs based on the calculated relative speed, relative distance, and dynamic threshold. The module compares the relative speed with the speed threshold, and the relative distance with the distance threshold. If the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is directly determined that a following behavior occurs. In the case where the above conditions are not met, when the relative distance is less than the distance threshold, the module starts a timer. If the timing duration exceeds the preset time threshold, it is also determined that a following behavior occurs.

[0086] The gate control module 205 performs the corresponding gate control actions when the following determination module determines that a following behavior occurs. As an optimization, the gate control module can be configured to consider the peak hours of vehicle entry and exit. The module obtains the current time and determines whether the current time is during the peak hours of vehicle entry and exit. If it is during the peak hours, the module controls the gate to lift the rod after a preset time delay to relieve traffic pressure. If it is not during the peak hours, the module controls the gate not to lift the rod and sends a following alarm to the management personnel, and the management personnel manually intervenes to lift the rod to prevent malicious following.

[0087] In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0088] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A channel gate control method, characterized in that: Applied to a gate of an underground parking lot, the gate is equipped with a radar sensor, and the method comprises the steps of: S1: Acquire radar data of the target vehicle and the front vehicle in the channel, and calculate the speed of the front vehicle based on the radar data; S2: Calculate the speed threshold and distance threshold of the target vehicle according to the preset dynamic threshold adjustment strategy based on the speed of the vehicle ahead; S3: Calculating the relative speed and relative distance of the target vehicle relative to the preceding vehicle according to the radar data; S4: comparing the relative speed with the speed threshold, and comparing the relative distance with the distance threshold, if the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is determined that tailgating occurs; otherwise, when the relative distance between the target vehicle and the vehicle ahead is less than the distance threshold, starting timing, if the timing exceeds a preset time threshold, it is determined that tailgating occurs; S5: If it is determined that tailgating occurs, the gate is controlled to perform corresponding actions.

2. A channel gate control method according to claim 1, characterized in that: Step S1 includes: S11: periodically scan the target vehicle and the vehicle ahead in the channel at a preset sampling frequency to obtain raw radar data; S12: performing denoising and smoothing preprocessing on the original radar data to obtain radar data; S13: Tracking the vehicle ahead according to the radar data, establishing a speed time series of the vehicle ahead, and calculating the speed of the vehicle ahead based on the speed time series.

3. A channel gate control method according to claim 2, characterized in that: Step S13 includes: S131: Identify and associate multiple vehicles in the channel according to the radar data, assign a unique tracking ID to each vehicle, and record the position, speed and angle information of each vehicle; S132: predicting the state of the vehicle ahead at the next moment using the position, speed and angle information for the tracking ID of the vehicle ahead; S133: establishing a speed time series of the front vehicle according to the state of the front vehicle, wherein the speed time series records the speed values ​​of the front vehicle at various moments within a preset time window; S134: performing outlier detection on the speed time series, eliminating outlier speed values ​​in the speed time series whose speed values ​​exceed a preset speed value range, and processing the speed time series using a median filter to obtain the speed of the vehicle ahead.

4. A channel gate control method according to claim 1, characterized in that: Step S2 includes: S21: Calculating an initial speed threshold and an initial distance threshold according to the speed of the vehicle ahead; S22: Collecting ambient light intensity data of a preset area in front of the gate, and establishing a first mapping relationship between the area position and the light intensity; S23: determining the light intensity level of the area where the target vehicle is located according to the first mapping relationship, and selecting a corresponding dynamic threshold adjustment strategy according to the light intensity level; S24: adjusting the initial speed threshold and the initial distance threshold according to the selected dynamic threshold adjustment strategy to obtain the speed threshold and the distance threshold.

5. A channel gate control method according to claim 4, characterized in that: Step S21 includes: S211: The formula for calculating the initial speed threshold according to the speed of the vehicle ahead is: Initial speed threshold = speed threshold coefficient * front vehicle speed, the speed threshold coefficient is 0.8; S212: The formula for calculating the initial distance threshold according to the speed of the vehicle ahead is: Initial distance threshold=distance threshold coefficient*front vehicle speed*safety time interval, the distance threshold coefficient is 1.2, and the safety time interval is 2 seconds.

6. A channel gate control method according to claim 5, characterized in that: Step S23 includes: S231: querying the light intensity value corresponding to the position of the target vehicle according to the first mapping relationship; S232: normalizing the light intensity value to obtain a light intensity level, where the light intensity level includes three levels: strong light, medium light, and weak light; S233: According to the light intensity level, select a corresponding dynamic threshold adjustment strategy from a preset dynamic threshold adjustment strategy set, wherein the dynamic threshold adjustment strategy set includes a strong light strategy, a medium light strategy and a weak light strategy, the strong light strategy is to keep the initial speed threshold and the initial distance threshold unchanged, the medium light strategy is to reduce the initial speed threshold and the initial distance threshold by 10% respectively, and the weak light strategy is to reduce the initial speed threshold and the initial distance threshold by 20% respectively.

7. A channel gate control method according to claim 1, characterized in that: Step S3 includes: S31: Acquire first radar point cloud data and second radar point cloud data of the target vehicle and the front vehicle in the radar data; S32: extracting target vehicle contour information and front vehicle contour information respectively according to the first radar point cloud data and the second radar point cloud data; S33: according to the target vehicle profile information and the front vehicle profile information, using least second order fitting to obtain a first driving trajectory of the target vehicle and a second driving trajectory of the front vehicle, and calculating an angle between the first driving trajectory and the second driving trajectory; S34: when the angle is less than or equal to a preset angle threshold, calculating, according to the radar data, a first velocity vector of the target vehicle and a second velocity vector of the front vehicle, decomposing the first velocity vector to obtain a first longitudinal velocity, decomposing the second velocity vector to obtain a second longitudinal velocity, and calculating a velocity component difference between the first longitudinal velocity and the second longitudinal velocity to obtain a relative velocity; S35: Calculate the longitudinal distance and the lateral distance between the target vehicle and the vehicle in front according to the radar data, and calculate the relative distance between the target vehicle and the vehicle in front according to the longitudinal distance and the lateral distance.

8. A channel gate control method according to claim 7, characterized in that: Step S35 includes: S351: Calculating first centroid coordinates from first radar point cloud data of the target vehicle according to the radar data, and calculating second centroid coordinates from second radar point cloud data of the front vehicle; S352: Calculate the difference in projection distance between the first centroid coordinate and the second centroid coordinate in the vehicle driving direction to obtain the longitudinal distance, and calculate the difference in projection distance between the first centroid coordinate and the second centroid coordinate in a direction perpendicular to the vehicle driving direction to obtain the lateral distance; S353: According to the formula: relative distance=sqrt(longitudinal distance^2+lateral distance^2), the relative distance is calculated.

9. A channel gate control method according to claim 1, characterized in that: Step S5 includes: S51: If it is determined that tailgating occurs, obtain the current time and determine whether the current time is during a peak vehicle entry and exit period; S52: If the current time is during the peak period of vehicle entry and exit, the gate is controlled to delay the lifting of the gate by a preset time; S53: If the current time is not during the peak period of vehicle ingress and egress, the gate is controlled not to lift the barrier, and a tailgating alarm is sent to the management personnel.

10. A channel gate control system, applied to the steps of a channel gate control method as described in any one of claims 1 to 9, characterized in that: The system comprises: Radar data acquisition module: used to acquire radar data of the target vehicle and the vehicle in front in the channel, and calculate the speed of the vehicle in front according to the radar data; Dynamic threshold calculation module: used to calculate the speed threshold and distance threshold of the target vehicle according to the speed of the vehicle ahead and the preset dynamic threshold adjustment strategy; Data calculation module: used to calculate the relative speed and relative distance of the target vehicle relative to the front vehicle according to the radar data; A tailing determination module: used for comparing the relative speed with the speed threshold, and comparing the relative distance with the distance threshold. If the relative speed is greater than or equal to the speed threshold and the relative distance is less than or equal to the distance threshold, it is determined that tailing occurs. Otherwise, when the relative distance between the target vehicle and the vehicle ahead is less than the distance threshold, the timing is started. If the timing exceeds a preset time threshold, it is determined that tailing occurs. Gate control module: used to control the gate to perform corresponding actions if tailgating is detected.

Images