A traffic signal data automatic classification control method based on target recognition

Abstract

The application discloses a traffic signal data automatic classification control method based on target identification, relates to the technical field of signal processing, and is used for improving problems such as sudden accidents caused by the fact that target vehicle characteristics are not timely received at a fixed frequency, and comprises the following steps: a mechanism of an exploration time is set; when a sudden event occurs, a plurality of laser radar detection frequencies are set in the exploration time for screening; the screened laser radar detection frequencies are used to detect the motion state of a target vehicle; the motion state of the target vehicle, the speed of the system itself and the event abnormality degree are analyzed and determined by using a reinforcement learning method; the system transmits pulses and receives reflected signals to determine the type of a small vehicle target; the laser radar detection frequency is adjusted in combination with the event abnormality degree and the type of the small vehicle target; the touch time is dynamically updated by using the laser radar detection frequency; the safety distance is calculated according to the touch time to set an alarm threshold; and when the distance between vehicles reaches the alarm threshold, an alarm is given.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of signal processing, more particularly, the present application relates to a traffic signal data automatic classification control method based on target recognition. BACKGROUND

[0002] Signal processing technology plays a crucial role in laser radar and other sensor systems, mainly used to improve data quality, enhance signal features and realize real-time analysis, and the application of signal processing technology in traffic signal target recognition can predict accidents and provide important assistance for drivers to avoid in advance.

[0003] The prior art has the following disadvantages:

[0004] In the past, laser radar receives target vehicle features by presetting pulse emission frequency and makes subsequent judgment and processing, when the target vehicle changes the motion state and trajectory, the preset fixed frequency receiving target vehicle features is not timely and is easily affected by sudden situations, resulting in traffic problems such as traffic accidents. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a traffic signal data automatic classification control method based on target recognition, which dynamically adjusts the laser radar detection frequency and the alarm threshold by analyzing the abnormal behavior of the target vehicle and the risk degree caused by the collision between the target vehicle and the vehicle itself to solve the problems raised in the above background technology.

[0006] To achieve the above purpose, the present application provides the following technical scheme:

[0007] A traffic signal data automatic classification control method based on target recognition, comprising the following steps:

[0008] Step S1, set the exploration time, set a plurality of laser radar detection frequencies in the exploration time to detect the signal-to-noise ratio respectively, and select the maximum signal-to-noise ratio as the initial laser radar detection frequency;

[0009] Step S2, calculate the event anomaly index by using the initial laser radar detection frequency to detect the motion state of the vehicle and the motion state of the target vehicle;

[0010] Step S3, receive the detection target reflection signal feature to determine the small vehicle target type, and adjust the laser radar detection frequency by comprehensively considering the event anomaly index and the small vehicle target type;

[0011] Step S4, calculate the collision time by the laser radar detection frequency and the distance between the target vehicle and the vehicle, and set the alarm threshold according to the collision time.

[0012] In a preferred embodiment, in step S1, the exploration time is used to search for the laser radar detection frequency under the maximum signal-to-noise ratio, which is a measure of the ratio between the strength of the signal and the strength of the background noise, and is used to evaluate the ability to detect targets in the laser radar system, and a higher signal-to-noise ratio can improve the recognition rate and accuracy of the target.

[0013] In a preferred embodiment, in step S2, the ego vehicle motion state includes the current position, speed and direction of travel of the ego vehicle, and the target vehicle motion state includes the current position, speed and direction of travel of the target vehicle.

[0014] In a preferred embodiment, in step S2, the relative position between the ego vehicle and the target vehicle is calculated by the current position of the ego vehicle and the current position of the target vehicle, and the event anomaly index is calculated using a reinforcement learning method in combination with the speed, direction of travel of the ego vehicle and the speed, direction of travel of the target vehicle.

[0015] In a preferred embodiment, in step S2, the event anomaly index is calculated using a reinforcement learning method, and the specific steps are as follows:

[0016] Environment setting: set the vehicle state, set the vehicle action, and set the behavior reward according to the vehicle state and the vehicle action;

[0017] Reinforcement learning: initialize the event anomaly index, set the reward mechanism, update the event anomaly index according to the reward mechanism, formulate the training rules, set the time step, and update the event anomaly index at each time step.

[0018] In a preferred embodiment, in step S3, when the detection target reflection signal feature is used to determine the type of small vehicle target, the type of small vehicle target is determined by comparing the reflection signals and shapes of different types of small vehicles in the database, and different feature coefficients are calculated according to the type of small vehicle target, if the target vehicle is a non-motor vehicle, the feature coefficient is set to 0, and if the target vehicle is a motor vehicle, the feature coefficient is calculated as follows:

[0019] Select a period of detection time to record all the target vehicle sizes and target vehicle speeds of small vehicles, and merge them into a vehicle size dataset and a vehicle speed dataset respectively, and sort the data in the vehicle size dataset and the vehicle speed dataset after unitization, and set the classification interval in the order from small to large, set the segmentation ratio to divide the dataset into multiple small datasets, get the numerical interval of the divided small datasets and calculate the average value, select the median value in the average value, and calculate the ratio of the average value of each small dataset to the median value as the vehicle size coefficient or the vehicle speed coefficient;

[0020] After detecting the target vehicle, the size of the target vehicle and the corresponding small data set value interval of the driving speed of the target vehicle are determined, and the average value of the vehicle size coefficient and the vehicle speed coefficient of the corresponding small data set is calculated as the characteristic coefficient of the target vehicle.

[0021] In a preferred embodiment, in step S3, the characteristic coefficient of the target vehicle and the event anomaly coefficient obtained at each time step are used to calculate the logistic regression coefficient as the adjustment ratio of the laser radar detection frequency by using the logistic regression method, and the ratio of the previous laser radar detection frequency to the adjustment ratio is taken as the adjusted laser radar detection frequency at each time step.

[0022] In a preferred embodiment, in step S4, the system calculates the collision time and dynamically sets the safety distance according to the detection range of the laser radar, and the specific steps are as follows:

[0023] Each time the laser radar detection frequency is updated, the same direction difference is performed according to the vehicle speed and the target vehicle speed, the collision speed is calculated by summing in opposite directions, and the size of the collision speed is compared with the recorded collision speed, the larger speed is selected for calculation, the ratio of the distance between the target vehicle and the vehicle to the selected collision speed is taken as the collision time, and the collision time is compared with the recorded collision time, the smaller one is selected as the collision evaluation time, the safety distance is calculated by setting the safety range ratio, and the product of the collision evaluation time and the safety range ratio and the collision speed is taken as the safety range.

[0024] In a preferred embodiment, in step S4, the motion state of the target vehicle and the motion state of the vehicle are detected at each time step by adjusting the laser radar detection frequency, and the safety range is dynamically updated, and when the distance between the vehicle and the target vehicle reaches the safety range, the alarm is alarmed.

[0025] The technical effects and advantages of the traffic signal data automatic classification control method based on target recognition are as follows:

[0026] This invention employs an exploration time mechanism. During the exploration period following a sudden event, multiple lidar detection frequencies are selected for filtering. The selected lidar frequencies are used to detect the movement of target vehicles, improving the accuracy of vehicle data detection and providing a data foundation for subsequent anomaly analysis. The system determines the severity of the event by combining the vehicle's own speed and the target vehicle's movement. It then emits pulses and receives reflected signals to identify the type of small vehicle target. Analyzing the characteristics of different vehicles based on their target types helps determine the risk of collision, improving the accuracy of adjusting lidar detection frequencies and alarm thresholds. The lidar detection frequency is adjusted based on the severity of the event and the type of small vehicle target. Finally, the contact time is dynamically updated based on the lidar detection frequency. A safe distance is calculated based on the contact time, and an alarm threshold is set. When the vehicle-to-vehicle distance reaches the alarm threshold, an alarm is triggered to ensure driver safety. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of an automatic classification and control method for traffic signal data based on target recognition according to the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] This invention establishes an exploration time mechanism. When a sudden event occurs, multiple lidar detection frequencies are set within the exploration time for filtering. The selected lidar detection frequencies are used to detect the movement state of the target vehicle. The severity of the event is determined by combining the vehicle's own speed and the target vehicle's movement state. The system emits pulses and receives reflected signals to determine the type of small vehicle target. The lidar detection frequency is adjusted based on the severity of the event and the type of small vehicle target. Finally, the contact time is dynamically updated based on the lidar detection frequency. A safe distance is calculated based on the contact time, and an alarm threshold is set. When the vehicle-to-vehicle distance reaches the alarm threshold, an alarm is triggered to ensure driver safety.

[0030] An example is an automatic classification and control method for traffic signal data based on target recognition, such as... Figure 1 As shown, it includes the following steps:

[0031] Step S1: Set the exploration time. During the exploration time, set multiple lidar detection frequencies to detect the signal-to-noise ratio (SNR) respectively, and select the maximum SNR as the initial lidar detection frequency.

[0032] Step S2, detecting the motion state of the vehicle and the target vehicle to calculate the event anomaly index using the initial laser radar detection frequency;

[0033] Step S3, receiving the target reflection signal characteristics to determine the small vehicle target type, and adjusting the laser radar detection frequency by combining the event anomaly index and the small vehicle target type;

[0034] Step S4, calculating the collision time by the laser radar detection frequency and the distance between the target vehicle and the vehicle, and setting the alarm threshold according to the collision time.

[0035] The specific implementation is as follows:

[0036] In step S1, the exploration time is used to search for the laser radar detection frequency with the maximum signal-to-noise ratio. The laser radar detection frequency is the frequency of transmitting and receiving laser pulses by the laser radar. The greater the frequency of transmitting and receiving laser pulses, the higher the target detection detail and resolution, but also increases the energy consumption.

[0037] The signal-to-noise ratio is the ratio between the strength of the signal and the strength of the background noise. In radar and laser radar systems, the signal-to-noise ratio is used to evaluate the ability to detect targets. A higher signal-to-noise ratio can improve the recognition rate and accuracy of targets.

[0038] The exploration time is set by the percentile method. When the laser radar detects the target vehicle, the speed and direction of the target vehicle are obtained. The system collects the speed and direction of the vehicle and calculates the driving time when the vehicle and the target vehicle drive to the shortest distance. According to the driving time, set the N% percentile to set the exploration time. For example, if the driving time is 5 seconds, take 20% as the exploration time, then the exploration time is 1 second.

[0039] Record the radar echo data for a period of time before the laser radar detects the target vehicle, and calculate the average value of the noise as the standard noise. Within the exploration time, the system randomly sets multiple laser radar detection frequencies to emit laser pulses to the target vehicle and receive the intensity of the laser pulses reflected by the target vehicle. Calculate the signal-to-noise ratio of the laser pulse intensity at different laser radar detection frequencies and the standard noise. Compare the calculated signal-to-noise ratios, and select the laser radar detection frequency with the maximum signal-to-noise ratio as the initial laser radar detection frequency.

[0040] It should be noted that when randomly setting multiple laser radar detection frequencies, the switching time can be set according to the actual situation, that is, a laser radar detection frequency is randomly generated every switching time within the exploration time. For example, if the exploration time is 1 second and the switching time is 0.1 second, a laser radar detection frequency is generated every 0.1 second within the exploration time, and the average value of the received laser pulse intensity within 0.1 second is calculated as the laser pulse intensity corresponding to the laser radar detection frequency.

[0041] In step S2, the ego vehicle motion state includes the current position, speed and direction of the ego vehicle, the target vehicle motion state includes the current position, speed and direction of the target vehicle, and the relative position between the ego vehicle and the target vehicle is calculated according to the current position of the ego vehicle and the current position of the target vehicle.

[0042] The current position of the ego vehicle and the current position of the target vehicle can be represented by coordinates. The system determines the coordinates of the ego vehicle using the Beidou system and detects the coordinates of the target vehicle using a laser radar. When calculating the relative position between the two, the coordinate difference obtained by subtracting the horizontal and vertical coordinates of the two coordinates is taken to obtain the square root. The relative position between the two, the speed and direction of the ego vehicle, and the speed and direction of the target vehicle are used to calculate the event anomaly index using a reinforcement learning method. The specific steps are as follows:

[0043] Environment setting: Set the state, record the relative position between the ego vehicle and the target vehicle, and their respective speeds and directions; Set the action, accelerate, decelerate, turn left, turn right, and maintain the status quo; Set the reward mechanism, give negative reward when touching, give positive reward according to time when not colliding, and give behavior reward to the set action respectively.

[0044] Reinforcement learning:

[0045] Step 1: Initialization, set the initial event anomaly index according to the relative position between the ego vehicle and the target vehicle, which can be set according to the distance between the ego vehicle and the target vehicle, for example, when the distance between the ego vehicle and the target vehicle is 60 meters, set the initial event anomaly index to 60.

[0046] Step 2: Set up a reward mechanism, i.e. an updating mechanism for the event anomaly index, limit the event anomaly index to 100 at most, give a negative reward to deduct 100 from the event anomaly index when touching, set a judgment frequency, make a judgment according to the judgment frequency, give a positive reward to increase the event anomaly index by 1 when the ego vehicle does not collide, give a positive reward to increase the event anomaly index by 10 when gradually moving away from the target, give a negative reward to deduct 10 from the event anomaly index when gradually approaching the target. Set up a behavior reward, when the ego vehicle performs an action, if it is in the same direction as the target vehicle, increase the event anomaly index by 5, if it is in the opposite direction, deduct 5 from the event anomaly index; for example, if the ego vehicle acceleration or steering direction is consistent with the target vehicle speed direction, it is in the same direction; if the ego vehicle acceleration or steering direction has an included angle with the target vehicle speed direction, take the positive angle direction smaller than the right angle in the east, south, west and north as the ego vehicle driving direction and the target vehicle speed direction for comparison; otherwise, it is in the opposite direction. In addition, when the ego vehicle performs an action and is at right angles to the target vehicle, the event anomaly index does not change.

[0047] Step 3: Develop training rules, set time steps at the judgment frequency, observe the state of the ego vehicle and the target vehicle at each time step, randomly perform an action to update the position and state of the ego vehicle, receive rewards and record the updated event anomaly index.

[0048] It should be noted that the Beidou system is a global satellite navigation system, which can be used to determine the vehicle coordinates, and the reinforcement learning method belongs to the category of machine learning, which learns to optimize decision-making strategies through interaction with the environment, and can set up and update the event anomaly index through the reinforcement learning method, which is convenient for subsequent adjustment of the laser radar detection frequency and the alarm threshold. Time step is a basic time unit for system update.

[0049] In step S3, the detection target reflection signal feature determines the small vehicle target type by comparing the reflection intensity comparison table and shape comparison library of different types of small vehicle reflection signals in the open source database to determine the small vehicle target type, and dynamically adjusts the laser radar detection frequency based on the event anomaly index and the small vehicle target type.

[0050] The laser radar detection frequency is adjusted by obtaining the event anomaly index at each time step and combining the small vehicle target type, and the specific steps are as follows:

[0051] When a small vehicle appears in the detection range of the laser radar, the target vehicle is classified as a motor vehicle or a non-motor vehicle by emitting a pulse and receiving the detection target reflection signal feature, and if the target vehicle is a motor vehicle, the target vehicle is further divided, and the target vehicle size and target vehicle speed in the detection target reflection signal feature are used to set the interval for division.

[0052] When setting the interval, a detection experiment can be performed, a detection time is selected for the detection experiment, and the target vehicle size and target vehicle speed of all small vehicles in the detection time are recorded and merged into a vehicle size data set and a vehicle speed data set, respectively. The data in the vehicle size data set and the vehicle speed data set are de-unitized and numerically sorted in ascending order after sorting. The classification interval is set by using the percentile method to divide the data set, setting M% as the division ratio, and dividing the data set into multiple small data sets according to M%. Taking the vehicle size data set as an example, the minimum value and the maximum value in the divided small data set are used as the comparison numerical interval, and the average value is calculated. The median in the average value is selected, and the ratio of the average value of each small data set to the median is used as the vehicle size coefficient. The vehicle speed coefficient can be obtained in the same way.

[0053] When the laser radar detects the target vehicle, the target vehicle size and target vehicle speed are compared with the comparison numerical interval, the vehicle size coefficient and the vehicle speed coefficient of the interval to which the target vehicle size and target vehicle speed belong are calculated, and the average value is calculated as the feature coefficient of the target vehicle. In addition, if the detection target reflection signal feature determines that the target vehicle is a non-motor vehicle, the feature coefficient of the target vehicle is set to 0 by default.

[0054] After obtaining the feature coefficient of the target vehicle, the event anomaly index of the detected target vehicle is processed, the event anomaly index of the target vehicle is compared with the set event anomaly index upper limit, the operation result is used as the abnormal coefficient, the higher the abnormal coefficient, the higher the event anomaly index of the target vehicle under the condition that the event anomaly index upper limit does not change, and the more likely the collision between the ego vehicle and the target vehicle, and the laser radar detection frequency needs to be accelerated and the detection interval time needs to be reduced.

[0055] The abnormal coefficient and the feature coefficient of the target vehicle are used to calculate the logistic regression coefficient by using the logistic regression method to adjust the laser radar detection frequency, and the calculation formula is: where P is the logistic regression coefficient, z is the sum of the feature coefficient and the abnormal coefficient of the target vehicle, and e is the natural base. The calculated logistic regression coefficient is used as the adjustment ratio of the laser radar detection frequency, and the adjusted laser radar detection frequency is: , ​To adjust the laser radar detection frequency.

[0056] It should be noted that the larger the size of the target vehicle or the faster the speed, the greater the damage caused by the collision, and the laser radar detection frequency needs to be accelerated, that is, the interval time of detection is reduced, and the characteristic coefficient is the average of the vehicle size coefficient and the vehicle speed coefficient of the target vehicle. The larger the characteristic coefficient of the target vehicle, the larger the vehicle size coefficient or the vehicle speed coefficient of the target vehicle, that is, the larger the vehicle size and the vehicle speed of the target vehicle, the more the interval time of detection needs to be reduced. The segmentation ratio can be set according to actual requirements, for example, the segmentation ratio is set to 20%, the data set is divided into five small data sets, and five comparative numerical intervals are obtained, which will not be described here.

[0057] In step S4, the system calculates the collision time and sets the safety distance according to the laser radar detection range. When the target vehicle enters the set safety distance, the alarm is triggered to alarm. The safety distance can be dynamically set by calculating the collision time through the laser radar detection frequency and the distance between the target vehicle and itself. Each time the laser radar detection frequency is updated, the same direction difference is operated according to the speed of the vehicle itself and the speed of the target vehicle, and the opposite direction sum is operated, for example, when the driving direction of the vehicle itself and the target vehicle is the same, the speed of the target vehicle is subtracted from the speed of the vehicle itself, and when the driving direction of the vehicle itself and the target vehicle is opposite, the speed of the target vehicle is summed as the collision speed.

[0058] It should be explained that since there are many driving directions between vehicles, the driving speed of the vehicle itself and the target vehicle is calculated by taking the driving speed component on the parallel line of the distance between the two vehicles, for example, when the angle between the driving direction of the two vehicles and the parallel line of the distance between the two vehicles is 30 degrees, the driving speed of the vehicle is the speed component after taking 30 degrees cosine of the original driving speed on the average line of the distance between the two vehicles.

[0059] Record the collision speed under each laser radar detection frequency, and compare it with the collision speed recorded last time to select the larger speed for calculation. The ratio of the distance between the target vehicle and the vehicle itself to the selected collision speed is recorded as the collision time. When the laser radar detection frequency is updated at each time step, the collision time is also dynamically updated. The minimum value of the past recorded collision time is selected as the collision evaluation time. The safety distance is calculated by setting the safety range ratio. The product of the collision evaluation time multiplied by the safety range ratio and the collision speed is taken as the safety range. When the distance between the vehicle itself and the target vehicle reaches the safety range, the alarm is alarmed.

[0060] It should be noted that the safety range ratio is used to control the size of the set safety range, which is set by the user using the user interface, and will not be analyzed here.

[0061] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product.

[0062] Those skilled in the art can realize that the modules and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and the constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0063] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0064] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0065] Finally, the above is merely preferred embodiments of the present application, and is not intended to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for automatic classification and control of traffic signal data based on target recognition, characterized in that, Includes the following steps, Step S1: Set the exploration time. During the exploration time, set multiple lidar detection frequencies to detect the signal-to-noise ratio respectively, and select the lidar detection frequency corresponding to the maximum signal-to-noise ratio as the initial lidar detection frequency. Step S2: Detect the motion state of the vehicle itself and the target vehicle using the initial lidar detection frequency to calculate the event anomaly index. Step S3: Receive the characteristics of the reflected signal from the detected target to determine the type of small vehicle target, and adjust the lidar detection frequency based on the event anomaly index and the type of small vehicle target. Step S4: Calculate the collision time by using the lidar detection frequency and the distance between the target vehicle and the vehicle itself, calculate the safe distance based on the collision time, and use the safe distance as the alarm threshold.

2. The automatic classification and control method for traffic signal data based on target recognition according to claim 1, characterized in that: In step S1, the exploration time is used to search for the lidar detection frequency with the maximum signal-to-noise ratio (SNR). The SNR is a measure of the ratio between the strength of a signal and the strength of background noise. In a lidar system, the SNR is used to evaluate the ability to detect targets. A higher SNR can improve the target recognition rate and accuracy.

3. The automatic classification and control method for traffic signal data based on target recognition according to claim 1, characterized in that: In step S2, the motion state of the vehicle itself includes its current position, speed and direction of travel, and the motion state of the target vehicle includes its current position, speed and direction of travel.

4. The automatic classification and control method for traffic signal data based on target recognition according to claim 3, characterized in that: In step S2, the relative positions between the vehicle and the target vehicle are calculated using the vehicle's current position and the target vehicle's current position. The event anomaly index is then calculated using reinforcement learning methods, taking into account the vehicle's speed and direction of travel as well as the target vehicle's speed and direction of travel.

5. The automatic classification and control method for traffic signal data based on target recognition according to claim 4, characterized in that: In step S2, the specific steps for calculating the event anomaly index using reinforcement learning methods are as follows: Environment settings: Set vehicle status, set vehicle actions, and set behavioral rewards based on vehicle status and vehicle actions; Reinforcement learning: Initialize the event anomaly index, set a reward mechanism, update the event anomaly index according to the reward mechanism, formulate training rules, set time steps, and update the event anomaly coefficient at each time step.

6. The automatic classification and control method for traffic signal data based on target recognition according to claim 1, characterized in that: In step S3, when determining the type of small vehicle target by receiving the characteristics of the detected target reflection signal, the type of small vehicle target is determined by comparing the reflection signals and shapes of different types of small vehicles in the database. Different feature coefficients are calculated according to the type of small vehicle target. If the target vehicle is a non-motorized vehicle, the feature coefficient is set to 0; if the target vehicle is a motorized vehicle, ... The steps for calculating its characteristic coefficients are as follows: Select a detection time period to record the target vehicle size and target vehicle speed of all small vehicles and merge them into vehicle size dataset and vehicle speed dataset respectively. After denormalizing the data in the vehicle size dataset and vehicle speed dataset, sort the values ​​in ascending order and set the classification interval. Set the split ratio to divide the dataset into multiple small datasets, obtain the value interval of the divided small datasets and calculate the average value. Select the median of the average value and calculate the ratio of the average value to the median of each small dataset as the vehicle size coefficient or vehicle speed coefficient. After detecting the target vehicle, the numerical range of the small dataset corresponding to the target vehicle size and the target vehicle speed is determined. The average value of the vehicle size coefficient and vehicle speed coefficient of the corresponding small dataset is calculated as the feature coefficient of the target vehicle.

7. The automatic classification and control method for traffic signal data based on target recognition according to claim 6, characterized in that: In step S3, the characteristic coefficients of the target vehicle and the event anomaly coefficients obtained at each time step are used to calculate the logistic regression coefficient as the adjustment ratio of the lidar detection frequency. At each time step, the ratio of the previous lidar detection frequency to the adjustment ratio is used as the adjusted lidar detection frequency.

8. The automatic classification and control method for traffic signal data based on target recognition according to claim 1, characterized in that: In step S4, after calculating the collision time, the system dynamically sets a safe distance based on the lidar detection range. The specific steps are as follows: Each time the lidar detection frequency is updated, the collision speed is calculated by subtracting the speed of the vehicle itself and the speed of the target vehicle in the same direction and summing the speeds in opposite directions. This speed is then compared with the previously recorded collision speed, and the larger speed is selected for calculation. The ratio of the distance between the target vehicle and the vehicle itself to the selected collision speed is recorded as the collision time and compared with the previously recorded collision time. The smaller time is selected as the collision assessment time. A safety range ratio is set to calculate the safety distance. The product of the collision assessment time multiplied by the safety range ratio and the collision speed is used as the safety range.

9. The automatic classification and control method for traffic signal data based on target recognition according to claim 8, characterized in that: In step S4, the safety range is dynamically updated by detecting the target vehicle's motion state and the vehicle's own motion state at each time step using the adjusted lidar detection frequency. When the distance between the vehicle and the target vehicle reaches the safety range, the alarm is triggered.

Images