A vehicle stall identification method based on lane change auxiliary radar

Abstract

The present invention relates to a vehicle stall distinguishing method based on lane change assist radar, which establishes a vehicle speed sliding window, adopts an extreme value calculation average method to obtain a vehicle speed average, compares the real-time vehicle speed with the average, and judges whether to enter a stall processing logic; if the difference between the real-time vehicle speed and the average exceeds a preset threshold, it is judged as a stall state, and the average vehicle speed is used instead of the real-time vehicle speed to maintain a target alarm logic until normal speed measurement is restored; the present invention effectively solves the problem of underreporting caused by the failure of lane change assist radar speed measurement in specific scenarios, such as severe weather conditions such as rain and snow, and the presence of long trailers or smooth cement guardrails in adjacent lanes, thereby improving driving safety.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile assisted driving, and in particular to a vehicle stall determination method based on lane change auxiliary radar. Background Art

[0002] Millimeter-wave radar is small in size, light in weight, has high measurement accuracy and strong ability to penetrate smoke and dust. It has the advantages of working uninterruptedly around the clock and has been widely used in the field of automobile assisted driving. Lane change assist radar is an important component of the current advanced driver assistance system. It can not only detect the distance and speed of objects, but also identify the height and shape of objects, providing more accurate detection and assistance functions. Under normal circumstances, the lane change assist radar can obtain the speed of the vehicle by reverse inference through the stationary target on the ground, so as to determine whether there is a target in the adjacent lane that needs to generate an alarm. In some extreme cases, such as heavy rain and the presence of a large trailer or a smooth concrete guardrail in the adjacent lane of the vehicle, the radar field of view can no longer detect stationary targets on the ground, as well as curves or ramps. The vehicle's driving trajectory and speed change significantly, and the radar is difficult to obtain stable surface information for speed measurement. At this time, the radar's calculation of the vehicle's speed will be wrong, resulting in the failure of the vehicle's speed measurement, and there is a problem of underreporting, which affects driving safety. Summary of the invention

[0003] In view of this, the present invention provides a vehicle stall determination method based on lane change assist radar, which effectively solves the problem of lane change assist radar speed measurement failure caused by bad weather or conditions in adjacent lanes that affect radar detection of ground targets.

[0004] To achieve the above object, the present invention provides a vehicle stall determination method based on lane change auxiliary radar, comprising the following steps:

[0005] S1. Establish a vehicle speed sliding window array, where the vehicle speed sliding window array can store N elements;

[0006] S2, measure the vehicle speed in each frame time, detect the stationary targets around the vehicle through the vehicle-mounted radar, and reversely calculate the movement speed of the vehicle when it is driving normally. When the speed sliding window array is not full of N elements, the speed Save it to the vehicle speed sliding window array, and continue to execute step S2; after the vehicle speed sliding window array is full of N elements, execute step S3;

[0007] S3, using the extreme value calculation method to obtain the average speed in the speed sliding window array ;

[0008] S4, calculate the speed of the next frame And the average speed of the speed sliding window array Compare;

[0009] If the next frame speed The average speed of the speed sliding window array The difference is less than the preset threshold, and the next frame speed Save to the vehicle speed sliding window array and repeat step 4;

[0010] If the next frame speed The average speed of the speed sliding window array The difference is greater than the preset threshold, triggering the stall process and executing step 5;

[0011] S5: Discard the next frame of vehicle speed , using the average vehicle speed As the vehicle speed, maintain the target alarm logic;

[0012] S6: Detect stationary targets around the vehicle through the vehicle-mounted radar, and recalculate and infer the speed of the next frame ;

[0013] S7, recalculate the next frame speed The average speed of the speed sliding window array Compare;

[0014] If the next frame speed The average speed of the speed sliding window array The difference is less than the preset threshold, and the next frame speed Save to the vehicle speed sliding window array, repeat the process from step 2 to step 7, and implement continuous vehicle speed monitoring and stall determination;

[0015] If the next frame speed The average speed of the speed sliding window array The difference is greater than the preset threshold, triggering the stall process and executing step 5.

[0016] Preferably, the preset threshold can be adjusted according to the actual scenario, and the preset threshold can be dynamically adjusted according to vehicle speed, road conditions, weather and historical data.

[0017] Preferably, the vehicle-mounted camera is used to identify lane lines and road signs, and the vehicle speed is calculated in combination with the vehicle-mounted radar data.

[0018] Compared with the prior art, the beneficial effect of the present invention is that the vehicle stall judgment method based on lane change assist radar provided by the present invention can maintain normal alarm in specific scenarios: severe weather conditions such as rain and snow, the presence of long trailers or smooth concrete guardrails in adjacent lanes, and the failure of lane change assist radar speed measurement, thereby effectively avoiding the problem of underreporting and improving driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG1 is a flow chart of the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0021] When a vehicle is driving in heavy rain, visibility is reduced and radar detection distance is shortened, making it difficult to obtain sufficient ground information for speed measurement. In order to solve the problem of missed reports due to speed measurement failure of the speed change auxiliary radar in heavy rain or when there are trailers or smooth concrete guardrails in adjacent lanes, and to improve driving safety, the present invention provides the following technical solutions: A vehicle stall determination method based on lane change auxiliary radar, comprising the following steps:

[0022] S1. Establish a vehicle speed sliding window array, which can store N elements;

[0023] The sliding window size determines the amount of data involved in the mean calculation. A larger sliding window can improve the smoothness of the result, but will reduce the response speed to emergencies; a smaller sliding window will do the opposite. Therefore, it is necessary to select a suitable sliding window size according to the actual application scenario. In this embodiment, the sliding window array size is set to 10;

[0024] S2. Measure the vehicle speed in each frame, use the on-board camera to identify lane lines and road signs, and combine the on-board radar to detect stationary targets around the vehicle to infer the vehicle's normal speed. In the case of emergency braking, the maximum deceleration of an ordinary car is generally 7.5~8m / s 2 , the rate of change within the radar frame period of 100ms is about 0.8m / s;

[0025] When the speed sliding window array does not store 10 elements, the speed Save it to the vehicle speed sliding window array, and continue to execute step S2; after the vehicle speed sliding window array is full of 10 elements, execute step S3;

[0026] S3, using the extreme value calculation method to obtain the average speed in the speed sliding window array ;

[0027] In this embodiment, the method of removing the maximum and minimum values ​​is used to calculate the average vehicle speed. :

[0028] First, sort the vehicle speeds stored in the vehicle speed sliding window array from small to large;

[0029] Remove the first value (minimum value) and the last value (maximum value) after sorting;

[0030] Calculate the average value of the remaining vehicle speed using the formula:

[0031] ;

[0032] Where N represents the number of vehicle speeds stored in the sliding window array. represents the speed of the i-th vehicle after sorting;

[0033] S4, calculate the speed of the next frame And the average speed of the speed sliding window array Compare;

[0034] If the next frame speed The average speed of the speed sliding window array The difference is less than the preset threshold. In this embodiment, the preset threshold is 3, that is: , the next frame speed Save to the vehicle speed sliding window array and repeat step 4;

[0035] If the next frame speed The average speed of the speed sliding window array The difference is greater than the preset threshold, that is: , trigger stall processing, and execute step 5;

[0036] The preset threshold can be adjusted according to the actual scenario, and dynamically adjusted according to vehicle speed, road conditions, weather and historical data. The threshold can be appropriately lowered for complex road conditions, severe rain and snow conditions, and when the vehicle is in sudden acceleration or sudden braking. The threshold also needs to be lowered for scenarios where stalling often occurs according to historical data.

[0037] S5: Discard the next frame of vehicle speed , using the average vehicle speed As the vehicle speed, maintain the target alarm logic;

[0038] S6: Detect stationary targets around the vehicle through the vehicle-mounted radar, and recalculate and infer the speed of the next frame ;

[0039] S7, recalculate the next frame speed The average speed of the speed sliding window array Compare;

[0040] If the next frame speed The average speed of the speed sliding window array The difference is less than the preset threshold. In this embodiment, the preset threshold is 2, that is: , the next frame speed Save to the vehicle speed sliding window array, repeat the process from step 2 to step 7, and implement continuous vehicle speed monitoring and stall determination;

[0041] If the next frame speed The average speed of the speed sliding window array The difference is greater than the preset threshold, that is: , trigger stall processing and execute step 5.

[0042] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A vehicle stall identification method based on lane change auxiliary radar, characterized in that: The following steps are involved: S1. Establish a vehicle speed sliding window array, where the vehicle speed sliding window array can store N elements; S2, measure the vehicle speed in each frame time, detect the stationary targets around the vehicle through the vehicle-mounted radar, and reversely calculate the movement speed of the vehicle when it is driving normally. When the speed sliding window array is not full of N elements, the speed Save it to the vehicle speed sliding window array, and continue to execute step S2; after the vehicle speed sliding window array is full of N elements, execute step S3; S3, using the extreme value calculation method to obtain the average speed in the speed sliding window array ; S4, calculate the speed of the next frame And the average speed of the speed sliding window array Compare; If the next frame speed The average speed of the speed sliding window array The difference is less than the preset threshold, and the next frame speed Save to the vehicle speed sliding window array and repeat step 4; If the next frame speed The average speed of the speed sliding window array The difference is greater than the preset threshold, triggering the stall process and executing step 5; S5: Discard the next frame of vehicle speed , using the average vehicle speed As the vehicle speed, maintain the target alarm logic; S6: Detect stationary targets around the vehicle through the vehicle-mounted radar, and recalculate and infer the speed of the next frame ; S7, recalculated vehicle speed for the next frame The average speed of the speed sliding window array Compare; If the next frame speed The average speed of the speed sliding window array The difference is less than the preset threshold, and the next frame speed Save to the vehicle speed sliding window array, repeat the process from step 2 to step 7, and implement continuous vehicle speed monitoring and stall determination; If the next frame speed The average speed of the speed sliding window array The difference is greater than the preset threshold, triggering the stall process and executing step 5.

2. The vehicle stall determination method based on lane change auxiliary radar according to claim 1, characterized in that: The preset threshold can be adjusted according to the actual scenario, and the preset threshold can be dynamically adjusted according to vehicle speed, road conditions, weather and historical data.

3. The vehicle stall determination method based on lane change auxiliary radar according to claim 1, characterized in that: The on-board camera is used to identify lane lines and road signs, and the vehicle speed is calculated in combination with the on-board radar data.

Images