A method for improving brake triggering sensitivity based on light signals of a front vehicle, an electronic device and a computer readable storage medium

Abstract

The application discloses a method for improving brake triggering sensitivity based on front vehicle light signal, an electronic device and a computer readable storage medium. If the front-view camera of the vehicle cannot completely identify the target vehicle image, and the target vehicle existence value is lower than the set threshold, the target vehicle light signal is collected. If there is a light signal, the target vehicle existence value is increased by a constant for correction. The target vehicle existence value is corrected and improved through the target vehicle light signal, so that the target vehicle existence value has a greater probability of being greater than the system set threshold, and the target vehicle signal is not easy to be lost, thereby improving the brake triggering sensitivity. The application can improve the brake triggering sensitivity in the near-distance following environment, so as to ensure the accuracy and continuity of the system in identifying the front vehicle target when following the front vehicle at a near distance.

Description

TECHNICAL FIELD

[0001] The present application relates to the improvement of vehicle braking technology, more particularly to a method for improving braking triggering sensitivity based on front vehicle light signal, belonging to the field of low-speed auxiliary driving. BACKGROUND

[0002] In the driving assistance system, the automatic emergency braking function can perform emergency braking according to the relative relationship between the vehicle and the obstacle to avoid collision. This function needs to be able to accurately identify the front vehicle to make a judgment. In most congestion environments, the distance between the host vehicle and the front vehicle is very close, and the front camera (FC) cannot see the complete image of the front vehicle within its field of view, resulting in a decrease in the existence value of the front vehicle in the front vehicle target signal output by the front camera (FC). If the existence value of the front vehicle decreases below the recognition threshold of the host vehicle assistance system, the system may fail to trigger the automatic emergency braking function at the correct time due to recognition problems. At present, this problem is generally solved by perception fusion technology, which comprehensively judges the input signals of the front-view camera (FC) and millimeter-wave radar and other sensors. When the existence value of the front camera (FC) is reduced due to too close distance and too narrow field of view, the system relies more on the feedback signal of the millimeter-wave radar for judgment. However, the working principle of the millimeter-wave radar determines that its recognition effect is subject to the Doppler effect caused by the change in longitudinal distance. In the congestion environment, the recognition rate of the millimeter-wave radar is still very low when following closely. Ultimately, the system output of the front vehicle tracking target is discontinuous, the ID number abnormally jumps, and in extreme cases, the braking function of the host vehicle cannot be started in time when the front vehicle brakes. SUMMARY

[0003] In view of the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a method for improving braking triggering sensitivity based on front vehicle light signal. The present application can improve the braking triggering sensitivity in the environment of close following to ensure the accuracy and continuity of the system in identifying the front vehicle target when following closely.

[0004] The technical solution of the present application is as follows:

[0005] A method for improving braking triggering sensitivity based on front vehicle light signal, which corrects and improves the existence value of the target vehicle through the target vehicle light signal, so that the existence value of the target vehicle has a greater probability of being greater than the threshold set by the system, and the target vehicle signal is not easy to be lost, thereby improving the braking triggering sensitivity.

[0006] Specifically, the correction and improvement of the existence value of the target vehicle is carried out according to the following steps,

[0007] 1) The front-view camera of the host vehicle captures the closest vehicle in front of the host vehicle lane as the target vehicle, and inputs the target vehicle information to the automatic driving system; the target vehicle information includes target classification, ID number, and existence value;

[0008] 2) If the front-view camera of the host vehicle cannot completely identify the image of the target vehicle, step 3) is performed, otherwise the target vehicle existence value remains unchanged;

[0009] 3) It is judged whether the target vehicle existence value is lower than a set threshold E, if yes, step 4) is performed, otherwise the target vehicle existence value remains unchanged;

[0010] 4) The light signal of the target vehicle is collected; if the preceding vehicle has no light signal, the target vehicle existence value remains unchanged, otherwise step 5) is performed;

[0011] 5) The target vehicle existence value N is increased by a constant C for correction, and the corrected target vehicle existence value is M, i.e. M = N + C.

[0012] The target vehicle is determined by the following method,

[0013] A, the overall discrete trajectory of the host vehicle is determined, the overall discrete trajectory of the host vehicle includes the historical discrete trajectory of the host vehicle and the predicted discrete trajectory of the host vehicle, and the historical discrete trajectory and the predicted discrete trajectory of the host vehicle are the positions of the host vehicle corresponding to each time period in a plurality of continuous time periods;

[0014] B, the first vehicle in front of the predicted discrete trajectory of the host vehicle is determined according to the historical discrete trajectory of the host vehicle, which is the target vehicle.

[0015] When braking, the braking control is performed based on the predicted discrete trajectory of the host vehicle and the predicted discrete trajectory of the target vehicle and in combination with the host vehicle and target vehicle information including the corrected target vehicle existence value.

[0016] The application also provides an electronic device for implementing the method for improving the braking trigger sensitivity based on the light signal of the preceding vehicle, which comprises a memory configured to store executable instructions;

[0017] A processor configured to execute the executable instructions stored in the memory to implement the foregoing method for improving the braking trigger sensitivity based on the light signal of the preceding vehicle.

[0018] The application also simultaneously provides a computer readable storage medium having computer program instructions stored thereon, and the computer program instructions execute the method for improving the braking trigger sensitivity based on the light signal of the preceding vehicle.

[0019] Compared with the prior art, the application has the following beneficial effects:

[0020] 1、The present application is improved by the existence value of the front vehicle, and the existence value after the improvement is more likely to be greater than the threshold value of the system set judging target type, so that the front vehicle signal is not easy to lose. In the near distance following environment, the braking trigger sensitivity can be improved to ensure the accuracy and continuity of the system in identifying the front vehicle target in the near distance following.

[0021] 2、The front vehicle light signal can be used as a reliable basis for objects that cannot be seen in the front image, so as to further modify the existence value, which will not affect the identification of the front object, and the braking trigger is more sensitive and reliable.

[0022] 3、In normal driving, the biggest collision risk often comes from the front, and the closest vehicle in front is used as the target vehicle in the present application, and the light signal of the rear of the target vehicle is not blocked, so it is better to identify, and therefore the method is simple and easy to implement. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The application diagram of the present application is shown in the figure - the distance between the vehicle and the front vehicle is far.

[0024] Figure 2 The application diagram of the present application is shown in the figure - the distance between the vehicle and the front vehicle is close.

[0025] Figure 3 The flow chart of the present application is shown in the figure. DETAILED DESCRIPTION

[0026] The specific embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0027] The method for improving the braking trigger sensitivity based on the front vehicle light signal is to modify and improve the existence value of the target vehicle through the light signal of the target vehicle (including the brake and lighting light signal), so that the existence value of the target vehicle is more likely to be greater than the threshold value set by the system, so that the target vehicle signal is not easy to lose, thereby improving the braking trigger sensitivity. In addition to the modification of the existence value, the rest of the braking strategy is the same as the prior art.

[0028] The modified and improved target vehicle existence value is performed according to the following steps,

[0029] 1) The front view camera of the vehicle captures the nearest vehicle in front of the lane as the target vehicle, and inputs the target vehicle information to the automatic driving system; the target vehicle information includes target classification, ID number and existence value;

[0030] 2) If the target vehicle image cannot be completely identified by the front view camera of the vehicle, step 3) is executed, otherwise the existence value of the target vehicle remains unchanged;

[0031] 3) judge whether the target vehicle existence value is lower than the set threshold E, if yes, execute step 4), otherwise the target vehicle existence value remains unchanged;

[0032] 4) collect the target vehicle light signal; if the preceding vehicle has no light signal, the target vehicle existence value remains unchanged, otherwise execute step 5);

[0033] 5) increase the target vehicle existence value N by a constant C for correction, and the corrected target vehicle existence value is M, i.e. M = N + C.

[0034] The front camera (FC) of the host vehicle captures the first vehicle in front of the host lane, and inputs the front vehicle target information to the automatic driving system. The information includes target classification, ID number, existence value, etc., and continuously tracks and predicts the target trajectory. The "existence value" of the preceding vehicle (i.e. the target vehicle) at this time is set as N1, and the system judges the threshold value of the preceding vehicle existence as E, and at this time N1>E. As the target continues to approach, the front camera (FC) cannot see the complete image of the preceding vehicle within its field of view, resulting in the "existence value" of the preceding vehicle target information in the target signal output by the front camera (FC) being reduced to N2. At this time, if the value is lower than the set threshold, i.e. N2<E, the system will lose the target. Therefore, when the "existence value" of the preceding vehicle is reduced (N2

[0035] The target vehicle is determined by the following method,

[0036] A, determine the overall discrete trajectory of the host vehicle, which includes the historical discrete trajectory and the predicted discrete trajectory of the host vehicle. The historical discrete trajectory and the predicted discrete trajectory of the host vehicle are the positions of the host vehicle corresponding to each time period in a plurality of continuous time periods; the discrete trajectory of the target vehicle is defined in the same way as the host vehicle.

[0037] B, according to the historical discrete trajectory of the host vehicle, determine the predicted discrete trajectory of the host vehicle and the first vehicle in front of it, which is the target vehicle.

[0038] Input the front vehicle information, including vehicle ID, vehicle type, vehicle existence value, and calculate the distance D between the host vehicle and the preceding vehicle and the width S of the preceding vehicle.

[0039] When the distance between the host vehicle and the preceding vehicle is too close, the front camera of the host vehicle cannot see the complete image of the preceding vehicle, and the existence value is lower than the set threshold, the automatic driving brake sensitivity function of the host vehicle is started. In each time period, the headlight signal of the preceding vehicle is extracted for comparison. If the preceding vehicle has a headlight signal output, the target vehicle existence value is increased, the preceding vehicle ID is not lost, and the automatic driving brake sensitivity requirement is met. When the distance between the host vehicle and the preceding vehicle increases, the front camera of the host vehicle can completely identify the image of the preceding vehicle, the existence value of the preceding vehicle is increased, and the automatic driving brake sensitivity function of the host vehicle is closed.

[0040] The application will be described in detail below with reference to the accompanying drawings.

[0041] The main purpose of the application is to adjust the existence value of the preceding vehicle to prevent the target from being lost. The threshold of the existence value of the target vehicle is set to E, the actual recognition existence value of the target vehicle is N, and the input recognition existence value of the target vehicle in each time period is defined as N1, N2, N3, …, N100, N101, ….

[0042] Please refer to Figure 1 At this time, the distance between the host vehicle and the preceding vehicle is far, and the front camera of the host vehicle can completely identify the image of the target vehicle. Figure 1 The follow-up method provided by the embodiment of the application is shown, which involves a host vehicle 100, a front camera 110 on the host vehicle, a preceding vehicle 200 at the closest distance in the front direction of the host vehicle, and a tail light 210 of the preceding vehicle.

[0043] The distance between the host vehicle 100 and the preceding vehicle 200 is D. The value of D in each time period is D1, D2, D3, …, D100, D101, ….

[0044] The tail light signal determination value of the preceding vehicle 200 is L, and the tail light of the preceding vehicle 200 has a signal output, L=1; when the tail light signal of the preceding vehicle 200 is not output, L=0.

[0045] The width of the preceding vehicle is S. When the distance between the host vehicle 100 and the preceding vehicle 200 is far, the image of the preceding vehicle 200 can be completely in the range of the front camera 110 of the host vehicle, and the front camera 110 can lock the existence of the preceding vehicle, and the output existence value N1 of the preceding vehicle 200 is greater than E.

[0046] Please refer to Figure 2, the car and the car distance is close, the car front camera can not be identified to the target vehicle image. When the car 100 and the car 200 distance shortens, the car 200 image exceeds the car front camera 110 visual angle range, the front camera 110 cannot lock the front car exists, its output front car 200 exists value N2 < E. At this time, the automatic driving system promotes the brake sensitivity function to start, and each time period will determine the front car tail light 210 signal L value.

[0047] When the front car tail light 210 signal L = 1, the automatic driving system will add a constant C to the existence value N of the front car 200. That is, the modified N2' = N2 + C. At this time, N2' > E, the system maintains the identification of the existence of the front car 200, and the classification information, ID number continues to remain unchanged.

[0048] At the same time, please refer to Figure 3 , the flowchart of the present application.

[0049] The present application corrects the target vehicle light signal to improve the existence value of the target vehicle, so that the existence value of the target vehicle has a greater probability of being greater than the threshold value set by the system, so that the target vehicle signal is not easy to lose, thereby improving the brake trigger sensitivity.

[0050] Finally, it should be noted that the above examples of the present application are only examples for illustrating the present application, and are not limited to the embodiments of the present application. Although the applicant has made a detailed description of the present application with reference to the preferred embodiments, those skilled in the art can make other different forms of changes and variations on the basis of the above description. Here, all the embodiments cannot be exhausted. Any obvious changes or variations derived from the technical solutions of the present application are still within the protection scope of the present application.

Claims

1. A method for improving brake triggering sensitivity based on light signals of a preceding vehicle, characterized in that: The target vehicle existence value is modified by the target vehicle light signal, so that the target vehicle existence value has a greater probability of being greater than the threshold set by the system, the target vehicle signal is not easy to be lost, and the brake triggering sensitivity is improved; The modification of the target vehicle existence value is performed according to the following steps, 1) The front-looking camera of the host vehicle captures the nearest vehicle in front of the host vehicle lane as a target vehicle, and inputs target vehicle information to the automatic driving system; the target vehicle information includes target classification, ID number, and existence value; 2) If the front-looking camera of the host vehicle cannot completely identify the target vehicle image, step 3) is performed, otherwise the target vehicle existence value remains unchanged; 3) It is judged whether the target vehicle existence value is lower than the set threshold E, if yes, step 4) is performed, otherwise the target vehicle existence value remains unchanged; 4) The target vehicle light signal is collected; if the preceding vehicle has no light signal, the target vehicle existence value remains unchanged, otherwise step 5) is performed; 5) The target vehicle existence value N is increased by a constant C for modification, and the modified target vehicle existence value is M, i.e. M = N + C.

2. The method for improving the sensitivity of triggering the brake based on the light signal of the front vehicle according to claim 1, characterized in that: The constant C is less than the set threshold E.

3. The method of claim 1, wherein the method comprises: The target vehicle is determined according to the following method, A, determine the overall discrete trajectory of the host vehicle, the overall discrete trajectory of the host vehicle includes the historical discrete trajectory and the predicted discrete trajectory of the host vehicle, and the historical discrete trajectory and the predicted discrete trajectory of the host vehicle include the position of the host vehicle corresponding to each time period in a plurality of continuous time periods; B, according to the historical discrete trajectory of the host vehicle, the first vehicle in front of the predicted discrete trajectory of the host vehicle is determined, which is the target vehicle.

4. The method of claim 1, wherein the method comprises: During braking, the brake control is performed based on the predicted discrete trajectory of the host vehicle and the predicted discrete trajectory of the target vehicle, and combined with the host vehicle and target vehicle information including the modified target vehicle existence value.

5. An electronic device implementing a method of improving brake trigger sensitivity based on a preceding vehicle headlight signal, the method comprising: receiving a signal from a headlight sensor; determining a headlight state of the preceding vehicle based on the signal; and adjusting a brake trigger sensitivity based on the headlight state. The memory is configured to store executable instructions; The processor is configured to execute the executable instructions stored in the memory to implement the method for improving brake triggering sensitivity based on the light signal of the preceding vehicle according to any one of claims 1 to 4.

6. A computer readable storage medium having stored thereon computer program instructions, characterized in that: The computer program instructions perform the method for improving brake triggering sensitivity based on the light signal of the preceding vehicle according to any one of claims 1 to 4.

Images