Fusion obstacle confidence determination method, system, device and storage medium

Abstract

The application discloses a kind of fusion obstacle confidence determination method, system, equipment and storage medium, the method includes: by the camera and radar in current driving vehicle built-in respectively camera perception information and radar perception information are obtained;According to camera perception information and radar perception information determine the perception information of fusion obstacle;According to the perception information of fusion obstacle, determine fusion obstacle existence mark number, fusion obstacle match success number and fusion obstacle match mark number;According to fusion obstacle match success number, fusion obstacle existence mark number and fusion obstacle match mark number determine the confidence of fusion obstacle.Compared with the error of camera or radar data in prior art, direct fusion confidence can cause error transmission, and the application adjusts fusion confidence dynamically by obstacle match success number, obstacle existence mark number and obstacle match mark number, to realize real-time acquisition accurate fusion obstacle confidence.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving perception, and in particular to a confidence determination method, system and device for fused obstacles and a storage medium. BACKGROUND

[0002] The confidence method for directly fusing obstacles using cameras and radars has the advantages of comprehensively utilizing multi-sensor information and improving reliability and decision accuracy, but the data of cameras and radars may have certain inconsistencies, direct fusion of confidence may ignore the differences between sensors, leading to information distortion; if there is an error in the camera or radar data, direct fusion of confidence may cause error propagation, thereby affecting the decision accuracy of the system. Therefore, how to obtain accurate fusion obstacle confidence in real time has become a problem to be solved.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a confidence determination method, system, device and storage medium for fused obstacles, aiming to solve the technical problem of how to obtain accurate fusion obstacle confidence in real time.

[0005] To achieve the above-mentioned purpose, the present application provides a confidence determination method for fused obstacles, which comprises:

[0006] acquiring camera perception information and radar perception information by the cameras and radars built-in in the current driving vehicle respectively;

[0007] determining the perception information of the fused obstacles according to the camera perception information and the radar perception information;

[0008] determining the number of existence marks of the fused obstacles, the number of successful matches of the fused obstacles and the number of match marks of the fused obstacles according to the perception information of the fused obstacles;

[0009] determining the confidence of the fused obstacles according to the number of successful matches of the fused obstacles, the number of existence marks of the fused obstacles and the number of match marks of the fused obstacles.

[0010] Optionally, the step of determining the number of existence marks of the fused obstacles according to the perception information of the fused obstacles comprises:

[0011] if there is camera obstacle information and radar obstacle information in the perception information of the fused obstacles, determining the fused obstacle information according to the camera obstacle information and the radar obstacle information;

[0012] determining a number of times of obstacle recognition of the fusion obstacle information;

[0013] determining a number of times of fusion obstacle existence marking according to the number of times of obstacle recognition.

[0014] Optionally, the step of determining the number of times of fusion obstacle matching success and the number of times of fusion obstacle matching marking according to the perception information of the fusion obstacle comprises:

[0015] determining previous frame obstacle position information and current frame obstacle position information according to the perception information of the fusion obstacle;

[0016] determining an obstacle position difference value according to the previous frame obstacle position information and the current frame obstacle position information;

[0017] when the obstacle position difference value is less than or equal to a preset difference value, determining fusion obstacle matching success, determining the number of times of fusion obstacle matching success, and taking the number of times of fusion obstacle existence marking as the number of times of fusion obstacle matching marking.

[0018] Optionally, the step of determining the confidence of the fusion obstacle according to the number of times of fusion obstacle matching success, the number of times of fusion obstacle existence marking and the number of times of fusion obstacle matching marking comprises:

[0019] determining a confidence calculation rule according to the number of times of fusion obstacle matching success;

[0020] determining a pending confidence of the fusion obstacle based on the confidence calculation rule;

[0021] determining a marking difference value between the number of times of fusion obstacle existence marking and the number of times of fusion obstacle matching marking;

[0022] if the marking difference value is less than or equal to the preset threshold value, taking the pending confidence as the confidence of the fusion obstacle.

[0023] Optionally, after the step of determining the marking difference value between the number of times of fusion obstacle existence marking and the number of times of fusion obstacle matching marking, the method further comprises:

[0024] when the marking difference value is greater than the preset threshold value, setting the pending confidence to 0.

[0025] Optionally, after the step of determining the perception information of the fusion obstacle according to the camera perception information and the radar perception information, the method further comprises:

[0026] if the fusion obstacle information contains camera obstacle information and does not contain radar obstacle information, determining a position distance between the fusion obstacle and the current driving vehicle according to the camera obstacle information;

[0027] determining a confidence selection rule according to the position distance, and determining a pending confidence of the fusion obstacle according to the confidence selection rule;

[0028] updating the pending confidence of the fusion obstacle based on a fusion obstacle existence marking number, a fusion obstacle matching success number and a fusion obstacle matching marking number;

[0029] taking the updated pending confidence of the fusion obstacle as the confidence of the fusion obstacle.

[0030] Optionally, after the step of determining the fusion obstacle information according to the camera perception information and the radar perception information, the method further comprises:

[0031] if the fusion obstacle information contains radar obstacle information and does not contain camera obstacle information, determining speed information of the fusion obstacle according to the radar obstacle information;

[0032] determining a confidence calculation strategy according to the speed information of the fusion obstacle;

[0033] determining the confidence of the fusion obstacle based on the confidence calculation strategy.

[0034] In addition, to achieve the above object, the application further provides a fusion obstacle confidence determination system, which comprises:

[0035] an acquisition module, configured to acquire camera perception information and radar perception information through a camera and a radar built in a current driving vehicle respectively;

[0036] a fusion module, configured to determine fusion obstacle information according to the camera perception information and the radar perception information;

[0037] a calculation module, configured to determine a fusion obstacle existence marking number, a fusion obstacle matching success number and a fusion obstacle matching marking number according to the fusion obstacle information;

[0038] a determination module, configured to determine a confidence of the fusion obstacle according to the fusion obstacle matching success number, the fusion obstacle existence marking number and the fusion obstacle matching marking number.

[0039] In addition, to achieve the above object, the application further provides a confidence determination device for fusion obstacles, comprising a memory, a processor and a confidence determination program for fusion obstacles stored on the memory and executable on the processor, the confidence determination program for fusion obstacles being configured to implement the steps of the confidence determination method for fusion obstacles as described above.

[0040] In addition, to achieve the above object, the application further provides a storage medium having a confidence determination program for fusion obstacles stored thereon, the confidence determination program for fusion obstacles being executable by a processor to implement the steps of the confidence determination method for fusion obstacles as described above.

[0041] Firstly, the application acquires camera perception information and radar perception information through the camera and radar built in the current driving vehicle respectively, then determines fusion obstacle perception information according to the camera perception information and the radar perception information, thereafter determines fusion obstacle existence marking times, fusion obstacle matching successful times and fusion obstacle matching marking times according to the fusion obstacle perception information, and finally determines the confidence of the fusion obstacle according to the fusion obstacle matching successful times, the fusion obstacle existence marking times and the fusion obstacle matching marking times. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 is a structural schematic diagram of the confidence determination device for fusion obstacles of the hardware running environment involved in the embodiment scheme of the application;

[0043] Figure 2 is a flowchart of the confidence determination method for fusion obstacles of the first embodiment of the application;

[0044] Figure 3 is a confidence calculation flowchart of the confidence determination method for fusion obstacles of the first embodiment of the application;

[0045] Figure 4 is a structural block diagram of the confidence determination system for fusion obstacles of the first embodiment of the application.

[0046] The implementation of the object of the application, functional features and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

[0048] Referring to Figure 1 , Figure 1 The confidence determination device structure diagram of the fusion obstacle involved in the embodiment of the present application is shown.

[0049] As Figure 1 shown, the confidence determination device of the fusion obstacle can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between the components. The user interface 1003 can include a display screen, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM), and can also be a stable non-volatile memory (NVM), such as a disk memory. The memory 1005 can also be an independent storage system from the aforementioned processor 1001.

[0050] Those skilled in the art can understand that the structure shown in Figure 1 does not constitute a limitation on the confidence determination device of the fusion obstacle, and can include more or fewer components than the diagram, or combine certain components, or different component arrangements.

[0051] As Figure 1 shown, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and a fusion obstacle confidence determination program.

[0052] In Figure 1In the confidence determination device of the fusion obstacle shown, the network interface 1004 is mainly used for data communication with the network server, and the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the confidence determination device of the fusion obstacle can be arranged in the confidence determination device of the fusion obstacle, and the confidence determination device of the fusion obstacle calls the confidence determination program of the fusion obstacle stored in the memory 1005 through the processor 1001, and executes the confidence determination method of the fusion obstacle provided in the embodiment of the application.

[0053] The embodiment of the application provides a confidence determination method of a fusion obstacle. Figure 2 , Figure 2 The confidence determination method of the fusion obstacle provided in the embodiment of the application is shown in the flowchart of the first embodiment.

[0054] In the embodiment, the confidence determination method of the fusion obstacle comprises the following steps:

[0055] Step S10: Obtain camera perception information and radar perception information through a camera and a radar built in a current driving vehicle respectively.

[0056] It is easy to understand that the execution subject of the embodiment can be a confidence determination system of a fusion obstacle with functions of data processing, network communication and program running, and can also be other computer devices with similar functions, and the embodiment is not limited thereto.

[0057] It should be noted that the camera perception information is surrounding environment perception information collected by a camera in real time according to a set time period during driving of the current driving vehicle, and the radar perception information is surrounding environment perception information collected by a radar in real time according to a set time period during driving of the current driving vehicle.

[0058] The camera perception information can exist or not exist obstacle information, and the radar perception information can exist or not exist obstacle information.

[0059] In the implementation, the confidence determination method of the fusion obstacle provided in the embodiment of the application is shown in the flowchart of the confidence determination method of the fusion obstacle. Figure 3 , Figure 3 The confidence determination method of the fusion obstacle provided in the embodiment of the application is shown in the flowchart of the confidence determination method of the fusion obstacle.

[0060] Step S20: determining the fusion obstacle perception information according to the camera perception information and the radar perception information.

[0061] In this embodiment, the camera perception information and the radar perception information need to be information fused to obtain the fusion obstacle perception information.

[0062] The fusion obstacle perception information can only include the camera obstacle information, can only include the radar obstacle information, or can include both the camera obstacle information and the radar obstacle information.

[0063] The camera obstacle information is the obstacle information obtained by the forward-looking integrated machine, and the radar obstacle information is the obstacle information obtained by the radar. The obstacle information is the valid sensor data of the obstacle obj, which includes the distance range, the angle angle, the longitudinal velocity v_x, etc.

[0064] Step S30: determining the fusion obstacle existence marking number of times, the fusion obstacle matching successful number of times, and the fusion obstacle matching marking number of times according to the fusion obstacle perception information.

[0065] Further, if the fusion obstacle perception information includes the camera obstacle information and the radar obstacle information, the fusion obstacle information is determined according to the camera obstacle information and the radar obstacle information; the obstacle recognition number of times of the fusion obstacle information is determined; the fusion obstacle existence marking number of times is determined according to the obstacle recognition number of times; the previous frame obstacle position information and the current frame obstacle position information are determined according to the fusion obstacle perception information; the obstacle position difference value is determined according to the previous frame obstacle position information and the current frame obstacle position information; when the obstacle position difference value is less than or equal to a preset difference value, it is determined that the fusion obstacle matching is successful, the fusion obstacle matching successful number of times is determined, and the fusion obstacle existence marking number of times is taken as the fusion obstacle matching marking number of times.

[0066] It should be noted that the obstacle recognition number of times of the fusion obstacle information is obtained by setting a fusion time period to fuse the camera obstacle information and the radar obstacle information in the same time period.

[0067] Since the data acquisition time period of the camera is inconsistent with the data acquisition time period of the radar, the fusion obstacle information is the obstacle information obtained by time unification of the camera obstacle information and the radar obstacle information. Assuming that the data acquisition time period of the camera is 2s and the data acquisition time period of the radar is 4s, that is, the camera collects twice and the radar collects once. In order to enable the camera and the radar data to be fused, the data collected by the camera for 4s (i.e. the data collected by the camera for the second time) and the data collected by the radar for the first time need to be fused as the fusion obstacle information.

[0068] The number of obstacle recognitions is the number of times the camera and radar simultaneously detect the same obstacle. At the same time, the first time the camera and radar simultaneously detect the same obstacle, the fused obstacle obj needs to be recorded in the tracking obstacle list, and the number of times the fused obstacle obj exists (that is, the number of times the fused obstacle exists mark) is updated in real time in the tracking obstacle list.

[0069] It should be noted that the number of obstacle recognitions can be used as the duration of the fused obstacle presence mark.

[0070] It should be understood that the matching tag age is the duration value saved when the fused obstacle obj data is updated. When the fused obstacle obj data has not been updated, the existence time duration will continue to increase, but the matching tag age will remain unchanged.

[0071] In the specific implementation, if the camera and radar detect an obstacle at the same time, the obstacle needs to be written into the tracking obstacle list. At this time, the number of fused obstacle presence marks is 1. Since the obstacle cannot be matched, the current number of fused obstacle matching successes is 0, and the number of fused obstacle matching marks is 0. After a time period, the number of fused obstacle presence marks is 2. If the obstacle position difference is determined based on the obstacle position information of the previous frame and the obstacle position information of the current frame, when the obstacle position difference is less than or equal to the preset difference, the obstacle detected in the current frame matches the obstacle detected in the previous frame, and the current number of fused obstacle matching successes is 1. , the number of fused obstacle matching marks is 2, etc.; the obstacle position difference is determined based on the obstacle position information of the previous frame and the obstacle position information of the current frame. If the obstacle position difference is greater than the preset difference, and the obstacle detected in the current frame matches the obstacle detected in the previous frame, the fused obstacle matching fails. At this time, the number of fused obstacle existence marks is 3, the current number of fused obstacle matching successes is 1, and the number of fused obstacle matching marks is 2. According to the above method, when the difference between the existence time duration and the matching mark age is greater than the preset threshold (for example, 5 or 6), it means that the fused obstacle obj is unreliable and the confidence level becomes 0.

[0072] The preset difference value can be customized by the user, and this embodiment does not limit this.

[0073] Step S40: determining the confidence level of the fused obstacle according to the number of successful matching of the fused obstacle, the number of fused obstacle existence marks, and the number of fused obstacle matching marks.

[0074] Further, a confidence degree calculation rule is determined according to the number of successful matching of the fusion obstacle; a tentative confidence degree of the fusion obstacle is determined based on the confidence degree calculation rule; a marking difference value between the number of marking of the fusion obstacle and the number of matching marking of the fusion obstacle is determined; and if the marking difference value is less than or equal to a preset threshold, the tentative confidence degree is taken as the confidence degree of the fusion obstacle.

[0075] The confidence degree calculation rule is that when the number of successful matching of the fusion obstacle obj is less than a preset threshold (for example, 3), the confidence degree confidence is reduced by a confidence threshold (for example, 30); when the number of successful matching of the fusion obstacle obj is between the preset threshold range (for example, between 3 and 5), the confidence degree confidence is reduced by a confidence threshold (for example, 20); and when the number of successful matching of the fusion obstacle obj is greater than or equal to the preset threshold (for example, 5), the confidence degree confidence is unchanged.

[0076] In a specific implementation, the initial confidence degree confidence of the fusion obstacle obj is set to 100, and after the tentative confidence degree of the fusion obstacle is obtained through the above confidence degree calculation rule, the marking difference value between the number of marking of the fusion obstacle and the number of matching marking of the fusion obstacle needs to be calculated, and if the marking difference value is less than or equal to a preset threshold, the tentative confidence degree is taken as the confidence degree of the fusion obstacle; and if the marking difference value is greater than the preset threshold, the tentative confidence degree is set to 0.

[0077] It should be understood that the preset threshold is a user-defined setting, and the embodiment is not limited thereto, and can be 4 or 5, etc.

[0078] In the embodiment, it also needs to be noted that if the perception information of the fusion obstacle contains camera obstacle information and does not contain radar obstacle information, the position distance between the fusion obstacle and the current driving vehicle is determined according to the camera obstacle information; the confidence degree selection rule is determined according to the position distance, and the tentative confidence degree of the fusion obstacle is determined according to the confidence degree selection rule; the tentative confidence degree of the fusion obstacle is updated based on the number of marking of the fusion obstacle, the number of successful matching of the fusion obstacle and the number of matching marking of the fusion obstacle; and the updated tentative confidence degree of the fusion obstacle is taken as the confidence degree of the fusion obstacle.

[0079] It should be noted that the number of marking of the fusion obstacle is the number of times that the obstacle is detected by the front-view integrated machine. The calculation method of the number of successful matching of the fusion obstacle and the number of matching marking of the fusion obstacle can refer to the content related to the number of successful matching of the fusion obstacle and the number of matching marking of the fusion obstacle in step S30.

[0080] In a specific implementation, if the fusion obstacle obj only has perception data of the camera (single sensor fusion result), a confidence selection rule is set according to the distance range of the fusion obstacle obj from the ego vehicle, and the confidence selection rule is as follows: a. When the distance range is less than a preset distance threshold (for example, 30 m), the confidence is the maximum value between the current confidence and 50; b. When the distance range is greater than the preset distance threshold (for example, 30 m), the confidence is the maximum value between the current confidence and 80. Then, the confidence is further adjusted according to the matching number of the fusion obstacle obj: a. When the matching success number matched of the fusion obstacle obj is less than a preset threshold (for example, 3), the confidence confidence is reduced by a confidence threshold (for example, 30); b. When the matching success number matched of the fusion obstacle obj is between the preset threshold range (for example, between 3 and 5), the confidence confidence is reduced by a confidence threshold (for example, 20); c. When the matching success number matched of the fusion obstacle obj is greater than or equal to the preset threshold (for example, 20), the confidence confidence is increased by a confidence threshold (for example, 10), and it is checked whether the confidence confidence exceeds 90. If it exceeds, the confidence confidence is set to 90. Then, the confidence is calculated according to the existence time duration (i.e., the number of existence marks) of the fusion obstacle obj: when the difference between the existence time duration and the matching mark age is greater than a threshold 3, the confidence confidence becomes 0.

[0081] In the embodiment, it is also necessary to note that if the perception information of the fusion obstacle contains radar obstacle information and does not contain camera obstacle information, the speed information of the fusion obstacle is determined according to the radar obstacle information; the confidence calculation strategy is determined according to the speed information of the fusion obstacle; and the confidence of the fusion obstacle is determined based on the confidence calculation strategy.

[0082] In a specific implementation, whether the fusion obstacle is a low-speed obstacle or a high-speed obstacle is determined according to the speed information of the fusion obstacle: if the fusion obstacle obj is a low-speed obstacle (the longitudinal speed V_x is less than 15 km / h), the confidence calculation strategy is as follows: a. When the distance range of the fusion obstacle obj from the ego vehicle is less than 10 m and the angle angle with the vehicle is less than 30 degrees, the confidence confidence is the maximum value between the current confidence and 50; b. When the matching number matched of the fusion obstacle obj is less than 5, the confidence confidence is reduced by 20; c. When the difference between the existence time duration and the matching mark age is greater than a threshold 3, the confidence confidence becomes 0.

[0083] If the fusion obstacle obj is a high-speed obstacle (the longitudinal speed V_x is less than 15 km / h), the confidence calculation strategy is as follows: a. When the angle between the fusion obstacle obj and the ego vehicle angle is less than 30 degrees, the confidence confidence is the maximum value between the current confidence and 50; b. Further adjust the confidence according to the matching number of the fusion obstacle obj: i. When the matching number of the fusion obstacle obj is less than 3, the confidence confidence is reduced by 30. ii. When the matching number of the fusion obstacle obj is between 3 and 5, the confidence confidence is reduced by 20. iii. When the matching number of the fusion obstacle obj is greater than or equal to 20, the confidence confidence is increased by 10, and it is checked whether the confidence confidence exceeds 90, if it exceeds, the confidence confidence is set to 90; c. Calculate the confidence according to the existence time duration of the fusion obstacle obj: when the difference between the existence time duration and the matching label age is greater than the threshold value 5, the confidence confidence becomes 0.

[0084] In this embodiment, first, the camera and radar built-in in the current driving vehicle are used to obtain camera perception information and radar perception information respectively, then the perception information of the fusion obstacle is determined according to the camera perception information and the radar perception information, after that, the matching success number of the fusion obstacle, the existence label number of the fusion obstacle and the matching label number of the fusion obstacle are determined according to the perception information of the fusion obstacle, finally, the confidence of the fusion obstacle is determined according to the matching success number of the fusion obstacle, the existence label number of the fusion obstacle and the matching label number of the fusion obstacle. Compared with the inconsistency or error of the data of the camera and the radar in the prior art, the direct fusion confidence may ignore the difference between the sensors, leading to information distortion or error transmission, thereby affecting the final fusion obstacle confidence and affecting the automatic driving decision module. In this embodiment, through the calculation of the matching number and the existence time, the misjudgment caused by instantaneous error or interference can be reduced, the accuracy of the real state of the obstacle can be improved, real-time updating can be realized, and a certain flexibility can be realized. The state change of the obstacle can be reflected in time, the perception ability of the system is improved, thereby optimizing the decision and behavior of the system, and the stability and persistence of the obstacle can be more comprehensively evaluated, thereby optimizing the decision effect of the automatic driving system and improving the driving safety and efficiency.

[0085] Referring to Figure 4 , Figure 4 The structure block diagram of the first embodiment of the fusion obstacle confidence determination system of the present application.

[0086] AsFigure 4 As shown, the confidence determination system for fusion obstacles proposed in the embodiments of the present application comprises:

[0087] The acquisition module 4001 is configured to acquire camera perception information and radar perception information respectively through a camera and a radar built in a current driving vehicle.

[0088] The fusion module 4002 is configured to determine fusion obstacle perception information according to the camera perception information and the radar perception information.

[0089] The calculation module 4003 is configured to determine a fusion obstacle existence marking number, a fusion obstacle matching success number and a fusion obstacle matching marking number according to the fusion obstacle perception information.

[0090] The determination module 4004 is configured to determine the confidence of the fusion obstacle according to the fusion obstacle matching success number, the fusion obstacle existence marking number and the fusion obstacle matching marking number.

[0091] Other embodiments or specific implementations of the confidence determination system for fusion obstacles can refer to the above-mentioned method embodiments, which will not be described here.

[0092] It should be noted that in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or system. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or system including the element.

[0093] The above-mentioned embodiment numbers of the present application are only for description, not representing the advantages and disadvantages of the embodiments.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platform, of course, also can be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software product, which is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk), including a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method described in each embodiment of the present application.

[0095] The above merely describes the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application, and any equivalent structure or equivalent process conversion, or direct or indirect application in other related technical fields, which are made by using the content of the present application specification and drawings, are also included in the patent protection scope of the present application.

Claims

1. A method of determining a confidence of a fusion obstacle, characterized by, The confidence degree determination method of the fusion obstacle comprises the following steps: Camera perception information and radar perception information are respectively acquired by a camera and a radar built in a current driving vehicle; Fusion obstacle perception information is determined according to the camera perception information and the radar perception information; A fusion obstacle existing mark number, a fusion obstacle matching success number and a fusion obstacle matching mark number are determined according to the fusion obstacle perception information; The confidence degree of the fusion obstacle is determined according to the fusion obstacle matching success number, the fusion obstacle existing mark number and the fusion obstacle matching mark number; The step of determining the fusion obstacle matching success number and the fusion obstacle matching mark number according to the fusion obstacle perception information comprises: A previous frame obstacle position information and a current frame obstacle position information are determined according to the fusion obstacle perception information; An obstacle position difference value is determined according to the previous frame obstacle position information and the current frame obstacle position information; When the obstacle position difference value is less than or equal to a preset difference value, it is determined that the fusion obstacle matching is successful, the fusion obstacle matching success number is determined, and the fusion obstacle existing mark number is taken as the fusion obstacle matching mark number.

2. The method of claim 1, wherein, The step of determining the fusion obstacle existing mark number according to the fusion obstacle perception information comprises: If there is camera obstacle information and radar obstacle information in the fusion obstacle perception information, the camera obstacle information and the radar obstacle information are time-unified to obtain fusion obstacle information; An obstacle identification number of the fusion obstacle information is determined; The fusion obstacle existing mark number is determined according to the obstacle identification number.

3. The method of claim 2, wherein, The step of determining the confidence degree of the fusion obstacle according to the fusion obstacle matching success number, the fusion obstacle existing mark number and the fusion obstacle matching mark number comprises: A confidence degree calculation rule is determined according to the fusion obstacle matching success number; A pending confidence degree of the fusion obstacle is determined based on the confidence degree calculation rule; A mark difference value between the fusion obstacle existing mark number and the fusion obstacle matching mark number is determined; If the mark difference value is less than or equal to a preset threshold value, the pending confidence degree is taken as the confidence degree of the fusion obstacle.

4. The method of claim 3, wherein, After the step of determining the mark difference value between the fusion obstacle existing mark number and the fusion obstacle matching mark number, the following step is further included: When the mark difference value is greater than the preset threshold value, the pending confidence degree is set to 0.

5. The method of claim 1, wherein, After the step of determining the fusion obstacle perception information according to the camera perception information and the radar perception information, the following step is further included: If there is camera obstacle information and no radar obstacle information in the fusion obstacle perception information, a position distance between the fusion obstacle and a current driving vehicle is determined according to the camera obstacle information; A confidence degree selection rule is determined according to the position distance, and a pending confidence degree of the fusion obstacle is determined according to the confidence degree selection rule; updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks; updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks; 6. The method of claim 1, wherein, updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks; updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks.

7. A system for determining a confidence of a fusion barrier, the system comprising: updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks.

8. A fusion obstacle confidence determination device characterized by comprising: updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks.

9. A storage medium, characterized by updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle based on the number of fusion obstacle existence marks, the number of fusion obstacle matching successes and the number of fusion obstacle matching marks. updating the pending confidence of the fusion obstacle

Images