Traffic sign detection method, device, equipment, medium and autonomous driving vehicle

Abstract

The present disclosure provides a traffic sign detection method, device, equipment, medium and autonomous driving vehicle, which relates to the field of computer technology, and specifically to the fields of artificial intelligence technology such as autonomous driving, intelligent transportation, computer vision, and deep learning. The traffic sign detection method includes: detecting and processing an environmental image collected by an autonomous driving vehicle to obtain multiple candidate detection frames corresponding to the traffic signs in the environmental image and information of the multiple candidate detection frames, wherein the information includes an initial confidence; based on the overlap between the multiple candidate detection frames, updating the initial confidence of the multiple candidate detection frames to obtain the updated confidence of the multiple candidate detection frames; based on the updated confidence of the multiple candidate detection frames, determining the final detection frame corresponding to the traffic sign. The present disclosure can timely and accurately identify traffic signs during autonomous driving.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of artificial intelligence technologies such as unmanned driving, intelligent transportation, computer vision, deep learning, and more particularly to a traffic sign detection method, device, equipment, medium and autonomous driving vehicle. Background Art

[0002] Autonomous vehicles (Self-driving automobile), also known as unmanned vehicles, computer-driven vehicles or wheeled mobile robots, are intelligent vehicles that achieve unmanned driving through a computer system.

[0003] When driving, autonomous vehicles need to identify traffic signs in a timely and accurate manner and perform corresponding operations based on the traffic signs. Summary of the invention

[0004] The present disclosure provides a traffic sign detection method, device, equipment and storage medium.

[0005] According to one aspect of the present disclosure, a traffic sign detection method is provided, comprising: performing detection processing on an environment image collected by an autonomous driving vehicle to obtain a plurality of candidate detection frames corresponding to traffic signs in the environment image and information of the plurality of candidate detection frames, the information including initial confidences; updating the initial confidences of the plurality of candidate detection frames based on the overlap between the plurality of candidate detection frames to obtain updated confidences of the plurality of candidate detection frames; and determining a final detection frame corresponding to the traffic sign based on the updated confidences of the plurality of candidate detection frames.

[0006] According to another aspect of the present disclosure, a traffic sign detection device is provided, including: a detection module, used to detect and process an environment image collected by an autonomous driving vehicle to obtain multiple candidate detection frames corresponding to traffic signs in the environment image and information of the multiple candidate detection frames, wherein the information includes initial confidences; an update module, used to update the initial confidences of the multiple candidate detection frames based on the overlap between the multiple candidate detection frames to obtain updated confidences of the multiple candidate detection frames; and a determination module, used to determine a final detection frame corresponding to the traffic sign based on the updated confidences of the multiple candidate detection frames.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method as described in any of the above aspects.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to any one of the above aspects.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the methods described in any one of the above aspects.

[0010] According to another aspect of the present disclosure, an autonomous driving vehicle is provided, comprising: an electronic device as described in any one of the above aspects.

[0011] According to the technical solution disclosed in the present invention, traffic signs can be identified timely and accurately during automatic driving.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0014] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0015] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0016] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0017] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0018] Figure 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0019] Figure 6 is a schematic diagram according to a sixth embodiment of the present disclosure;

[0020] Figure 7It is a schematic diagram of an electronic device used to implement any of the traffic sign detection methods in the embodiments of the present disclosure. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure. This embodiment provides a traffic sign detection method, the method comprising:

[0023] 101. Perform detection processing on an environment image collected by an autonomous driving vehicle to obtain a candidate detection frame corresponding to a traffic sign in the environment image and initial information of the candidate detection frame.

[0024] 102. Based on the overlap between the multiple candidate detection frames, update the initial information of the multiple candidate detection frames to obtain updated information of the multiple candidate detection frames.

[0025] 103. Determine a final detection frame corresponding to the traffic sign based on the updated information of the multiple candidate detection frames.

[0026] In the scenario of autonomous driving, timely and accurate detection of traffic signs on the road plays an important role in the safety and smooth progress of autonomous driving.

[0027] Traffic signs can be divided into warning signs, prohibition signs, instruction signs, etc. Figure 2 As shown, several examples of traffic signs are given.

[0028] In an autonomous driving scenario, the camera on the autonomous driving vehicle can be used to collect environmental images of the vehicle's surroundings, which may include traffic signs.

[0029] After the autonomous driving vehicle collects the environment image, Figure 3 As shown, the autonomous driving vehicle can send the collected environment image to the cloud through the network, and the cloud processes the environment image to detect the traffic sign in the environment image. After that, the cloud can generate corresponding control instructions based on the detected traffic sign and send it to the autonomous driving vehicle. For example, if the traffic sign is a left turn sign, a control instruction for controlling the autonomous driving vehicle to turn left can be generated.

[0030] Taking the above-mentioned cloud processing and control of environmental images as an example, it can be understood that if the autonomous driving vehicle itself has a higher performance processor, the above-mentioned processing and control can also be completed by the processor on the autonomous driving vehicle.

[0031] Taking the processing of environmental images in the cloud as an example, after the cloud receives the environmental images collected by the autonomous driving vehicle, it can use existing target detection models, such as the YOLO model, to process the environmental images to obtain multiple detection frames corresponding to traffic signs in the environmental images. In addition, the information of the detection frames can also be obtained through the YOLO model.

[0032] The information of the detection frame may include: the position information of the detection frame, the confidence of the detection frame, etc. The position information can be represented by (x, yw, h), where (x, y) is the position coordinate of the center point of the detection frame, and w, h are the width and height of the detection frame respectively. The confidence of the detection frame is a value between 0 and 1.

[0033] For the sake of distinction, the detection box at this time can be called a candidate detection box, and the confidence can be called an initial confidence.

[0034] In some embodiments, the overlap degree is an intersection-and-union ratio, and the initial confidence of the multiple candidate detection frames is updated based on the overlap degree between the multiple candidate detection frames, including: taking each of the multiple candidate detection frames as a current detection frame; selecting a candidate detection frame whose initial confidence is greater than the initial confidence of the current detection frame from the multiple candidate detection frames to obtain a selected detection frame; based on the intersection-and-union ratio between the selected detection frame and the current detection frame, determining the selected detection frame with the largest intersection-and-union ratio as a comparison detection frame; based on the intersection-and-union ratio between the comparison detection frame and the current detection frame, determining a suppression coefficient of the current detection frame; and updating the initial confidence of the current detection frame based on the suppression coefficient.

[0035] Furthermore, the information also includes: position information. After obtaining the selected detection frame, the method also includes: determining the intersection-and-union ratio between the selected detection frame and the current detection frame based on the position information of the selected detection frame and the position information of the current detection frame.

[0036] Among them, assuming that there are N candidate detection boxes, the j-th candidate detection box is represented as Bj, its initial confidence is Sj, and its position information is represented as Lj. The i-th candidate detection box is represented as Bi, its initial confidence is Si, and its position information is represented as Li. The k-th candidate detection box is represented as Bk, and its initial confidence is Sk. i, j, and k are all between [1, N].

[0037] The above detection box Bj can be used as the current detection box. If Sk>Sj, then Bk can be used as the selected detection box.

[0038] Afterwards, the intersection-over-union ratio between Bj and Bk can be calculated.

[0039] Assuming that the initial confidence is greater than Bj and the detection box with the largest intersection-over-union ratio is Bi, the detection box Bi can be used as the comparison detection box.

[0040] The following takes the calculation of the intersection-and-union ratio between Bi and Bj as an example for explanation. The calculation process of Bj and Bk is similar.

[0041] Among them, the intersection over union (IoU) of Bi and Bj can be calculated based on Li and Lj. The intersection over union ratio refers to the ratio of the intersection part and the union part of Bi and Bj.

[0042] like Figure 4 As shown, assuming that the overlapping part of Bi and Bj is represented by Y, the part of Bi other than Y is represented by X, and the part of Bj other than Y is represented by Z, the calculation formula of the intersection and union ratio of Bi and Bj can be expressed as: Y / (X+Y+Z).

[0043] The above X, Y, and Z can be calculated based on the position information of Bi and Bj, that is, Li and Lj.

[0044] The position information can be used to calculate the intersection-union ratio. After obtaining the intersection-union ratio, the suppression coefficient of the current detection frame can be calculated based on the intersection-union ratio.

[0045] The calculation formula of the suppression coefficient can be expressed as:

[0046]

[0047]

[0048] Among them, iou i,j It represents the intersection-over-union ratio between the detection box Bi and the detection box Bj. The parameters related to k are similar. decayj represents the suppression coefficient corresponding to the detection box Bj.

[0049] f(iou i,j ) can be obtained by linear or Gaussian calculation. Taking linear calculation as an example, the calculation formula can be: f(iou i,j )=1-iou i,j .

[0050] After obtaining the suppression coefficient, the suppression coefficient can be multiplied by the initial confidence to obtain the updated confidence.

[0051] Corresponding to the detection box Bj, its updated confidence can be expressed as: decayj*Sj.

[0052] By multiplying the suppression coefficient with the initial confidence to obtain the updated confidence, the confidence can be updated simply and quickly.

[0053] In road scenarios, traffic signs may overlap, for example Figure 5 As shown, Figure 5 The environment image shown includes three traffic signs, which are represented by traffic sign-1, traffic sign-2 and traffic sign-3. Figure 5 In the scenario shown, traffic sign-2 and traffic sign-3 overlap.

[0054] If the general non-maximum suppression (NMS) algorithm is used, the detection frame corresponding to the non-maximum (NMS) will be directly filtered out, that is, the detection frame corresponding to the traffic sign-3 will be filtered out, resulting in missed detection of the traffic sign-3.

[0055] In the embodiment, the initial confidence of the detection frame is suppressed instead of being directly filtered out, thereby avoiding missed detection and improving the accuracy of traffic sign detection.

[0056] In some embodiments, there are multiple selection detection frames, and determining the intersection-and-union ratio between the selection detection frame and the current detection frame based on the position information of the selection detection frame and the position information of the current detection frame includes: based on the position information of each selection detection frame in the multiple selection detection frames and the position information of the current detection frame, performing parallel operations on the multiple selection detection frames to respectively determine the intersection-and-union ratio of each selection detection frame in the multiple selection detection frames and the current detection frame.

[0057] Through parallel computing, the computing speed can be increased, thereby improving the efficiency of traffic sign detection.

[0058] In some embodiments, there are multiple traffic signs, each of the multiple traffic signs corresponds to multiple candidate detection frames, and determining the final detection frame corresponding to the traffic sign based on the updated confidence of the multiple candidate detection frames includes: corresponding to each traffic sign in the multiple traffic signs, taking the candidate detection frame with the largest updated confidence among the multiple candidate detection frames corresponding to each traffic sign as the final detection frame corresponding to each traffic sign.

[0059] Among them, the existing target detection model, such as the YOLO model, can distinguish multiple targets, such as the multiple traffic signs mentioned above. In this embodiment, the above-mentioned initial confidence update and other processing can be performed on each traffic sign distinguished by the YOLO model to obtain the final detection box corresponding to each traffic sign.

[0060] for example, Figure 5 The environment image shown includes multiple traffic signs, namely traffic sign-1, traffic sign-2 and traffic sign-3. After the above processing, the corresponding final detection frame can be determined for each traffic sign. Figure 5 The final detection frame corresponding to each traffic sign is represented by a bold frame.

[0061] By processing each of the multiple traffic signs, a final detection frame corresponding to each traffic sign can be obtained, thereby avoiding missed detection and improving the detection accuracy of the traffic signs.

[0062] In the disclosed embodiment, by acquiring an environmental image captured by an autonomous driving vehicle, the initial confidences of the multiple candidate detection frames are updated based on the overlap between the multiple candidate detection frames corresponding to the traffic signs in the environmental image to obtain updated confidences of the multiple candidate detection frames, and based on the updated confidences of the multiple candidate detection frames, a final detection frame corresponding to the traffic sign is determined, so that traffic signs can be identified in a timely and accurate manner during autonomous driving.

[0063] Figure 6 is a schematic diagram according to the sixth embodiment of the present disclosure, which provides a traffic sign detection device. Figure 6 As shown, the device 600 includes: a detection module 601, an update module 602 and a determination module 603.

[0064] The detection module 601 is used to perform detection processing on the environmental image collected by the autonomous driving vehicle to obtain multiple candidate detection frames corresponding to the traffic signs in the environmental image and information of the multiple candidate detection frames, wherein the information includes initial confidences; the update module 602 is used to update the initial confidences of the multiple candidate detection frames based on the overlap between the multiple candidate detection frames to obtain updated confidences of the multiple candidate detection frames; the determination module 603 is used to determine the final detection frame corresponding to the traffic sign based on the updated confidences of the multiple candidate detection frames.

[0065] In some embodiments, the overlap degree is an intersection-and-union ratio, and the update module 602 is specifically used to: use each candidate detection frame in the multiple candidate detection frames as a current detection frame; select a candidate detection frame whose initial confidence is greater than the initial confidence of the current detection frame from the multiple candidate detection frames to obtain a selected detection frame; based on the intersection-and-union ratio between the selected detection frame and the current detection frame, determine the selected detection frame with the largest intersection-and-union ratio as a comparison detection frame; based on the intersection-and-union ratio between the comparison detection frame and the current detection frame, determine a suppression coefficient of the current detection frame; and based on the suppression coefficient, update the initial confidence of the current detection frame.

[0066] In some embodiments, the information further includes: position information, and the updating module 602 is further used to: determine an intersection-over-union ratio between the selected detection frame and the current detection frame based on the position information of the selected detection frame and the position information of the current detection frame.

[0067] In some embodiments, there are multiple selection detection boxes, and the update module 602 is specifically used to: based on the position information of each selection detection box in the multiple selection detection boxes and the position information of the current detection box, perform parallel operations on the multiple selection detection boxes to respectively determine the intersection and union ratio of each selection detection box in the multiple selection detection boxes and the current detection box.

[0068] In some embodiments, the updating module 602 is specifically configured to: use the product of the suppression coefficient and the initial confidence of the current detection frame as the updated confidence of the current detection frame.

[0069] In some embodiments, there are multiple traffic signs, and each of the multiple traffic signs corresponds to multiple candidate detection frames. The determination module 603 is specifically used to: correspond to each traffic sign in the multiple traffic signs, and use the candidate detection frame with the largest updated confidence among the multiple candidate detection frames corresponding to each traffic sign as the final detection frame corresponding to each traffic sign.

[0070] In the disclosed embodiment, by acquiring an environmental image captured by an autonomous driving vehicle, the initial confidences of the multiple candidate detection frames are updated based on the overlap between the multiple candidate detection frames corresponding to the traffic signs in the environmental image to obtain updated confidences of the multiple candidate detection frames, and based on the updated confidences of the multiple candidate detection frames, a final detection frame corresponding to the traffic sign is determined, so that traffic signs can be identified in a timely and accurate manner during autonomous driving.

[0071] It can be understood that in the embodiments of the present disclosure, the same or similar contents in different embodiments can be referenced to each other.

[0072] It can be understood that the “first”, “second”, etc. in the embodiments of the present disclosure are only used for distinction and do not indicate the degree of importance, time sequence, etc.

[0073] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0074] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0075] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 707 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0076] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0077] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the traffic sign detection method. For example, in some embodiments, the traffic sign detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the traffic sign detection method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the traffic sign detection method in any other appropriate manner (e.g., by means of firmware).

[0078] According to an embodiment of the present disclosure, the present disclosure also provides an autonomous driving vehicle, which may include: Figure 7 Electronic equipment shown.

[0079] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0080] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0081] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0083] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0084] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0085] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0086] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A traffic sign detection method, comprising: Performing detection processing on an environment image collected by the autonomous driving vehicle to obtain a plurality of candidate detection frames corresponding to traffic signs in the environment image and information of the plurality of candidate detection frames, wherein the information includes an initial confidence level; Based on the overlap between the multiple candidate detection frames, updating the initial confidences of the multiple candidate detection frames to obtain updated confidences of the multiple candidate detection frames; Determining a final detection frame corresponding to the traffic sign based on the updated confidences of the multiple candidate detection frames; The overlap degree is an intersection-over-union ratio, and the updating process of the initial confidences of the multiple candidate detection frames based on the overlap degrees between the multiple candidate detection frames includes: Taking each of the multiple candidate detection frames as a current detection frame; Selecting, from the multiple candidate detection frames, a candidate detection frame whose initial confidence is greater than the initial confidence of the current detection frame to obtain a selected detection frame; Based on the intersection-and-union ratio between the selected detection frame and the current detection frame, determining the selected detection frame with the largest intersection-and-union ratio as the comparison detection frame; Determining a suppression coefficient of the current detection frame based on an intersection-and-union ratio between the comparison detection frame and the current detection frame; Based on the suppression coefficient, an initial confidence of the current detection box is updated.

2. The method according to claim 1, wherein: The information also includes: location information. After obtaining the selection detection frame, the method further includes: Based on the position information of the selected detection frame and the position information of the current detection frame, an intersection-over-union ratio between the selected detection frame and the current detection frame is determined.

3. The method according to claim 2, wherein: The selected detection frame is multiple, and the determining the intersection-over-union ratio between the selected detection frame and the current detection frame based on the position information of the selected detection frame and the position information of the current detection frame includes: Based on the position information of each selection detection frame in the multiple selection detection frames and the position information of the current detection frame, the multiple selection detection frames are parallelly calculated to respectively determine the intersection-and-union ratio of each selection detection frame in the multiple selection detection frames and the current detection frame.

4. The method according to claim 1, wherein: The updating of the initial confidence of the current detection frame based on the suppression coefficient includes: The product of the suppression coefficient and the initial confidence of the current detection frame is used as the updated confidence of the current detection frame.

5. The method according to any one of claims 1 to 4, wherein: There are multiple traffic signs, each of the multiple traffic signs corresponds to multiple candidate detection frames, and determining a final detection frame corresponding to the traffic sign based on the updated confidence of the multiple candidate detection frames includes: Corresponding to each of the multiple traffic signs, the candidate detection frame with the largest update confidence among the multiple candidate detection frames corresponding to the respective traffic signs is used as the final detection frame corresponding to the respective traffic sign.

6. A traffic sign detection device, comprising: A detection module, configured to perform detection processing on an environment image collected by the autonomous driving vehicle to obtain a plurality of candidate detection frames corresponding to traffic signs in the environment image and information of the plurality of candidate detection frames, wherein the information includes an initial confidence level; An updating module, configured to update the initial confidences of the multiple candidate detection frames based on the overlaps between the multiple candidate detection frames to obtain updated confidences of the multiple candidate detection frames; A determination module, configured to determine a final detection frame corresponding to the traffic sign based on the updated confidences of the multiple candidate detection frames; The overlap degree is an intersection-over-union ratio, and the updating module is specifically used for: Taking each of the multiple candidate detection frames as a current detection frame; Selecting, from the multiple candidate detection frames, a candidate detection frame whose initial confidence is greater than the initial confidence of the current detection frame to obtain a selected detection frame; Based on the intersection-and-union ratio between the selected detection frame and the current detection frame, determining the selected detection frame with the largest intersection-and-union ratio as the comparison detection frame; Determining a suppression coefficient of the current detection frame based on an intersection-and-union ratio between the comparison detection frame and the current detection frame; Based on the suppression coefficient, an initial confidence of the current detection box is updated.

7. The device according to claim 6, wherein: The information also includes: location information, and the update module is further used for: Based on the position information of the selected detection frame and the position information of the current detection frame, an intersection-over-union ratio between the selected detection frame and the current detection frame is determined.

8. The device according to claim 7, wherein: There are multiple selection detection boxes, and the update module is specifically used for: Based on the position information of each selection detection frame in the multiple selection detection frames and the position information of the current detection frame, the multiple selection detection frames are parallelly calculated to respectively determine the intersection-and-union ratio of each selection detection frame in the multiple selection detection frames and the current detection frame.

9. The device according to claim 6, wherein: The update module is specifically used for: The product of the suppression coefficient and the initial confidence of the current detection frame is used as the updated confidence of the current detection frame.

10. The device according to any one of claims 6 to 9, wherein: There are multiple traffic signs, each of which corresponds to multiple candidate detection frames, and the determination module is specifically used to: Corresponding to each of the multiple traffic signs, the candidate detection frame with the largest update confidence among the multiple candidate detection frames corresponding to the respective traffic signs is used as the final detection frame corresponding to the respective traffic sign.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

14. An autonomous driving vehicle comprising: The electronic device as claimed in claim 11.

Images