Street lamp fault detection method and device, electronic equipment and storage medium

Abstract

The application discloses a street lamp fault detection method and device, an electronic device, and a storage medium. The method is executed by a roadside device, and the method comprises the following steps: acquiring a night road image and high-precision map data of a current road section; preprocessing the night road image by using a preset preprocessing strategy, to obtain a bright spot area in the night road image; determining a street lamp area in the night road image according to the night road image and the high-precision map data; and determining a street lamp fault detection result according to the bright spot area in the night road image and the street lamp area in the night road image. The street lamp fault detection method provided by the application can quickly and accurately detect the fault condition of a street lamp by using the street lamp data provided by a high-precision map and the bright spot area in a night road image, without manual inspection, so that the efficiency of street lamp fault detection is improved, and the detection cost is reduced.

Description

Technical Field

[0001] This application relates to the field of street light detection technology, and in particular to a street light fault detection method, device, electronic equipment, and storage medium. Background Technology

[0002] Streetlights provide strong protection for road safety, but they can also malfunction or break down after long-term use. It often takes a long time from the onset of a malfunction to repair and restoration, mainly because the malfunctions are not detected in time. Therefore, the detection of streetlight malfunctions is particularly important.

[0003] Existing street light inspection methods mainly rely on manual nighttime inspections, which have drawbacks such as low efficiency, easy fatigue of inspectors, and high inspection costs. Summary of the Invention

[0004] This application provides a street light fault detection method, device, electronic equipment, and storage medium to improve the efficiency of street light fault detection and reduce detection costs.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a street light fault detection method, the method being executed by a roadside device, wherein the method includes:

[0007] Acquire nighttime road images and high-precision map data for the current road segment;

[0008] The nighttime road image is preprocessed using a preset preprocessing strategy to obtain bright spot areas in the nighttime road image;

[0009] The street light areas in the nighttime road images are determined based on the nighttime road images and the high-precision map data;

[0010] The street light fault detection result is determined based on the bright areas in the nighttime road image and the street light areas in the nighttime road image.

[0011] Optionally, the step of preprocessing the nighttime road image using a preset preprocessing strategy to obtain the bright spot regions in the nighttime road image includes:

[0012] The nighttime road image is processed into grayscale to obtain a grayscale image corresponding to the nighttime road image;

[0013] The grayscale image corresponding to the nighttime road image is denoised using a preset denoising strategy to obtain a denoised grayscale image.

[0014] By using a preset pixel filtering strategy to filter the pixels in the denoised grayscale image, bright spot areas in the grayscale image corresponding to the nighttime road image are obtained.

[0015] Optionally, the nighttime road images include multiple images, and the preprocessing of the nighttime road images using a preset preprocessing strategy to obtain bright spot regions in the nighttime road images includes:

[0016] The preset preprocessing strategy is used to preprocess each of the nighttime road images to obtain the bright spot areas in each of the nighttime road images;

[0017] The bright areas in each of the nighttime road images are fused together, and the bright areas belonging to streetlights in each of the nighttime road images are determined based on the fusion processing results.

[0018] Optionally, the bright spots include multiple regions, and the process of fusing the bright spots in each of the nighttime road images and determining the bright spots belonging to streetlights in each of the nighttime road images based on the fusing results includes:

[0019] Determine whether each of the bright spots appears in the same location in each of the nighttime road images;

[0020] If so, the bright area will be retained and designated as a bright area belonging to the streetlight;

[0021] Otherwise, the highlighted area is discarded.

[0022] Optionally, determining the streetlight area in the nighttime road image based on the nighttime road image and the high-precision map data includes:

[0023] The absolute location of the streetlights in the current road segment is determined based on the high-precision map data.

[0024] Based on the transformation relationship between the high-precision map and the roadside camera, the absolute position of the streetlights in the current road segment is projected into the nighttime road image to obtain the streetlight area in the nighttime road image.

[0025] Optionally, determining the streetlight fault detection result based on the bright spot area in the nighttime road image and the streetlight area in the nighttime road image includes:

[0026] Compare the bright areas in the nighttime road image with the street light areas in the nighttime road image;

[0027] If the street light area in the nighttime road image overlaps with the bright spot area in the nighttime road image, and the size of the overlapping area reaches a preset threshold, then the street light status corresponding to the street light area is determined to be normal.

[0028] Otherwise, the streetlight status corresponding to the streetlight area is determined to be a fault state.

[0029] Optionally, the nighttime road image is a first nighttime road image, and determining the streetlight fault detection result based on the bright spot areas and streetlight areas in the nighttime road image includes:

[0030] If the street light fault detection result corresponding to the first nighttime road image is that the street light status corresponding to the street light area is faulty, then the second nighttime road image of the current road segment is obtained.

[0031] Based on the second nighttime road image, the street light fault detection results corresponding to the first nighttime road image are verified;

[0032] The final street light fault detection result is determined based on the verification results, and the final street light fault detection result is sent to the cloud and / or the vehicle.

[0033] Secondly, embodiments of this application also provide a street light fault detection device, which is applied to roadside equipment, wherein the device includes:

[0034] The acquisition unit is used to acquire nighttime road images and high-precision map data for the current road segment;

[0035] The preprocessing unit is used to preprocess the nighttime road image using a preset preprocessing strategy to obtain the bright spot areas in the nighttime road image;

[0036] The first determining unit is configured to determine the street light area in the nighttime road image based on the nighttime road image and the high-precision map data;

[0037] The second determining unit is used to determine the street light fault detection result based on the bright spot area in the nighttime road image and the street light area in the nighttime road image.

[0038] Thirdly, embodiments of this application also provide an electronic device, including:

[0039] Processor; and

[0040] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0041] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the methods described above.

[0042] The above-mentioned technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The street light fault detection method of the embodiments of this application is executed by a roadside device. First, it acquires nighttime road images and high-precision map data of the current road segment; then, it preprocesses the nighttime road images using a preset preprocessing strategy to obtain bright spot areas in the nighttime road images; then, it determines the street light areas in the nighttime road images based on the nighttime road images and high-precision map data; finally, it determines the street light fault detection result based on the bright spot areas and street light areas in the nighttime road images. The street light fault detection method of the embodiments of this application can quickly and accurately detect street light faults using street light data provided by high-precision maps and bright spot areas in nighttime road images, without the need for manual inspection, thus improving the efficiency of street light fault detection and reducing detection costs. Attached Figure Description

[0043] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0044] Figure 1 This is a flowchart illustrating a street light fault detection method according to an embodiment of this application;

[0045] Figure 2 This is a schematic diagram of the structure of a street light fault detection device according to an embodiment of this application;

[0046] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0049] This application provides a street light fault detection method, which is executed by roadside equipment, such as... Figure 1 The diagram shows a flowchart of a street light fault detection method according to an embodiment of this application. The method includes at least the following steps S110 to S140:

[0050] Step S110: Obtain nighttime road images and high-precision map data for the current road segment.

[0051] The street light fault detection method of this application embodiment can be executed by a roadside device. The roadside camera collects nighttime road images of the current road segment. In addition, it is also necessary to obtain high-precision map data of the current road segment. Here, the corresponding local high-precision map data can be obtained according to the absolute position of the roadside device.

[0052] High-precision map data not only contains high-precision coordinates but also accurate road shapes, including the slope, curvature, heading, elevation, and lateral tilt data for each lane. Furthermore, the types of markings on each lane, the colors of lane lines, road dividers, streetlights, and arrows and text on road signs are all presented in the high-precision map. Therefore, based on high-precision map data, it is possible to determine the streetlight information for the current road segment.

[0053] Step S120: The nighttime road image is preprocessed using a preset preprocessing strategy to obtain bright spot areas in the nighttime road image.

[0054] After obtaining nighttime road images, certain preprocessing strategies are needed to preprocess them in order to identify the bright areas belonging to streetlights. Preprocessing operations may include at least one of grayscale processing, noise reduction, and pixel filtering.

[0055] Step S130: Determine the street light area in the nighttime road image based on the nighttime road image and the high-precision map data.

[0056] Since the high-precision map data provides information such as the location of all streetlights on the current road segment, it is possible to further determine the location of these streetlights in the nighttime road image, thereby obtaining the streetlight area in the nighttime road image.

[0057] Step S140: Determine the street light fault detection result based on the bright spot area in the nighttime road image and the street light area in the nighttime road image.

[0058] Bright spots in nighttime road images indicate which areas correspond to streetlights, while streetlight areas in nighttime road images indicate which areas are actually streetlights. Therefore, by combining the two, we can determine which streetlight areas are lit and which are not. In a nighttime road scene, the streetlights in the unlit areas can be considered faulty, thus obtaining the streetlight fault detection result.

[0059] The street light fault detection method of this application can quickly and accurately detect street light faults by using street light data provided by high-precision maps and bright areas in nighttime road images, without the need for manual inspection, thus improving the efficiency of street light fault detection and reducing detection costs.

[0060] In some embodiments of this application, the step of preprocessing the nighttime road image using a preset preprocessing strategy to obtain bright spot regions in the nighttime road image includes: performing grayscale processing on the nighttime road image to obtain a grayscale image corresponding to the nighttime road image; performing denoising processing on the grayscale image corresponding to the nighttime road image using a preset denoising strategy to obtain a denoised grayscale image; and filtering the pixels in the denoised grayscale image using a preset pixel filtering strategy to obtain bright spot regions in the grayscale image corresponding to the nighttime road image.

[0061] When preprocessing nighttime road images using a preset preprocessing strategy, the nighttime road images can first be processed into grayscale to obtain the corresponding grayscale images. Then, a certain denoising strategy, such as Gaussian smoothing filtering, can be used to denoise the grayscale images to obtain denoised grayscale images, thereby reducing high-frequency noise in the grayscale images.

[0062] Since the core of the preprocessing of nighttime road images in this embodiment lies in identifying the bright areas that belong to streetlights, a pixel filtering strategy can be further employed to filter pixels in the grayscale image that are clearly not bright spots or that do not correspond to the bright spots of streetlights. This results in bright areas that are more likely to belong to streetlights, while also reducing the amount of data processed subsequently. For example, pixels with values ​​below a pre-set threshold can be filtered out, as these pixels do not correspond to the bright areas of streetlights. Furthermore, image erosion and dilation processes can be used to remove excessively small bright spots in the grayscale image, as these are unlikely to be bright areas of streetlights.

[0063] In some embodiments of this application, the nighttime road images include multiple images. The step of preprocessing the nighttime road images using a preset preprocessing strategy to obtain bright spot regions in the nighttime road images includes: preprocessing each of the nighttime road images using the preset preprocessing strategy to obtain bright spot regions in each of the nighttime road images; performing fusion processing on the bright spot regions in each of the nighttime road images; and determining the bright spot regions belonging to streetlights in each of the nighttime road images based on the fusion processing results.

[0064] Since some bright areas that do not belong to streetlights may still exist in the bright areas detected based on a single nighttime road image, such as interference from vehicle lights, in order to further improve the accuracy of streetlight bright area detection, this application embodiment can acquire a nighttime road image at regular intervals, such as every 10 minutes, and perform the preprocessing operation described in the aforementioned embodiment on it, thereby obtaining bright areas in multiple nighttime road images. Then, these bright areas in multiple nighttime road images are comprehensively compared to filter out bright areas belonging to vehicle lights.

[0065] Since the real-time requirements for street light fault detection are relatively low, those skilled in the art can flexibly set the above time intervals according to actual needs, and no specific limitations are made here.

[0066] In some embodiments of this application, the bright spot regions include multiple regions. The step of performing fusion processing on the bright spot regions in each of the nighttime road images and determining the bright spot regions belonging to streetlights in each of the nighttime road images based on the fusion processing results includes: determining whether each of the bright spot regions appears in the same position in each of the nighttime road images; if so, the bright spot region is retained and regarded as a bright spot region belonging to streetlights; otherwise, the bright spot region is discarded.

[0067] A bright spot area in a nighttime road image may include multiple bright spots, including those belonging to streetlights and those not belonging to streetlights, such as those belonging to vehicle headlights. Therefore, this application embodiment can compare the bright spots contained in multiple nighttime road images. For any bright spot area, if its position overlaps or is the same in multiple nighttime road images, it means that its position is fixed and can be considered as a bright spot area belonging to a streetlight. Conversely, if its position does not overlap or is different in multiple nighttime road images, it means that its position is not fixed and can be considered as a bright spot area not belonging to a streetlight. This bright spot area can be directly discarded, thereby eliminating the interference of vehicle headlights.

[0068] In some embodiments of this application, determining the street light area in the night road image based on the night road image and the high-precision map data includes: determining the absolute position of the street lights in the current road segment based on the high-precision map data; and projecting the absolute position of the street lights in the current road segment onto the night road image based on the transformation relationship between the high-precision map and the roadside camera to obtain the street light area in the night road image.

[0069] Since high-precision maps are constructed based on the world coordinate system, while the bright areas in nighttime road images are in the coordinate system of roadside cameras, the transformation relationship between high-precision maps and roadside cameras can be calibrated in advance in this application embodiment. Those skilled in the art can flexibly choose the specific calibration method in combination with existing technology, and no specific limitation is made here.

[0070] Based on the transformation relationship between the calibrated high-precision map and the roadside camera, the absolute position of the streetlights in the high-precision map data can be projected into the nighttime road image, thereby obtaining the position of the streetlights in the nighttime road image, that is, obtaining the streetlight area in the nighttime road image.

[0071] In some embodiments of this application, determining the street light fault detection result based on the bright spot area in the nighttime road image and the street light area in the nighttime road image includes: comparing the bright spot area in the nighttime road image with the street light area in the nighttime road image; if the street light area in the nighttime road image overlaps with the bright spot area in the nighttime road image, and the size of the overlapping area reaches a preset threshold, then the street light status corresponding to the street light area is determined to be normal; otherwise, the street light status corresponding to the street light area is determined to be faulty.

[0072] When determining streetlight fault detection results based on bright spot areas and streetlight areas in nighttime road images, the bright spot areas can be compared with the streetlight areas. Specifically, the intersection-over-union (IoU) ratio of the bright spot areas and the streetlight areas can be calculated. If the IoU ratio is greater than a certain threshold, it indicates that a bright spot belonging to a streetlight has been detected in that streetlight area, thus indicating that the streetlights in that area are emitting light normally, i.e., they are in normal working condition. Conversely, if there is no intersection between the bright spot areas and the streetlight areas, or if the IoU ratio is less than the aforementioned threshold, it indicates that no bright spot belonging to a streetlight has been detected in that streetlight area, thus indicating that the streetlights in that area are not emitting light, i.e., they are in a fault state.

[0073] In some embodiments of this application, the nighttime road image is a first nighttime road image. The step of determining the street light fault detection result based on the bright spot area and the street light area in the nighttime road image includes: if the street light fault detection result corresponding to the first nighttime road image is that the street light status corresponding to the street light area is faulty, then obtaining a second nighttime road image of the current road segment; verifying the street light fault detection result corresponding to the first nighttime road image based on the second nighttime road image; determining the final street light fault detection result based on the verification result, and sending the final street light fault detection result to the cloud and / or the vehicle.

[0074] To further improve the accuracy of street light fault detection, after detecting faulty street lights on the current road segment based on the first nighttime road image, multiple second nighttime road images can be acquired and detected separately. For example, a second nighttime road image can be acquired every 10 minutes. Then, based on the potentially faulty street light area detected in the first nighttime road image, the corresponding location area in the second nighttime road image can be detected. If no bright spot belonging to a street light is detected in the street light area in multiple second nighttime road images, the accuracy of the previous fault detection results can be verified.

[0075] If a faulty streetlight is verified in the current road section, its location can be reported to the cloud so that maintenance personnel can be notified promptly. Furthermore, the location of the faulty streetlight can be sent to vehicles approaching the section to warn them to drive carefully. This embodiment of the application further ensures the accuracy and robustness of the streetlight detection results by adding a secondary verification step, avoiding the waste of human and material resources caused by false detections and false alarms.

[0076] In some embodiments of this application, determining the street light fault detection result based on the bright spot area in the nighttime road image and the street light area in the nighttime road image includes: if the street light fault detection result includes a street light area whose street light status is faulty, then obtaining the street light fault detection result of the surrounding street light area corresponding to the street light area; verifying the street light fault detection result of the street light area based on the street light fault detection result of the surrounding street light area; and determining the final street light fault detection result based on the verification result.

[0077] In addition to the verification methods provided in the foregoing embodiments, this application embodiment can also verify the fault detection results of the street light area by combining the fault detection status of the surrounding street lights corresponding to the potentially faulty street light area. Since in real-world scenarios, it is generally not the case that several consecutive street lights or multiple surrounding street lights will simultaneously malfunction, if it is determined that the current street light area may be faulty, the surrounding street light areas that are closest to or within a preset distance range can be further identified. Then, the fault detection results of these surrounding street light areas can be obtained. If the fault detection results of these surrounding street light areas are all normal, it can further verify that the current street light area is faulty.

[0078] It should be noted that the two verification methods provided in the above embodiments can be used in combination or either one can be used at will. Those skilled in the art can choose flexibly according to actual needs.

[0079] This application embodiment also provides a street light fault detection device 200, which is applied to roadside equipment, such as... Figure 2 As shown, a schematic diagram of a street light fault detection device according to an embodiment of this application is provided. The device 200 includes: an acquisition unit 210, a preprocessing unit 220, a first determination unit 230, and a second determination unit 240, wherein:

[0080] Acquisition unit 210 is used to acquire nighttime road images and high-precision map data of the current road segment;

[0081] Preprocessing unit 220 is used to preprocess the nighttime road image using a preset preprocessing strategy to obtain bright spot areas in the nighttime road image;

[0082] The first determining unit 230 is used to determine the street light area in the night road image based on the night road image and the high-precision map data;

[0083] The second determining unit 240 is used to determine the street light fault detection result based on the bright spot area in the night road image and the street light area in the night road image.

[0084] In some embodiments of this application, the preprocessing unit 220 is specifically used to: perform grayscale processing on the nighttime road image to obtain a grayscale image corresponding to the nighttime road image; perform denoising processing on the grayscale image corresponding to the nighttime road image using a preset denoising strategy to obtain a denoised grayscale image; and filter the pixels in the denoised grayscale image using a preset pixel filtering strategy to obtain bright spot areas in the grayscale image corresponding to the nighttime road image.

[0085] In some embodiments of this application, the nighttime road images include multiple images, and the preprocessing unit 220 is specifically used to: preprocess each of the nighttime road images using the preset preprocessing strategy to obtain bright spot areas in each of the nighttime road images; perform fusion processing on the bright spot areas in each of the nighttime road images, and determine the bright spot areas belonging to streetlights in each of the nighttime road images based on the fusion processing results.

[0086] In some embodiments of this application, the bright spot area includes multiple areas, and the preprocessing unit 220 is specifically used to: determine whether each of the bright spot areas appears in the same position in each of the nighttime road images; if so, retain the bright spot area as a bright spot area belonging to the street lamp; otherwise, discard the bright spot area.

[0087] In some embodiments of this application, the first determining unit 230 is specifically used to: determine the absolute position of the streetlights in the current road segment based on the high-precision map data; and project the absolute position of the streetlights in the current road segment onto the nighttime road image based on the transformation relationship between the high-precision map and the roadside camera, thereby obtaining the streetlight area in the nighttime road image.

[0088] In some embodiments of this application, the second determining unit 240 is specifically used to: compare the bright spot area in the nighttime road image with the street light area in the nighttime road image; if the street light area in the nighttime road image overlaps with the bright spot area in the nighttime road image, and the size of the overlapping area reaches a preset threshold, then determine that the street light status corresponding to the street light area is a normal state; otherwise, determine that the street light status corresponding to the street light area is a fault state.

[0089] In some embodiments of this application, the nighttime road image is a first nighttime road image, and the second determining unit 240 is specifically used to: if the street light fault detection result corresponding to the first nighttime road image is that the street light status corresponding to the street light area is faulty, then obtain the second nighttime road image of the current road segment; verify the street light fault detection result corresponding to the first nighttime road image based on the second nighttime road image; determine the final street light fault detection result according to the verification result, and send the final street light fault detection result to the cloud and / or the vehicle terminal.

[0090] It is understood that the above-mentioned street light fault detection device can realize all the steps of the street light fault detection method provided in the foregoing embodiments. The relevant explanations of the street light fault detection method are applicable to the street light fault detection device, and will not be repeated here.

[0091] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0092] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0093] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0094] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a street light fault detection device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0095] Acquire nighttime road images and high-precision map data for the current road segment;

[0096] The nighttime road image is preprocessed using a preset preprocessing strategy to obtain bright spot areas in the nighttime road image;

[0097] The street light areas in the nighttime road images are determined based on the nighttime road images and the high-precision map data;

[0098] The street light fault detection result is determined based on the bright areas in the nighttime road image and the street light areas in the nighttime road image.

[0099] The above is as stated in this application. Figure 1The method executed by the streetlight fault detection device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0100] The electronic device can also perform Figure 1 The method for implementing a street light fault detection device, and the realization of the street light fault detection device in... Figure 1 The functions of the embodiments shown are not described in detail here.

[0101] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the street light fault detection device in the illustrated embodiment is specifically used to perform the following:

[0102] Acquire nighttime road images and high-precision map data for the current road segment;

[0103] The nighttime road image is preprocessed using a preset preprocessing strategy to obtain bright spot areas in the nighttime road image;

[0104] The street light areas in the nighttime road images are determined based on the nighttime road images and the high-precision map data;

[0105] The street light fault detection result is determined based on the bright areas in the nighttime road image and the street light areas in the nighttime road image.

[0106] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0110] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0111] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0112] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0113] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0114] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting street light faults, wherein the method is performed by roadside equipment, wherein, The method includes: Acquire nighttime road images and high-precision map data for the current road segment; The nighttime road image is preprocessed using a preset preprocessing strategy to obtain bright spot areas in the nighttime road image; The street light areas in the nighttime road images are determined based on the nighttime road images and the high-precision map data; The street light fault detection result is determined based on the bright spot areas and street light areas in the nighttime road image; The nighttime road images include multiple images, and the preprocessing of the nighttime road images using a preset preprocessing strategy to obtain bright spot regions in the nighttime road images includes: The preset preprocessing strategy is used to preprocess each of the nighttime road images to obtain the bright spot areas in each of the nighttime road images; The bright areas in each of the nighttime road images are fused, and the bright areas belonging to streetlights in each of the nighttime road images are determined based on the fusion processing results. The step of determining the bright spots belonging to streetlights in each of the nighttime road images based on the fusion processing results includes: Based on the fusion processing results, bright areas that do not belong to streetlights are filtered out to obtain the bright areas that belong to streetlights in each of the nighttime road images. The bright areas that do not belong to streetlights include bright areas of vehicle lights.

2. The method as described in claim 1, wherein, The step of preprocessing the nighttime road image using a preset preprocessing strategy to obtain the bright spot regions in the nighttime road image includes: The nighttime road image is processed into grayscale to obtain a grayscale image corresponding to the nighttime road image; The grayscale image corresponding to the nighttime road image is denoised using a preset denoising strategy to obtain a denoised grayscale image. By using a preset pixel filtering strategy to filter the pixels in the denoised grayscale image, bright spot areas in the grayscale image corresponding to the nighttime road image are obtained.

3. The method as described in claim 1, wherein, The bright spots include multiple regions. The process of fusing the bright spots in each of the nighttime road images and determining the bright spots belonging to streetlights in each of the nighttime road images based on the fusing results includes: Determine whether each of the bright spots appears in the same location in each of the nighttime road images; If so, the bright area will be retained and designated as a bright area belonging to the streetlight; Otherwise, the highlighted area is discarded.

4. The method as described in claim 1, wherein, The step of determining the street light area in the nighttime road image based on the nighttime road image and the high-precision map data includes: The absolute location of the streetlights in the current road segment is determined based on the high-precision map data. Based on the transformation relationship between the high-precision map and the roadside camera, the absolute position of the streetlights in the current road segment is projected into the nighttime road image to obtain the streetlight area in the nighttime road image.

5. The method as described in claim 1, wherein, The step of determining the street light fault detection result based on the bright spot areas and street light areas in the nighttime road image includes: Compare the bright areas in the nighttime road image with the street light areas in the nighttime road image; If the street light area in the nighttime road image overlaps with the bright spot area in the nighttime road image, and the size of the overlapping area reaches a preset threshold, then the street light status corresponding to the street light area is determined to be normal. Otherwise, the streetlight status corresponding to the streetlight area is determined to be a fault state.

6. The method of claim 1, wherein, The nighttime road image is a first nighttime road image. The step of determining the streetlight fault detection result based on the bright spot areas and streetlight areas in the nighttime road image includes: If the street light fault detection result corresponding to the first nighttime road image is that the street light status corresponding to the street light area is faulty, then the second nighttime road image of the current road segment is obtained. Based on the second nighttime road image, the street light fault detection results corresponding to the first nighttime road image are verified; The final street light fault detection result is determined based on the verification results, and the final street light fault detection result is sent to the cloud and / or the vehicle.

7. A street light fault detection device, said device being applied to roadside equipment, wherein, The device includes: The acquisition unit is used to acquire nighttime road images and high-precision map data for the current road segment; The preprocessing unit is used to preprocess the nighttime road image using a preset preprocessing strategy to obtain the bright spot areas in the nighttime road image; The first determining unit is configured to determine the street light area in the nighttime road image based on the nighttime road image and the high-precision map data; The second determining unit is used to determine the street light fault detection result based on the bright spot area in the night road image and the street light area in the night road image; The nighttime road images include multiple images, and the preprocessing unit is specifically used for: The preset preprocessing strategy is used to preprocess each of the nighttime road images to obtain the bright spot areas in each of the nighttime road images; The bright areas in each of the nighttime road images are fused, and the bright areas belonging to streetlights in each of the nighttime road images are determined based on the fusion processing results. The preprocessing unit is specifically used for: Based on the fusion processing results, bright areas that do not belong to streetlights are filtered out to obtain the bright areas that belong to streetlights in each of the nighttime road images. The bright areas that do not belong to streetlights include bright areas of vehicle lights.

8. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 6.

Images