Urban lighting fault positioning method and device

Abstract

The invention discloses an urban lighting fault positioning method and device. The method comprises the following steps: acquiring lighting area images of a plurality of lighting devices in a city; performing fault analysis on the plurality of lighting devices based on the lighting area image, and determining abnormal lighting devices; acquiring position information of the abnormal lighting equipment; lighting equipment fault positioning is completed based on the position information of the abnormal lighting equipment; fault analysis is carried out based on the illumination area image, trace abnormal conditions of the illumination equipment are visually found, preventive maintenance is carried out before the fault really occurs, and adverse effects of the fault on traffic and public safety are avoided.

Description

Technical Field

[0001] The present invention relates to the field of urban lighting fault location, and in particular to a method and device for urban lighting fault location. Background Art

[0002] Today, with the rapid development of urbanization, urban energy-saving lighting equipment, as an important part of urban infrastructure, its stable and reliable working state is of great significance for ensuring traffic safety, enhancing the urban image, and promoting the prosperity of the night economy.

[0003] However, in the urban energy-saving lighting system, there are a large number of energy-saving lighting equipment and they are widely distributed. Timely and accurately locating the faults of energy-saving lighting equipment has always been an important challenge in urban lighting management. Traditional methods for locating faults in urban energy-saving lighting equipment have many limitations. They mainly rely on manual inspections and simple fault alarm systems, and can only detect faults with relatively obvious abnormal degrees, such as the continuous flashing of urban energy-saving lighting equipment. Although these faults are conspicuous, they are often the result of the accumulation of minor fault states of urban energy-saving lighting equipment to a certain extent. In fact, before a fault occurs in urban energy-saving lighting equipment, it usually goes through a series of minor abnormalities. If these minor abnormalities can be detected and handled in a timely manner, preventive maintenance can be carried out before the fault actually occurs, avoiding the adverse impact of the fault on traffic and public safety. However, most of the current detection schemes lack sensitivity and detection strategies for minor abnormalities, making the maintenance and management of street lights often in a passive state.

[0004] Therefore, there is an urgent need for a method and device for urban lighting fault location to solve the above problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems in the above technologies to some extent. For this purpose, the first aspect of the present invention aims to propose a method for urban lighting fault location, which performs fault analysis based on the lighting area image, intuitively discovers minor abnormalities of lighting equipment, and performs preventive maintenance before the fault actually occurs, avoiding the adverse impact of the fault on traffic and public safety.

[0006] The second aspect of the present invention aims to propose a device for urban lighting fault location.

[0007] To achieve the above object, the first aspect embodiment of the present invention proposes a method for urban lighting fault location, including:

[0008] Obtaining lighting area images of a number of lighting equipment in the city;

[0009] Performing fault analysis on a number of lighting equipment based on the lighting area images to determine abnormal lighting equipment;

[0010] Obtain the location information of the abnormal lighting device;

[0011] Based on the location information of the abnormal lighting device, complete the fault location of the lighting device.

[0012] Preferably, it further includes: numbering a number of lighting devices in the urban lighting area and determining the location information of each lighting device.

[0013] Preferably, based on the lighting area image data, perform fault analysis on a number of lighting devices to determine the abnormal lighting device, including:

[0014] Arbitrarily select a lighting device as the target lighting device; obtain the time-domain image of the lighting area of the target lighting device;

[0015] Decompose the time-domain image to obtain the lighting area image dataset of the target lighting device;

[0016] Arbitrarily select a lighting area image in the lighting area image dataset as the target image;

[0017] Perform screening of abnormal pixel points on the target image to obtain a number of initial abnormal pixel points;

[0018] Obtain the reference image of the lighting area of the target lighting device; the pixel points in the reference image correspond one by one to the pixel points in the target image;

[0019] Based on the reference image, screen a number of initial abnormal pixel points to obtain a number of target abnormal pixel points;

[0020] Based on a number of target abnormal pixel points, determine a number of target abnormal areas;

[0021] Based on a number of target abnormal areas, determine the abnormal evaluation coefficient of the target lighting device;

[0022] Traverse all lighting devices and determine the abnormal evaluation coefficient of each lighting device;

[0023] Compare the abnormal evaluation coefficient with the preset abnormal evaluation threshold. When it is determined that the abnormal evaluation coefficient is greater than or equal to the preset abnormal evaluation threshold, determine the lighting device as an abnormal lighting device.

[0024] Preferably, performing screening of abnormal pixel points on the target image to obtain a number of initial abnormal pixel points includes:

[0025] Perform gray processing on the target image to obtain a gray image;

[0026] Obtain the gray value of each pixel point in the gray image;

[0027] Arbitrarily select a pixel point as the target pixel point;

[0028] Taking the target pixel as the center and the preset distance as the radius, determine the first target area;

[0029] Calculate the grayscale mean value of each pixel in the first target area to obtain the first grayscale mean value;

[0030] Calculate the difference between the grayscale value of the target pixel and the first grayscale mean value to obtain the first difference;

[0031] Compare the first difference with the first preset difference threshold. When it is determined that the first difference is greater than or equal to the first preset difference threshold, take the target pixel as the initial abnormal pixel.

[0032] Preferably, based on the reference image, screen a number of initial abnormal pixels to obtain a number of target abnormal pixels, including:

[0033] Calculate the grayscale difference between the initial abnormal pixel and the corresponding pixel in the reference image to obtain the second difference;

[0034] Compare the second difference with the second preset difference threshold. When it is determined that the second difference is greater than or equal to the second preset difference threshold, take the initial abnormal pixel as the target abnormal pixel;

[0035] Traverse all the initial abnormal pixels to obtain a number of target abnormal pixels.

[0036] Preferably, based on a number of target abnormal pixels, determine a number of target abnormal areas, including:

[0037] Cluster the number of target abnormal pixels to obtain a number of initial abnormal areas;

[0038] Obtain the minimum bounding rectangles of the number of initial abnormal areas to obtain a number of minimum bounding rectangles;

[0039] Arbitrarily take an initial abnormal area as the first area;

[0040] Count the number of pixels in the minimum bounding rectangle corresponding to the first area to obtain the first quantity;

[0041] Count the number of target abnormal pixels in the minimum bounding rectangle corresponding to the first area to obtain the second quantity;

[0042] Count the number of pixels outside the minimum bounding rectangle corresponding to the first area to obtain the third quantity;

[0043] Count the number of target abnormal pixels outside the minimum bounding rectangle corresponding to the first area to obtain the fourth quantity;

[0044] Calculate the difference between the first quantity and the second quantity to obtain a third difference;

[0045] Calculate the difference between the third quantity and the fourth quantity to obtain a fourth difference;

[0046] Calculate the absolute value of the difference between the third difference and the fourth difference as the abnormal evaluation value of the first region;

[0047] Traverse all initial abnormal regions to obtain the abnormal evaluation value corresponding to each initial abnormal region;

[0048] Compare the abnormal evaluation value with a preset abnormal evaluation threshold. When it is determined that the abnormal evaluation value is greater than or equal to the preset abnormal evaluation threshold, use the initial abnormal region as the target abnormal region to obtain a number of target abnormal regions.

[0049] Preferably, determining the abnormal evaluation coefficient of the target lighting device based on a number of target abnormal regions includes:

[0050] Obtain the total number of pixel points in a number of target abnormal regions to obtain a fifth quantity;

[0051] Obtain the total number of all pixel points in the target image to obtain a sixth quantity;

[0052] Use the ratio of the fifth quantity to the sixth quantity as the abnormal coefficient corresponding to the target image;

[0053] Traverse all images in the lighting area image dataset to determine the abnormal coefficient corresponding to each lighting area image, and obtain the abnormal coefficient dataset corresponding to the lighting area image dataset;

[0054] Perform a mean evaluation on the abnormal coefficient dataset to determine the abnormal evaluation coefficient of the target lighting device.

[0055] Preferably, before performing a fault analysis on a number of lighting devices based on the lighting area image, it also includes enhancing the lighting area image.

[0056] Preferably, enhancing the lighting area image includes:

[0057] Arbitrarily select a lighting area image;

[0058] Obtain the gray values of each pixel point in the lighting area image;

[0059] Arbitrarily select a pixel point in the gray image as the first target pixel point;

[0060] With the target pixel point as the center and a preset distance as the radius, determine a second target region;

[0061] Arbitrarily select a pixel point in the second target region as the second target pixel point;

[0062] Calculate the gray - level difference between the second target pixel and other pixels in the second target area to obtain a number of differences;

[0063] Sum up and take the average of the number of differences as the gray - level evaluation value of the second target pixel;

[0064] Traverse all pixels in the second target area to obtain the gray - level evaluation value corresponding to each pixel;

[0065] Calculate the absolute value of the difference between the gray - level evaluation values corresponding to any two pixels to obtain a number of absolute values; take the cumulative sum of the number of absolute values as the feature value of the first target pixel;

[0066] Traverse all pixels in the grayscale image to obtain the feature value corresponding to each pixel in the grayscale image;

[0067] Calculate the absolute value of the difference between the feature values corresponding to any two adjacent pixels in the grayscale image to obtain a number of absolute feature differences;

[0068] Compare the absolute feature differences with a preset absolute feature difference threshold, and classify two pixels with absolute feature differences less than or equal to the preset absolute feature difference threshold into one category to obtain a number of pixel classifications;

[0069] Determine a number of image regions based on the number of pixel classifications;

[0070] Calculate the gray - level enhancement coefficient corresponding to each image region;

[0071] Enhance the pixels in each image region based on the gray - level enhancement coefficient corresponding to each image region to obtain the enhanced illumination area image;

[0072] Traverse all the illumination area images to obtain the enhanced illumination area image.

[0073] To achieve the above object, a second - aspect embodiment of the present invention proposes an urban lighting fault location device, including:

[0074] A first acquisition module, configured to acquire illumination area images of a number of lighting devices;

[0075] An analysis module, configured to perform fault analysis on a number of lighting devices based on the illumination area images to determine abnormal lighting devices;

[0076] A second acquisition module, configured to acquire the location information of the abnormal lighting devices;

[0077] A location module, configured to complete the lighting device fault location based on the location information of the abnormal lighting devices.

[0078] The present invention provides a method and device for locating urban lighting faults. By using image analysis technology, it can simultaneously process the images of the lighting areas of several lighting devices. It can quickly screen out abnormal lighting devices from a large number of lighting devices in a short time, greatly saving the fault location time, improving work efficiency, ensuring that faults can be discovered and located in the shortest time, and reducing the duration of urban lighting faults. Based on the images of the lighting areas for fault analysis, it breaks through the limitation of only relying on electrical parameters to judge faults. It can intuitively discover various micro-abnormal conditions of lighting devices. By analyzing these image details, it can accurately determine the potential micro-abnormal conditions of abnormal lighting devices, avoiding positioning deviations caused by the ambiguity of abnormal electrical parameters, and greatly improving the accuracy of fault location. It reduces the large amount of human and material resources consumed by manual inspections. In the past, manual inspections required arranging many staff members and equipping transportation tools, etc., with high costs. This technical solution realizes the automation and intelligence of fault location, reduces the dependence on manpower, enables maintenance personnel to go to the fault location for repair targeted according to the accurate location results, improves the utilization efficiency of maintenance resources, and effectively reduces the overall maintenance cost of the urban lighting system.

[0079] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written specification and the accompanying drawings.

[0080] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the accompanying drawings:

[0082] Figure 1 is a flowchart of a method for locating urban lighting faults according to an embodiment of the present invention;

[0083] Figure 2 is a flowchart of obtaining a plurality of target abnormal pixel points according to an embodiment of the present invention;

[0084] Figure 3 is a block diagram of a device for locating urban lighting faults according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0085] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0086] Example 1

[0087] As Figure 1 shown, an embodiment of the first aspect of the present invention provides a method for locating urban lighting faults, including steps S1 - S4:

[0088] S1: Obtain images of the lighting areas of several lighting devices in the city;

[0089] S2: Based on the images of the lighting areas, perform fault analysis on several lighting devices to determine abnormal lighting devices;

[0090] S3: Obtain the location information of the abnormal lighting devices;

[0091] S4: Complete the fault location of the lighting devices based on the location information of the abnormal lighting devices.

[0092] In this embodiment, the way to obtain the images of the lighting areas of the lighting devices is as follows: Each lighting device is equipped with a monitoring camera, which is used to monitor the lighting area of the lighting device and collect the images of the lighting area of the lighting device.

[0093] The working principle of the above technical solution is: By analyzing the images of the lighting areas of several lighting devices, determine the micro - abnormal conditions existing in the lighting devices, mark the lighting devices with micro - abnormal conditions, and determine them as abnormal lighting devices. Obtain the location information of the abnormal lighting devices, and complete the fault location of the lighting devices based on the location information of the abnormal lighting devices.

[0094] The beneficial effects of the above technical solution are as follows: Using image analysis technology, the images of the lighting areas of several lighting devices can be processed simultaneously; Abnormal lighting devices can be quickly screened out from a large number of lighting devices in a short time, greatly saving the fault location time, improving work efficiency, ensuring that faults can be discovered and located in the shortest time, and reducing the duration of urban lighting faults; Based on the images of the lighting areas for fault analysis, it breaks through the limitation of relying only on electrical parameters to judge faults. It can intuitively discover various micro - abnormal conditions of lighting devices. By analyzing these image details, accurately determine the potential micro - abnormal conditions of abnormal lighting devices, avoiding positioning deviations caused by the ambiguity of abnormal electrical parameters, and greatly improving the accuracy of fault location; Reducing the large amount of human and material resources consumed by manual inspections. In the past, manual inspections required arranging many staff members and equipping transportation tools, etc., with high costs. This technical solution realizes the automation and intelligence of fault location, reduces human dependence, enables maintenance personnel to go to the fault location for repair targeted according to the accurate location results, improves the utilization efficiency of maintenance resources, and effectively reduces the overall maintenance cost of the urban lighting system.

[0095] Example 2

[0096] It further includes: numbering a number of lighting devices in the urban lighting area and determining the location information of each lighting device.

[0097] In this embodiment, the location information includes but is not limited to the longitude and latitude information and geographical location marking information of the lighting device.

[0098] Embodiment 3

[0099] Based on the lighting area image data, perform fault analysis on a number of lighting devices to determine abnormal lighting devices, including:

[0100] Arbitrarily select a lighting device as the target lighting device; obtain the time-domain image of the lighting area of the target lighting device;

[0101] Decompose the time-domain image to obtain the lighting area image dataset of the target lighting device;

[0102] Arbitrarily select a lighting area image in the lighting area image dataset as the target image;

[0103] Screen abnormal pixel points from the target image to obtain a number of initial abnormal pixel points;

[0104] Obtain the reference image of the lighting area of the target lighting device; the pixel points in the reference image correspond one by one to the pixel points in the target image;

[0105] Based on the reference image, screen a number of initial abnormal pixel points to obtain a number of target abnormal pixel points;

[0106] Based on a number of target abnormal pixel points, determine a number of target abnormal areas;

[0107] Based on a number of target abnormal areas, determine the abnormal evaluation coefficient of the target lighting device;

[0108] Traverse all lighting devices to determine the abnormal evaluation coefficient of each lighting device;

[0109] Compare the abnormal evaluation coefficient with the preset abnormal evaluation threshold. When it is determined that the abnormal evaluation coefficient is greater than or equal to the preset abnormal evaluation threshold, determine the lighting device as an abnormal lighting device.

[0110] The working principle of the above technical solution is as follows: Arbitrarily select a lighting device as the target lighting device; obtain the time-domain image of the lighting area of the target lighting device; disassemble the time-domain image to obtain the lighting area image dataset of the target lighting device; arbitrarily select an image of the lighting area in the lighting area image dataset as the target image; screen the target image for abnormal pixel points to obtain a number of initial abnormal pixel points; obtain the reference image of the lighting area of the target lighting device; the pixel points in the reference image correspond one by one to the pixel points in the target image; based on the reference image, screen the number of initial abnormal pixel points to obtain a number of target abnormal pixel points; based on the number of target abnormal pixel points, determine a number of target abnormal areas; based on the number of target abnormal areas, determine the abnormal evaluation coefficient of the target lighting device; traverse all lighting devices to determine the abnormal evaluation coefficient of each lighting device; compare the abnormal evaluation coefficient with the preset abnormal evaluation threshold, and when it is determined that the abnormal evaluation coefficient is greater than or equal to the preset abnormal evaluation threshold, determine the lighting device as an abnormal lighting device.

[0111] The beneficial effects of the above technical solution are as follows: Through image data and automated processing (such as screening of abnormal pixel points and identification of target abnormal areas), the degree of automation of fault detection is greatly improved, the workload of manual inspection and manual fault troubleshooting is reduced, and the efficiency is improved; through the screening of target abnormal pixel points and abnormal areas, it is possible to accurately identify whether there are faults in the lighting device area. This avoids the inefficiency of blindly searching for faults, enables maintenance personnel to quickly locate the problem area, and reduces the maintenance time; by using the time-domain image dataset of the target lighting device, the working state of the lighting device changing over time can be captured, so as to better analyze the fault mode. This dynamic analysis enables the system to detect occasional or periodic faults in a timely manner, rather than relying solely on static images, further improving the accuracy of fault diagnosis; through the one-by-one comparison of the pixel points of the reference image and the target image, abnormal pixel points can be screened out more accurately. This comparison mechanism ensures the accuracy of the system in determining whether a lighting device has a fault, and avoids misjudgment caused by environmental factors or other interference factors.

[0112] Embodiment 4

[0113] Screening the target image for abnormal pixel points to obtain a number of initial abnormal pixel points includes:

[0114] Perform gray-scale processing on the target image to obtain a gray-scale image;

[0115] Obtain the gray-scale values of each pixel point in the gray-scale image;

[0116] Arbitrarily select a pixel point as the target pixel point;

[0117] Taking the target pixel as the center and the preset distance as the radius, determine the first target area;

[0118] Calculate the gray mean value of each pixel in the first target area to obtain the first gray mean value;

[0119] Calculate the difference between the gray value of the target pixel and the first gray mean value to obtain the first difference;

[0120] Compare the first difference with the first preset difference threshold. When it is determined that the first difference is greater than or equal to the first preset difference threshold, take the target pixel as the initial abnormal pixel.

[0121] The working principle of the above technical solution is: perform gray processing on the target image to obtain a gray image; obtain the gray values of each pixel in the gray image; arbitrarily select a pixel as the target pixel; take the target pixel as the center and the preset distance as the radius to determine the first target area; calculate the gray mean value of each pixel in the first target area to obtain the first gray mean value; calculate the difference between the gray value of the target pixel and the first gray mean value to obtain the first difference; compare the first difference with the first preset difference threshold. When it is determined that the first difference is greater than or equal to the first preset difference threshold, take the target pixel as the initial abnormal pixel.

[0122] The beneficial effects of the above technical solution are: by comparing the gray mean value of the target pixel with that of its neighboring pixels, abnormal pixels deviating from the normal gray range can be effectively identified. By calculating the difference and comparing it with the preset threshold, it can be accurately determined whether the target pixel is abnormal, thereby improving the detection accuracy of abnormal pixels; the calculation of the gray mean value takes into account the gray values of multiple pixels in the neighborhood, thereby reducing the influence of possible misjudgments caused by abnormal values of individual pixels. Even under the interference of environmental changes, the system can still stably detect the true abnormal area, enhancing the robustness of the algorithm; by setting different difference thresholds, the judgment criteria for abnormal pixels can be flexibly adjusted. This enables the method to adapt to the requirements of different lighting environments, different devices or different detection conditions, and has strong adaptability; taking the target pixel as the center, defining a preset detection area, and statistically analyzing the gray values within this area. This local detection method can quickly and effectively locate the abnormal area in the image, avoiding redundant processing of the entire image and improving the detection efficiency.

[0123] Embodiment 5

[0124] As Figure 2 shown, based on the reference image, screen a number of initial abnormal pixels to obtain a number of target abnormal pixels, including steps S261 - S263:

[0125] S261: Calculate the grayscale difference between the initial abnormal pixel points and the corresponding pixel points in the reference image to obtain a second difference value;

[0126] S262: Compare the second difference value with a second preset difference threshold. When it is determined that the second difference value is greater than or equal to the second preset difference threshold, regard the initial abnormal pixel points as target abnormal pixel points;

[0127] S263: Traverse all the initial abnormal pixel points to obtain a number of target abnormal pixel points.

[0128] The working principle of the above technical solution is: Calculate the grayscale difference between the initial abnormal pixel points and the corresponding pixel points in the reference image to obtain a second difference value; Compare the second difference value with a second preset difference threshold. When it is determined that the second difference value is greater than or equal to the second preset difference threshold, regard the initial abnormal pixel points as target abnormal pixel points; Traverse all the initial abnormal pixel points to obtain a number of target abnormal pixel points.

[0129] The beneficial effects of the above technical solution are: By calculating the grayscale difference between the initial abnormal pixel points and the corresponding pixel points in the reference image and comparing it with the second preset difference threshold, the true abnormal pixel points can be identified more accurately. Compared with simply relying on the detection of initial abnormal pixel points, this method can reduce misjudgment and missed judgment; As a reference image, the reference image can effectively reduce errors caused by light changes, noise or other external factors, making the screening of abnormal pixel points more reliable. This enables the detection process to run stably under various environmental conditions; By setting different second preset difference thresholds, the screening criteria for abnormal pixel points can be flexibly adjusted to adapt to different scenarios or application requirements.

[0130] Embodiment 6

[0131] Based on a number of target abnormal pixel points, determine a number of target abnormal regions, including:

[0132] Cluster the number of target abnormal pixel points to obtain a number of initial abnormal regions;

[0133] Obtain the minimum bounding rectangles of the number of initial abnormal regions to obtain a number of minimum bounding rectangles;

[0134] Arbitrarily select an initial abnormal region as the first region;

[0135] Count the number of pixel points in the minimum bounding rectangle corresponding to the first region to obtain a first quantity;

[0136] Count the number of target abnormal pixel points in the minimum bounding rectangle corresponding to the first region to obtain a second quantity;

[0137] Count the number of pixels outside the minimum bounding rectangle corresponding to the first region to obtain a third quantity;

[0138] Count the number of target abnormal pixels outside the minimum bounding rectangle corresponding to the first region to obtain a fourth quantity;

[0139] Calculate the difference between the first quantity and the second quantity to obtain a third difference;

[0140] Calculate the difference between the third quantity and the fourth quantity to obtain a fourth difference;

[0141] Calculate the absolute value of the difference between the third difference and the fourth difference as the abnormal evaluation value of the first region;

[0142] Traverse all the initial abnormal regions to obtain the abnormal evaluation value corresponding to each initial abnormal region;

[0143] Compare the abnormal evaluation value with a preset abnormal evaluation threshold. When it is determined that the abnormal evaluation value is greater than or equal to the preset abnormal evaluation threshold, take the initial abnormal region as the target abnormal region to obtain a number of target abnormal regions.

[0144] The working principle of the above technical solution is: clustering a number of target abnormal pixels to obtain a number of initial abnormal regions; by calculating the abnormal evaluation value in the initial abnormal regions, determining the abnormal degree of the initial abnormal regions, and taking the initial abnormal regions with a large abnormal degree as the target abnormal regions to obtain a number of target abnormal regions.

[0145] The beneficial effects of the above technical solution are: by clustering the target abnormal pixels and obtaining the minimum bounding rectangle based on the clustering result, the scattered abnormal pixels can be effectively grouped into relatively concentrated and clear abnormal regions. This method can more accurately identify the abnormal regions, rather than relying solely on single abnormal pixels, reducing the possibility of false detection and missed detection; by calculating the first quantity, the second quantity, the third quantity, the fourth quantity and each difference, a detailed abnormal evaluation can be carried out for each initial abnormal region. This multi-dimensional analysis can not only identify the abnormal regions, but also provide a more accurate basis for subsequent abnormal diagnosis and treatment. The calculation of the abnormal evaluation value can reflect the density and distribution characteristics of abnormal pixels in the region, thus optimizing the screening process of abnormal regions; by calculating the minimum bounding rectangle, the boundary of the abnormal region can be quickly determined, greatly improving the efficiency of abnormal region localization. In the processing of large-scale image data, this method has high real-time performance and stability, and can quickly complete the detection and evaluation of abnormal regions; calculating the minimum bounding rectangle and analyzing the pixels inside and outside the region can effectively exclude the influence of noise in the image and prevent noise points from being misidentified as abnormal regions. By performing fine statistics within the minimum bounding rectangle range, the interference of external noise on the detection of abnormal regions can be reduced.

[0146] Example 7

[0147] Determining an abnormal evaluation coefficient of a target lighting device based on a plurality of target abnormal regions includes:

[0148] Obtaining the total number of pixel points in a plurality of target abnormal regions to obtain a fifth quantity;

[0149] Obtaining the total number of all pixel points in the target image to obtain a sixth quantity;

[0150] Taking the ratio of the fifth quantity to the sixth quantity as the abnormal coefficient corresponding to the target image;

[0151] Traversing all images in the lighting area image dataset, determining the abnormal coefficient corresponding to each lighting area image, and obtaining an abnormal coefficient dataset corresponding to the lighting area image dataset;

[0152] Performing a mean evaluation on the abnormal coefficient dataset to determine the abnormal evaluation coefficient of the target lighting device.

[0153] The working principle of the above technical solution is: obtaining the total number of pixel points in a plurality of target abnormal regions to obtain a fifth quantity; obtaining the total number of all pixel points in the target image to obtain a sixth quantity; taking the ratio of the fifth quantity to the sixth quantity as the abnormal coefficient corresponding to the target image; traversing all images in the lighting area image dataset, determining the abnormal coefficient corresponding to each lighting area image, and obtaining an abnormal coefficient dataset corresponding to the lighting area image dataset; performing a mean evaluation on the abnormal coefficient dataset to determine the abnormal evaluation coefficient of the target lighting device.

[0154] The beneficial effects of the above technical solution are: by calculating the ratio of the pixel points in the target abnormal region to the total number of pixel points in the entire image, the degree of abnormality can be quantified, so as to more accurately evaluate the operating state of the lighting device. This method can effectively reflect the abnormal performance of the lighting device in the image and provide an evaluation result with a quantitative index; by traversing all images in the lighting area image dataset and calculating the abnormal coefficient of each image, an abnormal coefficient dataset can be finally obtained, which can reflect the overall performance of the device at different times and in different scenarios. Performing a mean evaluation on these data helps to evaluate the stability and health status of the device during long-term operation.

[0155] Example 8

[0156] Before performing a fault analysis on a plurality of lighting devices based on the lighting area image, it further includes enhancing the lighting area image.

[0157] Example 9

[0158] Enhancing the lighting area image includes:

[0159] Randomly select an image of the illumination area;

[0160] Obtain the gray values of each pixel point in the image of the illumination area;

[0161] Randomly select a pixel point in the grayscale image as the first target pixel point;

[0162] Taking the target pixel point as the center and a preset distance as the radius, determine the second target area;

[0163] Randomly select a pixel point in the second target area as the second target pixel point;

[0164] Calculate the gray difference between the second target pixel point and other pixel points in the second target area to obtain a number of differences;

[0165] Sum up and take the average of the number of differences as the gray evaluation value of the second target pixel point;

[0166] Traverse all pixel points in the second target area to obtain the gray evaluation value corresponding to each pixel point;

[0167] Calculate the absolute value of the difference between the gray evaluation values corresponding to any two pixel points to obtain a number of absolute values; take the cumulative sum of the number of absolute values as the eigenvalue of the first target pixel point;

[0168] Traverse all pixel points in the grayscale image to obtain the eigenvalue corresponding to each pixel point in the grayscale image;

[0169] Calculate the absolute value of the difference between the eigenvalues corresponding to any two adjacent pixel points in the grayscale image to obtain a number of absolute eigenvalue differences;

[0170] Compare the absolute eigenvalue difference with a preset absolute eigenvalue difference threshold, and classify two pixel points with the absolute eigenvalue difference less than or equal to the preset absolute eigenvalue difference threshold into one category to obtain a number of pixel point classifications;

[0171] Determine a number of image areas based on the number of pixel point classifications;

[0172] Calculate the gray enhancement coefficient corresponding to each image area;

[0173] Enhance the pixel points of each image area based on the gray enhancement coefficient corresponding to each image area to obtain the enhanced image of the illumination area;

[0174] Traverse all images of the illumination area to obtain the enhanced image of the illumination area.

[0175] In this embodiment,

[0176]

[0177] Among them, T i represents the gray-scale enhancement coefficient of the i-th image region; k i represents the average gray scale of all pixel points in the i-th image region; v i represents the average gradient magnitude of all pixel points in the i-th image region; represents the average gray scale of pixel points in all image regions adjacent to the i-th image region; represents the average gradient magnitude of pixel points in all image regions adjacent to the i-th image region; Sigmoid represents the normalization function.

[0178] In this embodiment,

[0179]

[0180] Among them, B i,j represents the enhanced gray value of the j-th pixel point in the i-th image region; b i,j represents the initial gray value of the j-th pixel point in the i-th image region; represents the floor function.

[0181] The working principle of the above technical solution is as follows: By classifying as many categories as possible for each pixel point in the illumination area image, the more categories and the finer the classification, the more accurate the corresponding gray-scale enhancement coefficient; The illumination area image is divided into several image regions; Calculate the gray-scale enhancement coefficient corresponding to each image region, and enhance the pixel points of each image region based on the gray-scale enhancement coefficient corresponding to each image region to obtain the enhanced illumination area image.

[0182] The beneficial effects of the above technical solution are as follows: By calculating the gray-scale evaluation value of each pixel point and classifying pixel points according to feature differences, the local contrast of the image can be effectively improved, making the image details clearer. This is particularly important for scenarios where it is necessary to carefully observe the working state of lighting devices or abnormal areas, and it can help better identify important information in the image; By calculating the gray-scale enhancement coefficient of the image area and performing enhancement processing, the brightness and contrast of the image can be improved. Especially in environments with insufficient lighting or complex backgrounds, the visibility of the image can be significantly improved. This is of great significance for image processing and analysis, especially for the state evaluation of the lighting area; This method not only focuses on the gray-scale value of individual pixel points but also optimizes the overall image effect through the contrast differences in local areas, thus achieving a balance between local enhancement and global consistency. In this way, while improving the local clarity of the image, it can avoid image distortion caused by over-enhancement; By calculating the gray-scale feature differences and classifying pixel points, the image can be accurately divided into regions. Each region is processed according to a specific enhancement coefficient, effectively avoiding over-enhancement or under-enhancement that may be caused by global enhancement, and thus obtaining a more balanced enhancement effect.

[0183] As Figure 3 shown, the second aspect embodiment of the present invention proposes an urban lighting fault location device, including:

[0184] A first acquisition module, configured to acquire images of the lighting areas of a plurality of lighting devices;

[0185] An analysis module, configured to perform fault analysis on a plurality of lighting devices based on the images of the lighting areas to determine abnormal lighting devices;

[0186] A second acquisition module, configured to acquire the location information of the abnormal lighting devices;

[0187] A location module, configured to complete the fault location of the lighting devices based on the location information of the abnormal lighting devices.

[0188] The working principle of the above technical solution is as follows: By analyzing the images of the lighting areas of a plurality of lighting devices, the micro-abnormal conditions existing in the lighting devices are determined, the lighting devices with micro-abnormal conditions are marked and determined as abnormal lighting devices, the location information of the abnormal lighting devices is acquired, and the fault location of the lighting devices is completed based on the location information of the abnormal lighting devices.

[0189] The beneficial effects of the above technical solution are as follows: By using image analysis technology, the images of the lighting areas of several lighting devices can be processed simultaneously; abnormal lighting devices can be quickly screened out from a large number of lighting devices in a short time, greatly saving the fault location time, improving work efficiency, ensuring that faults can be discovered and located within the shortest time, and reducing the duration of urban lighting faults; based on the images of the lighting areas for fault analysis, it breaks through the limitation of relying solely on electrical parameters to judge faults. It can intuitively detect various micro-abnormal conditions of lighting devices, and through the analysis of these image details, accurately determine the potential micro-abnormal conditions of abnormal lighting devices, avoiding positioning deviations caused by the ambiguity of abnormal electrical parameters, and greatly improving the accuracy of fault location; it reduces the large amount of human and material resources consumed by manual inspections. In the past, manual inspections required arranging many staff members and equipping transportation vehicles, etc., with high costs. This technical solution realizes the automation and intelligence of fault location, reduces the dependence on manpower, enables maintenance personnel to go to the fault location for repair targeted according to the accurate location results, improves the utilization efficiency of maintenance resources, and effectively reduces the overall maintenance cost of the urban lighting system.

[0190] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A method for locating urban lighting faults, characterized in that, Including: Obtaining illumination area images of several lighting devices within a city; Performing fault analysis on several lighting devices based on the illumination area images to determine abnormal lighting devices; Obtaining the location information of the abnormal lighting devices; Completing the fault location of the lighting devices based on the location information of the abnormal lighting devices.

2. The urban lighting fault location method according to claim 1, wherein, Before obtaining the operation data of several lighting devices, it further includes: numbering several lighting devices in the urban lighting area and determining the location information of each lighting device.

3. The urban lighting fault location method according to claim 1, characterized in that, Performing fault analysis on several lighting devices based on the illumination area images to determine abnormal lighting devices, including: Arbitrarily selecting one lighting device as the target lighting device; obtaining the time-domain image of the illumination area of the target lighting device; Disassembling the time-domain image to obtain an illumination area image dataset of the target lighting device; Arbitrarily selecting one illumination area image in the illumination area image dataset as the target image; Performing screening of abnormal pixel points on the target image to obtain several initial abnormal pixel points; Obtaining a reference image of the illumination area of the target lighting device; the pixel points in the reference image correspond one by one to the pixel points in the target image; Performing screening on several initial abnormal pixel points based on the reference image to obtain several target abnormal pixel points; Determining several target abnormal areas based on several target abnormal pixel points; Determining the abnormal evaluation coefficient of the target lighting device based on several target abnormal areas; Traversing all lighting devices to determine the abnormal evaluation coefficient of each lighting device; Comparing the abnormal evaluation coefficient with a preset abnormal evaluation threshold, and when it is determined that the abnormal evaluation coefficient is greater than or equal to the preset abnormal evaluation threshold, determining the lighting device as an abnormal lighting device.

4. The urban lighting fault location method according to claim 3, characterized in that Performing screening of abnormal pixel points on the target image to obtain several initial abnormal pixel points, including: Performing grayscale processing on the target image to obtain a grayscale image; Obtaining the grayscale values of each pixel point in the grayscale image; Arbitrarily selecting one pixel point as the target pixel point; Taking the target pixel point as the center and a preset distance as the radius to determine the first target area; Calculating the grayscale mean value of each pixel point in the first target area to obtain the first grayscale mean value; Calculating the difference between the grayscale value of the target pixel point and the first grayscale mean value to obtain the first difference; Comparing the first difference with a first preset difference threshold, and when it is determined that the first difference is greater than or equal to the first preset difference threshold, taking the target pixel point as an initial abnormal pixel point.

5. The urban lighting fault location method according to claim 4, wherein, Performing screening on several initial abnormal pixel points based on the reference image to obtain several target abnormal pixel points, including: Calculating the grayscale difference between the initial abnormal pixel point and the corresponding pixel point in the reference image to obtain the second difference; Comparing the second difference with a second preset difference threshold, and when it is determined that the second difference is greater than or equal to the second preset difference threshold, taking the initial abnormal pixel point as a target abnormal pixel point; Traversing all initial abnormal pixel points to obtain several target abnormal pixel points.

6. The urban lighting fault location method according to claim 5, wherein Determining several target abnormal areas based on several target abnormal pixel points, including: Clustering the several target abnormal pixel points to obtain several initial abnormal areas; Obtain the minimum bounding rectangles of several initial abnormal regions to get several minimum bounding rectangles; Arbitrarily select an initial abnormal region as the first region; Count the number of pixel points in the minimum bounding rectangle corresponding to the first region to get the first quantity; Count the number of target abnormal pixel points in the minimum bounding rectangle corresponding to the first region to get the second quantity; Count the number of pixel points outside the minimum bounding rectangle corresponding to the first region to get the third quantity; Count the number of target abnormal pixel points outside the minimum bounding rectangle corresponding to the first region to get the fourth quantity; Calculate the difference between the first quantity and the second quantity to get the third difference; Calculate the difference between the third quantity and the fourth quantity to get the fourth difference; Calculate the absolute value of the difference between the third difference and the fourth difference as the abnormal evaluation value of the first region; Traverse all the initial abnormal regions to get the abnormal evaluation value corresponding to each initial abnormal region; Compare the abnormal evaluation value with a preset abnormal evaluation threshold. When it is determined that the abnormal evaluation value is greater than or equal to the preset abnormal evaluation threshold, take the initial abnormal region as the target abnormal region to get several target abnormal regions.

7. The urban lighting fault location method according to claim 6, wherein Determine the abnormal evaluation coefficient of the target lighting device based on several target abnormal regions, including: Obtain the total number of pixel points in several target abnormal regions to get the fifth quantity; Obtain the total number of all pixel points in the target image to get the sixth quantity; Take the ratio of the fifth quantity to the sixth quantity as the abnormal coefficient corresponding to the target image; Traverse all the images in the lighting area image dataset to determine the abnormal coefficient corresponding to each lighting area image, and get the abnormal coefficient dataset corresponding to the lighting area image dataset; Perform a mean evaluation on the abnormal coefficient dataset to determine the abnormal evaluation coefficient of the target lighting device.

8. The urban lighting fault location method according to claim 1, wherein, Before performing fault analysis on several lighting devices based on the lighting area image, it also includes enhancing the lighting area image.

9. The urban lighting fault location method according to claim 8, wherein, Enhancing the lighting area image includes: Arbitrarily select a lighting area image; Obtain the gray values of each pixel point in the lighting area image; Arbitrarily select a pixel point in the gray image as the first target pixel point; Taking the target pixel point as the center and a preset distance as the radius, determine the second target region; Arbitrarily select a pixel point in the second target region as the second target pixel point; Calculate the gray differences between the second target pixel point and other pixel points in the second target region to get several differences; Sum and average several differences as the gray evaluation value of the second target pixel point; Traverse all the pixel points in the second target region to get the gray evaluation value corresponding to each pixel point; Calculate the absolute value of the difference between the gray evaluation values corresponding to any two pixel points to get several absolute values; take the cumulative sum of several absolute values as the eigenvalue of the first target pixel point; Traverse all the pixel points in the gray image to get the eigenvalue corresponding to each pixel point in the gray image; Calculate the absolute value of the difference between the eigenvalues corresponding to any two adjacent pixel points in the gray image to get several absolute feature differences; Compare the absolute feature difference with a preset absolute feature difference threshold, and classify two pixel points with an absolute feature difference less than or equal to the preset absolute feature difference threshold into one category to obtain several pixel point classifications; Determine several image regions based on the several pixel point classifications; Calculate the gray scale enhancement coefficient corresponding to each image region; Enhance the pixel points of each image region based on the gray scale enhancement coefficient corresponding to each image region to obtain an enhanced illumination region image; Traverse all the illumination region images to obtain the enhanced illumination region image.

10. An urban lighting fault location device applying the urban lighting fault location method according to any one of claims 1-9, characterized in that, including: A first acquisition module for acquiring illumination region images of several lighting devices; An analysis module for performing fault analysis on several lighting devices based on the illumination region images to determine abnormal lighting devices; A second acquisition module for acquiring the position information of the abnormal lighting devices; A positioning module for completing the fault positioning of the lighting devices based on the position information of the abnormal lighting devices.

Images