Multi-terminal cooperative road illumination comprehensive evaluation method and system

Abstract

The application discloses a multi-terminal cooperative road illumination comprehensive evaluation method and system. The method comprises the following steps: constructing a street lamp geographic coordinate database; acquiring street lamp illumination values, image gray scale features and time stamps collected by detection devices on different vehicles; identifying and removing interference spectrum to obtain multi-vehicle detection data after interference removal; verifying the multi-vehicle detection data after interference removal based on a correlation coefficient between the street lamp illumination values and the image average gray scale values and a spectrum relative coefficient corresponding to the street lamp illumination values to determine effective multi-vehicle detection data; determining the weight of the effective multi-vehicle detection data based on the street lamp geographic coordinate database; determining a comprehensive illumination value by combining the effective multi-vehicle detection data with the corresponding weight; and determining the state of the street lamp according to comparative analysis of the comprehensive illumination value and historical data to update a street lamp state file. The method can realize accurate monitoring and early warning of street lamp performance degradation.

Description

Technical Field

[0001] This invention relates to a comprehensive road illumination assessment method, and more specifically to a multi-terminal collaborative comprehensive road illumination assessment method and system. Background Technology

[0002] With the increasing popularity of smart city concepts, efficient lighting detection technology is an essential component in building intelligent urban management systems. However, current lighting detection technologies have several limitations, primarily manifested in the limitations of single-sensor detection, the isolation of individual detections, and the disconnect between actual visual perception and numerical measurement. First, traditional illuminance sensor detection methods are easily affected by ambient light interference, such as oncoming vehicle headlights or building lighting, increasing the possibility of misjudgments. Second, the main drawback of existing technologies lies in the isolation of individual detections, including deficiencies in both the temporal and spatial dimensions. Specifically, a single detection can only provide instantaneous information and cannot capture intermittent faults in streetlights, such as start-up delays or power fluctuations. Furthermore, the lack of statistical analysis of historical data from the same road segment makes it difficult to establish reliable benchmarks for streetlight condition assessment, resulting in inaccurate assessment results.

[0003] Furthermore, existing solutions fail to fully utilize the data association and cumulative analysis capabilities of multi-vehicle collaboration, meaning they miss the opportunity to improve detection accuracy through large-sample statistics. Simultaneously, current detection methods mostly focus on measuring illuminance values, neglecting the significant impact of light source distribution uniformity on driver visual perception. Due to the lack of multi-vehicle perspective fusion mechanisms, these methods cannot comprehensively evaluate the actual lighting effect of streetlights, especially at different angles and times.

[0004] Finally, regarding the assessment of streetlight condition, existing technologies lack characterization of continuity and gradual changes. Streetlight degradation and failure typically occur gradually, but existing technologies struggle to accurately track this process. In particular, there is a lack of an effective long-term multi-vehicle tracking mechanism to construct a time-series model of streetlight performance degradation, and sufficient correlation analysis methods are also lacking when processing detection data from different time points on the same road segment. These problems limit the improvement of streetlight maintenance efficiency and service quality, indicating a need for a new, comprehensive solution to overcome these challenges.

[0005] Therefore, it is necessary to design a new method based on multi-vehicle collaborative multi-sensor and vision fusion technology to achieve accurate monitoring and early warning of street light performance degradation. This would solve the problems of existing technologies lacking multi-vehicle collaborative monitoring mechanisms and comprehensive spatiotemporal data analysis, which leads to large random errors in street light status detection, inability to effectively capture the gradual process of brightness decay, and a single visual evaluation perspective. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for comprehensive evaluation of road illumination through multi-terminal collaboration.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a multi-terminal collaborative road illumination comprehensive evaluation method, comprising:

[0008] Construct a geographic coordinate database for streetlights;

[0009] The system acquires street light illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data.

[0010] Interference spectra in the detection data of the multiple vehicles are identified and removed to obtain interference-free detection data of the multiple vehicles.

[0011] The detection data of the multi-vehicles after removing interference is verified based on the correlation coefficient between the street light illuminance value and the average gray value of the image, as well as the relative coefficient of the spectrum corresponding to the street light illuminance value, in order to determine the effective detection data of the multi-vehicles.

[0012] The weights of the effective detection data for the multiple vehicles are determined based on the street light geographic coordinate database.

[0013] The comprehensive illuminance value is determined by combining the effective detection data of the multiple vehicles with the corresponding weights.

[0014] Based on the comparative analysis of the comprehensive illuminance value and historical data, the status of the streetlights is determined in order to update the streetlight status file.

[0015] A further technical solution is as follows: the identification and removal of interference spectra from the detection data of the multiple vehicles to obtain interference-free detection data of the multiple vehicles includes:

[0016] The spectral similarity of the detection data of the multiple vehicles is calculated. The detection data corresponding to the similarity that meets the requirements is confirmed as the real signal, and the detection data corresponding to the similarity that does not meet the requirements is confirmed as the interference signal. The interference signal is removed to obtain the multi-vehicle detection data with interference removed.

[0017] The further technical solution is as follows: the multi-vehicle detection data after interference removal is verified based on the correlation coefficient between the street light illuminance value and the average gray value of the image, and the relative coefficient of the spectrum corresponding to the street light illuminance value, in order to determine the effective detection data of the multi-vehicles, including:

[0018] The effectiveness of the multi-vehicle detection data after removing interference is verified based on the correlation coefficient between the street light illuminance value and the average gray value of the image, so as to determine the first effective data;

[0019] The spectral relative coefficients corresponding to the street light illuminance values ​​are calculated based on the first valid data to determine the valid detection data for multiple vehicles.

[0020] The further technical solution is as follows: the effectiveness of the multi-vehicle detection data after removing interference is verified based on the correlation coefficient between the street light illuminance value and the average gray value of the image, in order to determine the first valid data, including:

[0021] For each vehicle, the correlation coefficient between the street light illuminance value and the average gray value of the image is calculated based on the ratio of covariance to standard deviation of the detection data to measure the internal consistency of the detection data for a single vehicle. For multiple vehicles, within the same time period, the correlation coefficient between the street light illuminance value and the average gray value of the image is calculated based on the ratio of covariance to standard deviation of the detection data, and the correlation coefficients calculated for each vehicle are compared to measure the consistency and reliability of the detection data for multiple vehicles and determine the first valid data.

[0022] Specifically, when the correlation coefficient of a vehicle deviates from the correlation coefficients of other vehicles, the weight of that vehicle is reduced.

[0023] The further technical solution is as follows: The calculation of the spectral relative coefficient corresponding to the streetlight illuminance value based on the first valid data to determine the valid detection data for multiple vehicles includes:

[0024] For the first valid data, calculate the product of the spectral response and the exponentially decaying interference intensity function within the current time window to obtain the spectral relative coefficient corresponding to the street light illuminance value;

[0025] The relationship between the spectral relative coefficient corresponding to the street light illuminance value and a set threshold is used to determine the effective detection data for multiple vehicles.

[0026] The further technical solution is as follows: determining the weights of the effective detection data of the multiple vehicles based on the street light geographic coordinate database includes:

[0027] When different vehicles pass through the same location, the detection data of the multiple vehicles are automatically identified and associated based on the street light geographic coordinate database and a GPS matching algorithm.

[0028] Within a specific time window, weights are assigned based on the temporal order of the valid detection data of the multiple vehicles to obtain time weights;

[0029] The spatial weights are obtained by assigning weights based on the distance between the vehicle and the standard street light detection point;

[0030] The reliability weight is obtained by assigning weights based on the historical detection accuracy of the vehicle.

[0031] The further technical solution is as follows: The acquisition of streetlight illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data includes:

[0032] The sliding window length is automatically adjusted based on traffic density, and the sampling frequency of key road sections is adjusted accordingly.

[0033] The further technical solution is as follows: the determination of the comprehensive illuminance value by combining the effective detection data of the multiple vehicles with corresponding weights includes:

[0034] The valid detection data for each vehicle are weighted and summed according to the aforementioned weights to obtain a weighted detection value;

[0035] The instantaneous state value of the street light is obtained by averaging the weighted detection values ​​of all vehicles.

[0036] The instantaneous state value, historical trend analysis value, and consistency evaluation value of the street light are combined according to their respective weighting coefficients to obtain the comprehensive illuminance value.

[0037] The further technical solution is as follows: The step of determining the street light status based on the comparative analysis of the comprehensive illuminance value and historical data, in order to update the street light status file, includes:

[0038] The judgment threshold is determined based on the historical data and current environmental factors. The threshold is dynamically adjusted by combining the average and standard deviation of historical data with the weighted sum of environmental impact factors, and continuously updated using a sliding window mechanism to adapt to environmental changes.

[0039] The status of the streetlights is determined by comparing the comprehensive illuminance value with the judgment threshold, so as to update the streetlight status file.

[0040] This invention also provides a multi-terminal collaborative road illumination comprehensive evaluation system, including:

[0041] Building unit, used to build street light geographic coordinate database;

[0042] The acquisition unit is used to acquire street light illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data.

[0043] An identification and elimination unit is used to identify and eliminate interference spectra in the detection data of the multiple vehicles to obtain interference-free detection data of the multiple vehicles.

[0044] The validity determination unit is used to verify the interference-removed multi-vehicle detection data based on the correlation coefficient between the street light illuminance value and the average gray value of the image and the spectral relative coefficient corresponding to the street light illuminance value, so as to determine the valid detection data of the multi-vehicle.

[0045] A weight determination unit is used to determine the weights of the effective detection data of the multiple vehicles based on the street light geographic coordinate database.

[0046] The fusion unit is used to determine the comprehensive illuminance value by combining the effective detection data of the multiple vehicles with corresponding weights.

[0047] The comparison and analysis unit is used to determine the status of the streetlights based on the comparison and analysis of the comprehensive illuminance value and historical data, so as to update the streetlight status file.

[0048] The advantages of this invention compared to existing technologies are as follows: This invention constructs a street light geographic coordinate database, combines illuminance values, image grayscale features, and timestamp information collected from detection devices of different vehicles, and employs multi-vehicle collaborative multi-sensor and visual fusion technology to identify and eliminate interference spectra in the detection data. The validity of the data is verified based on the correlation coefficient between illuminance values ​​and average image grayscale values, as well as the relative coefficient of the spectrum corresponding to the street light illuminance values. Appropriate weights are assigned according to the geographical location of the street lights to calculate the comprehensive illuminance value. By comparing and analyzing with historical data, the street light status is accurately determined and the status file is updated, thereby achieving precise monitoring and early warning of street light performance degradation. This method solves the problems of insufficient multi-vehicle collaborative monitoring mechanisms and inadequate spatiotemporal data analysis in existing technologies, effectively reduces random errors, captures the gradual process of brightness decay, and overcomes the limitations of a single visual evaluation perspective, providing a more comprehensive and accurate street light status detection solution.

[0049] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart illustrating the multi-terminal collaborative road illumination comprehensive evaluation method provided in this embodiment of the invention;

[0052] Figure 2 This is a schematic diagram of multi-vehicle detection data provided in an embodiment of the present invention. Figure 1 ;

[0053] Figure 3 This is a schematic diagram of multi-vehicle detection data provided in an embodiment of the present invention. Figure 2 ;

[0054] Figure 4 This is a schematic diagram of multi-vehicle detection data provided in an embodiment of the present invention. Figure 3 ;

[0055] Figure 5 A schematic diagram of the fusion process provided in an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of the comprehensive illuminance values ​​provided in an embodiment of the present invention;

[0057] Figure 7 A schematic diagram of historical data provided in the embodiments of the present invention;

[0058] Figure 8 This is a schematic diagram illustrating the brightness change during vehicle activation detection according to an embodiment of the present invention;

[0059] Figure 9 A schematic block diagram of a multi-terminal collaborative road illumination comprehensive evaluation system provided in an embodiment of the present invention;

[0060] Figure 10 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0061] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0063] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0064] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0065] Please see Figure 1 , Figure 1 This is a schematic flowchart illustrating a multi-terminal collaborative road illumination comprehensive evaluation method provided in an embodiment of the present invention. This method is applied in a server. The server interacts with detection devices on different vehicles and terminals, collecting streetlight illuminance values, image grayscale features, and timestamps by integrating detection devices on multiple vehicles. Spectral analysis is used to eliminate interference signals, ensuring data accuracy and reliability. Based on a streetlight geographic coordinate database, the method uses a GPS matching algorithm to associate data from different vehicles at the same location. It combines time weight, spatial weight, and confidence weight to weight the valid detection data to determine the comprehensive illuminance value. By comparing the comprehensive illuminance value with historical data, the judgment threshold is dynamically adjusted and the streetlight status file is updated, achieving accurate monitoring and early warning of streetlight performance degradation. This method solves the problems of large random errors, inaccurate brightness attenuation capture, and a single visual evaluation angle caused by the lack of a multi-vehicle collaborative monitoring mechanism and comprehensive spatiotemporal data analysis in existing technologies, greatly improving the accuracy and reliability of streetlight status detection.

[0066] Figure 1 This is a flowchart illustrating the multi-terminal collaborative road illumination comprehensive evaluation method provided in this embodiment of the invention. Figure 1 As shown, the method includes the following steps S110 to S170.

[0067] S110. Construct a geographic coordinate database for streetlights.

[0068] In this embodiment, the street light geographic coordinate database refers to a systematic dataset that records in detail the precise geographic location information and related attributes of each street light within the coverage detection area. Each street light is assigned a unique ID and corresponds to a precise GPS coordinate, enabling accurate identification and location of each street light. Constructing such a database is the foundation for realizing a multi-vehicle collaborative road illumination comprehensive evaluation method, providing the necessary prerequisites for subsequent data acquisition, spatiotemporal matching, and multi-source data fusion.

[0069] Specifically, building a street light geographic coordinate database includes the following steps:

[0070] First, a detailed on-site survey of all streetlights within the target area is required, recording the location information of each streetlight. This information can be obtained directly through high-precision GPS equipment, or from existing streetlight location data obtained from urban planning or municipal departments.

[0071] The collected street light location information is entered into the database management system, and each street light is assigned a unique identifier (ID). This ID not only helps distinguish different street lights, but also serves as an important basis for subsequent data association and analysis.

[0072] In addition to basic geographic location information, a series of attributes can be defined for each street light, such as installation date, bulb type, and wattage. This additional information helps to provide a more comprehensive understanding of the street light's operating status and performance trends.

[0073] The street light geographic coordinate database needs to be maintained and updated regularly to reflect any new, removed, or modified street lights. This typically involves collaboration with municipal authorities to ensure the information in the database is always up-to-date.

[0074] Ultimately, the constructed street light geographic coordinate database will be integrated with other systems (such as vehicle-mounted detection equipment and central servers) to support multi-vehicle collaborative road illumination assessment. Through GPS matching algorithms, detection data from different vehicles at the same location can be automatically identified and correlated, thereby establishing a multi-source detection profile for the street light and providing solid data support for subsequent comprehensive analysis.

[0075] In summary, the construction of a street light geographic coordinate database is crucial for achieving efficient and accurate monitoring of road lighting status. It not only improves the efficiency of data processing but also provides strong technical support for accurately locating and resolving street light faults.

[0076] S120. Obtain street light illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data.

[0077] In this embodiment, multi-vehicle detection data refers to information related to streetlight illumination collected from different vehicles equipped with specific detection devices (including illuminance sensors, cameras, GPS positioning modules, etc.). This data is acquired through multi-vehicle collaboration, aiming to more accurately assess the operational status of streetlights by fusing and analyzing data from different time points and spatial locations. Specifically, multi-vehicle detection data mainly includes the following:

[0078] Streetlight illuminance value: This data is directly measured by illuminance sensors installed on vehicles, representing the light intensity of the area where a streetlight is located at a specific time. This value is usually measured in lux, and for the same streetlight, the measured illuminance value may vary because different vehicles may be in different positions or at different angles.

[0079] Image grayscale features: The camera captures the scene outside the windshield, especially including streetlights, and then image processing techniques are used to extract the grayscale features of the image. This step is mainly to reflect the road surface brightness as perceived by the driver. Grayscale features can be quantified by calculating the average grayscale value of the pixels in the image, providing another perspective besides illuminance values ​​to evaluate the actual lighting effect of the streetlights.

[0080] Timestamp: Each data point is accompanied by a precise timestamp to identify the specific time the data was collected. This is crucial for subsequent time series analysis because it allows the system to arrange data from different vehicles in chronological order for comparison and fusion analysis.

[0081] Geographic location information: The exact location of the vehicle is recorded using a GPS positioning module at each data collection point. This is crucial for determining which vehicle inspected which streetlight at which location. Geographic location information not only helps correlate data from different vehicles but also forms the basis for building a geographic coordinate database for streetlights.

[0082] Data Fusion and Validation: After receiving data from multiple vehicles, the system first performs preliminary processing, including removing obvious outliers and interference. Next, based on the aforementioned principles of time weighting, spatial weighting, and credibility weighting, a weighted average is calculated for each group of data to generate a comprehensive state assessment value. This process also includes calculating the correlation between illumination values ​​and image grayscale values ​​to further validate the data's validity.

[0083] In summary, in this embodiment, the "multi-vehicle detection data" is not merely a collection of isolated numerical values, but a complex, multi-layered information system. It includes physical measurement results (such as illuminance values), environmental perception information (such as image grayscale features), a temporal dimension (such as timestamps), and spatial location (such as geographic location information). Through scientific and reasonable data fusion and analysis methods, this data can be effectively transformed into an accurate assessment of the streetlight's operational status, thereby supporting the intelligent upgrade of the urban lighting management system.

[0084] In this embodiment, the length of the sliding window is automatically adjusted according to the traffic flow density, and the sampling frequency of the key road section is adjusted accordingly.

[0085] Specifically, changes in traffic density across different time periods affect the data quality of streetlight status detection. During peak hours, traffic is dense and data updates rapidly; while during off-peak hours, traffic is sparse and data updates are slow. Therefore, a mechanism needs to be designed to dynamically adjust the sliding window length to adapt to different traffic density conditions.

[0086] Real-time traffic flow information for each road segment is obtained through GPS positioning and wireless communication modules.

[0087] The average traffic density at different times is analyzed based on historical data, and a threshold (such as high density, normal, low density) is set.

[0088] When traffic density is high, use a shorter sliding window (e.g., 2 minutes) to capture more granular temporal changes and ensure a fast response.

[0089] Under normal traffic density conditions, a medium-length sliding window (e.g., 5 minutes) is used to balance timeliness and stability.

[0090] If traffic density is low, extend the sliding window to a longer period (e.g., 10 minutes or more) to ensure sufficient data for analysis.

[0091] Certain urban areas may have higher requirements for street lighting, such as commercial districts, areas near schools, or accident-prone locations. These areas are known as "critical road sections" and require higher monitoring accuracy and faster problem response times.

[0092] Based on urban planning documents, traffic accident reports, resident feedback, and other materials, determine which areas are considered key road sections.

[0093] For known key road sections, the system will prioritize dispatching more vehicles for data collection, or increase the data upload frequency of vehicles passing through the area.

[0094] This also includes installing additional fixed sensor devices to supplement the insufficient data from mobile devices.

[0095] Dynamic adjustment mechanism: In addition to the preset key road sections, the system should also have the ability to learn and dynamically adjust the list of key road sections and their corresponding sampling frequency according to the latest road condition changes (such as new construction projects, temporary activities, etc.).

[0096] Through the above measures, this system can not only maintain efficient data processing capabilities under different traffic flow conditions, but also provide enhanced service guarantees for special needs. Specifically:

[0097] The parameter settings can be flexibly adjusted according to the actual situation, reducing data deviations caused by a single standard.

[0098] Especially in key road sections, it can identify and resolve problems more quickly, improving public safety.

[0099] This avoids excessive consumption of computing resources when unnecessary, and achieves efficient resource allocation.

[0100] In summary, this adaptive adjustment scheme based on traffic density and key road segment characteristics greatly enhances the flexibility and practicality of the entire street light monitoring system, providing strong technical support for smart city management.

[0101] The limitation of traditional single-vehicle detection lies in the fact that its sliding window is restricted to the travel time and speed of a single vehicle, resulting in limited data volume and potentially a lack of comprehensiveness. In contrast, multi-vehicle collaboration offers an innovative breakthrough. By establishing a dynamic sliding window mechanism based on the time sequence of multiple vehicles, richer temporal dimension data can be obtained.

[0102] When vehicle A detects a street light within 0 to 5 minutes, and vehicle B also detects the same street light within 3 to 8 minutes, the system will merge the data from both vehicles within the overlapping time period of 3 to 5 minutes for verification and analysis.

[0103] The sliding window length is dynamically adjusted based on the number and density of passing vehicles. For example, a shorter window (e.g., 2 minutes) is used when traffic is heavy to achieve higher temporal resolution, while a longer window (e.g., 10 minutes) is used when traffic is sparse to ensure sufficient data is collected.

[0104] The system can identify which road sections are particularly important for monitoring and prompt operators to increase the sampling frequency of vehicles in these areas, thereby improving the data collection density and quality in those areas.

[0105] In this way, by using data from multiple vehicles at different times, the system can not only track the dynamic trend of changes between illumination and grayscale, but also achieve continuous monitoring through relay between vehicles, which is an effect that cannot be achieved by a single vehicle.

[0106] S130. Identify and remove interference spectra from the detection data of the multiple vehicles to obtain interference-free detection data of the multiple vehicles.

[0107] In this embodiment, removing interference from multi-vehicle detection data refers to identifying and eliminating interference signals caused by non-streetlight light sources (such as oncoming vehicle lights, LED advertising screens, etc.) through a series of spectrum analysis and consistency verification steps, thereby retaining the data that truly reflects the working status of the streetlights.

[0108] The spectral similarity of the detection data of the multiple vehicles is calculated. The detection data corresponding to the similarity that meets the requirements is confirmed as the real signal, and the detection data corresponding to the similarity that does not meet the requirements is confirmed as the interference signal. The interference signal is removed to obtain the multi-vehicle detection data with interference removed.

[0109] Specifically, this process includes the following key steps:

[0110] First, the frequency domain component of the illuminance signal is extracted from the data collected from each participating vehicle. This step uses Fourier transform or other spectral analysis methods to convert the time-domain signal into a frequency-domain representation.

[0111] Next, the system compares the spectral data collected by different vehicles from the same streetlight within the same time period. By calculating the similarity between these spectra (e.g., using Pearson correlation coefficient or cosine similarity), the degree of matching between them can be quantified.

[0112] A threshold for spectral similarity is established to distinguish which data are genuine streetlight signals and which are abnormal signals caused by interference sources. If the similarity of one or more sets of data is higher than the threshold, these data are considered to reflect the true situation; otherwise, they are considered interference.

[0113] Once datasets below the similarity threshold are identified, they are marked as interference signals and removed from the overall dataset. This process helps reduce the risk of misjudgment due to local interference and improves the accuracy of the final evaluation results.

[0114] To further ensure data reliability, a "voting mechanism" can be employed in certain situations. This means that for each potential major frequency component, it is only officially recognized as part of a valid signal if a majority of vehicles (above a certain proportion) report similar results. This method effectively eliminates accidental interference experienced by individual vehicles.

[0115] In summary, removing interference from multi-vehicle detection data involves the application of complex spectral analysis techniques and statistical principles. Real streetlight signals should exhibit consistency across multiple vehicles; interference signals typically have spatial limitations; if multiple vehicles detect abnormal spectra simultaneously, it may indicate a genuine streetlight flickering problem; through multi-vehicle statistical analysis, localized interference affecting individual vehicles can be identified and eliminated. This method allows for the precise extraction of valuable information from massive amounts of raw data, providing a solid foundation for efficient urban lighting management.

[0116] S140. Verify the interference-removed multi-vehicle detection data based on the correlation coefficient between street light illuminance value and image average gray value, as well as the spectral relative coefficient corresponding to the street light illuminance value, to determine the effective detection data of multi-vehicles.

[0117] In this embodiment, the effective detection data for multiple vehicles refers to a dataset that, after verification and screening, can accurately reflect the relationship between the streetlight illuminance and the average grayscale of the image in the environment where each vehicle is located. This ensures the consistency and reliability of the data and can be used for subsequent analysis and processing.

[0118] In one embodiment, step S140 described above may include steps S141 to S142.

[0119] S141. Verify the effectiveness of the multi-vehicle detection data after removing interference based on the correlation coefficient between the street light illuminance value and the average gray value of the image, so as to determine the first valid data.

[0120] In this embodiment, the first valid data refers to the dataset determined by measuring the internal consistency of single vehicle and multi-vehicle detection data based on the correlation coefficient between street light illuminance value and image average gray value, thus excluding potentially interfered or abnormal data and ensuring data quality.

[0121] For each vehicle, the correlation coefficient between the street light illuminance value and the average gray value of the image is calculated based on the ratio of covariance to standard deviation of the detection data to measure the internal consistency of the detection data for a single vehicle. For multiple vehicles, within the same time period, the correlation coefficient between the street light illuminance value and the average gray value of the image is calculated based on the ratio of covariance to standard deviation of the detection data, and the correlation coefficients calculated for each vehicle are compared to measure the consistency and reliability of the detection data for multiple vehicles and determine the first valid data.

[0122] Specifically, when the correlation coefficient of a vehicle deviates from the correlation coefficients of other vehicles, the weight of that vehicle is reduced.

[0123] Specifically, for each vehicle participating in the detection, the collected streetlight illuminance value (Lux) is analyzed against the average gray value of the image. The strength of the linear relationship between the two is calculated using the ratio of covariance to standard deviation (i.e., the Pearson correlation coefficient formula). This step helps measure the consistency of data within a single vehicle. Within the same time period, the above calculation process is repeated for data from all vehicles to obtain the correlation coefficient for each vehicle. The calculated correlation coefficients between different vehicles are compared. If the correlation coefficient of a vehicle deviates significantly from that of other vehicles (e.g., a deviation exceeding 0.3), the vehicle is considered to have been affected by local interference or equipment malfunction, thus its weight is reduced.

[0124] In this embodiment, by simultaneously detecting the same light source (such as a street lamp) from multiple angles by different vehicles, the matching degree between illuminance sensor data and visual perception can be cross-verified. This cross-vehicle data collection and analysis method effectively eliminates random errors and local interference in single-vehicle detection, improving the accuracy and reliability of the detection results.

[0125] For each vehicle participating in the detection, the correlation coefficient between its illuminance value and the average gray value of the image is first calculated individually. This process involves using the ratio of covariance to standard deviation to quantify the strength of the linear relationship between the two. This step is fundamental; it helps us understand how changes in light intensity at a specific location affect the trend of image brightness changes in the absence of external interference.

[0126] After obtaining the individual correlation coefficients for each vehicle, the next step is to perform multi-vehicle consistency verification. This step involves comparing the correlation coefficients of different vehicles within the same time period. If the correlation coefficients of all vehicles remain at a high level (e.g., all greater than 0.8), it can be considered that the street lighting effect in that area is good, and there is good consistency between the illuminance sensor data and visual perception.

[0127] The system also incorporates an anomaly detection mechanism to handle potential data bias. When the correlation coefficient of a vehicle deviates significantly from that of other vehicles (e.g., a deviation exceeding 0.3), the system considers that vehicle's data to be interfered with, and automatically reduces the weight of that data. This effectively reduces the impact of outlier data on the overall analysis results, further enhancing the system's robustness and environmental adaptability.

[0128] In the absence of external interference, i.e., under normal circumstances, as the intensity of street lighting increases, the average gray value of the image should also increase accordingly, showing a stable linear positive correlation.

[0129] However, in the presence of interfering sources (such as oncoming headlights or LED advertising screens), although the illuminance sensor may detect higher brightness values, the overall grayscale of the image will not increase accordingly. This inconsistency can be quantified using a correlation coefficient, helping to identify and filter out these outlier data points.

[0130] In summary, implementing a multi-vehicle cross-validation mechanism not only eliminates accidental interference factors but also improves the overall system's detection accuracy, enabling it to better adapt to different environmental conditions. This method provides reliable data support and technical assurance for fields such as intelligent transportation systems and urban lighting management.

[0131] S142. Calculate the spectral relative coefficient corresponding to the street light illuminance value for the first valid data to determine the valid detection data for multiple vehicles.

[0132] In one embodiment, step S142 described above may include steps S1421 to S1422.

[0133] S1421. For the first valid data, calculate the product of the spectral response and the exponentially decaying interference intensity function within the current time window to obtain the spectral relative coefficient corresponding to the street light illuminance value.

[0134] In this embodiment, the spectral relative coefficient corresponding to the street light illuminance value is an index calculated by performing spectral analysis on the first valid data and combining it with an exponentially decaying interference intensity function. It is used to evaluate the characteristics and anti-interference ability of these data in the frequency domain and further confirm the validity of the data.

[0135] Specifically, firstly, a Fast Fourier Transform (FFT) is performed on each set of illuminance value sequences in the first set of valid data to obtain its spectral response.

[0136] Define a function that decays exponentially with time. ,in Indicates the intensity of interference. This represents the attenuation rate constant. In this embodiment, the interference intensity is essentially a weighting factor, and its working principle is as follows:

[0137] No interference or slight interference: when the interference intensity When the value is close to 0, it indicates that the data has been almost unaffected by external factors. At this point, the weighting factor is close to 1, meaning that the original spectral response of the data will be preserved to the greatest extent possible. This is because, in the absence of interference, the data has high reliability and accuracy.

[0138] Severe interference: Conversely, when the interference intensity A significant increase indicates that the data may have suffered severe external interference. In this case, the weighting factor value will approach 0, effectively reducing the influence of this unreliable data point in subsequent analysis. In this way, data points that are heavily affected by interference can be suppressed or penalized, preventing them from negatively impacting the overall analysis results.

[0139] To quantify the interference intensity, a method based on inter-vehicle data consistency was adopted. The specific steps are as follows:

[0140] First, the system analyzes the data recorded by each vehicle (such as illuminance values) and calculates the correlation coefficient between them. This process aims to assess the consistency and reliability of the data.

[0141] Next, the system compares the data of an individual vehicle with the average level of other vehicles in the same area. If a vehicle's data (whether it's illuminance or correlation coefficient) deviates significantly from the average of other vehicles, the degree of this deviation can be considered an indicator of the intensity of local interference in that vehicle's data.

[0142] Finally, based on the aforementioned degree of deviation, the system can determine the specific interference intensity of each vehicle's data and adjust its corresponding weighting factor accordingly. This allows for dynamic adjustment of weights to improve the quality of the entire dataset and the reliability of the analysis results, even in complex environments.

[0143] In summary, by introducing a weighting factor that adjusts according to the intensity of interference, the true value of the data can be more accurately reflected in frequency domain analysis, reducing errors caused by interference and ultimately improving the overall performance and reliability of data analysis. This method not only considers the characteristics of the data itself but also incorporates the impact of environmental factors on data quality, providing a more scientific and reasonable data processing strategy.

[0144] Multiplying the spectral response of each vehicle by the corresponding interference intensity function yields a correlation coefficient that reflects the frequency domain characteristics. This coefficient considers not only the frequency components of the signal itself but also the degree of influence of potential interference. here, Represents the spectral response within a specific time window.

[0145] S1422. Valid detection data for multiple vehicles is determined by using the relationship between the spectral relative coefficient corresponding to the street light illuminance value and a set threshold.

[0146] Based on historical data analysis and experimental results, a reasonable threshold for the relative spectral coefficient corresponding to a street light illuminance value is set. .

[0147] Compare the relative spectral coefficients corresponding to the streetlight illuminance values ​​of each vehicle. Its corresponding threshold. If If the data is positive, the vehicle's detection data is considered valid; otherwise, it is marked as interference data.

[0148] Combining the first set of valid data obtained in the previous step with the results of this screening based on the relative coefficients of the spectrum corresponding to the streetlight illuminance values, a comprehensive set of valid detection data for multiple vehicles is determined. This set is used for subsequent applications such as streetlight status assessment, trend analysis, and triggering of early warning mechanisms.

[0149] Through these two key steps, the system can effectively filter out high-quality and valid information from complex multi-source data, ensuring the accuracy and reliability of the street light monitoring system.

[0150] After successfully eliminating all interference signals, only the remaining high-quality data will be used for subsequent analysis. This includes, but is not limited to, operations such as time weighting, spatial weighting, and confidence weighting to generate an accurate description of the current operating status of a specific street light. Finally, the system updates the corresponding street light status file based on the processed data, recording the latest maintenance needs or fault information. This is of great significance for urban management departments to take timely action to repair damaged street lights.

[0151] In this embodiment, the correlation coefficient between the street light illuminance value and the average grayscale value of the image is a comparison of the relationship between the light intensity measured by the illuminance sensor and the average grayscale value of the image captured by the camera. The purpose is to verify whether there is a stable linear positive correlation between the two, thereby confirming whether the street light illumination effect is good.

[0152] This method can effectively eliminate random errors and local interference in single-vehicle detection because different vehicles simultaneously detect the same street light from multiple angles, providing more comprehensive data verification.

[0153] The relative spectral coefficients corresponding to street light illuminance values ​​mainly focus on the frequency characteristics differences of different light sources (such as street light sources, vehicle lights, LED advertising screens, etc.). By analyzing the spectral components of these light sources, interference from non-street light sources can be identified and suppressed. Based on this, further consistency analysis can be performed to determine the validity of the data.

[0154] S150. Determine the weights of the effective detection data of the multiple vehicles based on the street light geographic coordinate database.

[0155] In this embodiment, weight refers to the different degrees of importance assigned to the detection data points based on factors such as the timeliness of the data, the accuracy of the spatial location, and the credibility of the data provider, in order to optimize the accuracy of the results after multi-source data fusion.

[0156] In one embodiment, step S150 described above may include steps S151 to S154.

[0157] S151. When different vehicles pass through the same location, the detection data of the multiple vehicles are automatically identified and associated based on the street light geographic coordinate database and a GPS matching algorithm.

[0158] In this embodiment, when different vehicles pass the same street light location, the system uses a GPS matching algorithm to identify these vehicles and associates their detection data with the corresponding street light ID to form a multi-source detection profile for the street light.

[0159] This step ensures that data from different vehicles can be correctly categorized for a specific street light, laying the foundation for subsequent data fusion.

[0160] S152. Within a specific time window, assign weights according to the temporal order of the effective detection data of the multiple vehicles to obtain time weights.

[0161] In this embodiment, time weight refers to assigning different weight values ​​based on the freshness of the detected data. Generally, newer data is considered more reliable and therefore has a higher weight.

[0162] Within a defined time window (e.g., 30 minutes before and after), all detection data of passing vehicles are weighted according to the freshness of their detection time. For example, a linear decreasing function or an exponential decay function can be used to calculate the time weight of each data point.

[0163] S153. Assign weights based on the distance between the vehicle and the standard street light detection point to obtain spatial weights.

[0164] In this embodiment, the spatial weights are assigned based on the distance between the vehicle and the standard streetlight detection point. Theoretically, data points that are closer should have higher reliability.

[0165] For each detection data point, a weight is calculated based on its actual distance from the standard street light detection point. For example, an inverse proportional function or a Gaussian distribution function can be used to represent the influence of distance on the weight.

[0166] S154. Assign weights based on the historical detection accuracy of the vehicle to obtain the credibility weight.

[0167] In this embodiment, the confidence weight reflects the accuracy level of each vehicle's historical detection records. Vehicles that have historically performed well are assigned a higher weight.

[0168] Analyze the error rate or accuracy rate of each vehicle in past inspection tasks, and assign a weight reflecting its reliability to each new inspection. This can be achieved through statistical models or machine learning algorithms, such as calculating the mean absolute error (MAE) or mean squared error (MSE) and then converting it into a corresponding weight value.

[0169] After completing the above four steps, the system calculates the time weight, spatial weight, and confidence weight for each detection data point. Then, a weighted fusion algorithm combines these weights to form the final comprehensive weight, which is used to generate the overall status assessment value of the streetlights.

[0170] This method not only improves the accuracy of a single detection, but also utilizes diverse information from multiple vehicles to overcome the limitations of a single perspective, thereby providing more comprehensive and reliable street light condition assessment results.

[0171] S160. Determine the comprehensive illuminance value by combining the effective detection data of the multiple vehicles with the corresponding weights.

[0172] In this embodiment, the comprehensive illuminance value refers to a single numerical value representing the streetlight illumination status at a certain moment, obtained by weighted fusion processing of valid detection data collected from multiple vehicles. This process not only considers the time, spatial location, and reliability weight of each vehicle's detection data, but also incorporates historical trend analysis and consistency assessment of multiple detections to provide a comprehensive evaluation result reflecting the actual working status of the streetlights.

[0173] In one embodiment, step S160 described above may include steps S161 to S163.

[0174] S161. The valid detection data of each vehicle are weighted and summed together to obtain a weighted detection value.

[0175] In this embodiment, the weighted detection value refers to the adjusted value that reflects the detection result of a vehicle, which is calculated by assigning corresponding weights to the valid detection data provided by each vehicle based on its time freshness, distance from the street light, and the vehicle's historical accuracy.

[0176] For each vehicle, valid detection data (including illuminance values, image grayscale features, etc.) is assigned corresponding weights based on its freshness, distance from the streetlight, and historical accuracy. These data are then multiplied by their respective weights and summed to obtain a weighted detection value for that vehicle. This step ensures that vehicle data that is fresher, closer to the standard detection point, and has a better historical performance has a higher impact.

[0177] S162. Average the weighted detection values ​​of all vehicles to obtain the instantaneous state value of the street light.

[0178] In this embodiment, the instantaneous state value of the street light refers to a single value representing the street light illumination effect at the current moment, obtained by averaging the weighted detection values ​​of all vehicles.

[0179] Next, the system aggregates the weighted detection values ​​of all vehicles and calculates their average value to obtain an instantaneous state value representing the current streetlight illumination effect. In this way, data from different vehicles are effectively integrated, reducing the uncertainty caused by errors from individual vehicles.

[0180] S163. The instantaneous state value, historical trend analysis value, and consistency evaluation value of the street light are combined according to their respective weighting coefficients to obtain the comprehensive illuminance value.

[0181] Finally, the system combines the instantaneous streetlight status values ​​obtained above with historical trend analysis values ​​based on long-term monitoring data and consistency evaluation values ​​between multiple tests, and weights them according to pre-set weighting coefficients to generate the final comprehensive illuminance value. This multi-dimensional approach can more accurately capture changes in the working status of streetlights, promptly identify potential problems, and improve the overall reliability of the detection system.

[0182] Through this process, the system can not only provide accurate assessments of street lighting status, but also effectively identify abnormal situations, such as local interference or equipment failure, thereby supporting more scientific and reasonable maintenance decisions.

[0183] In this embodiment, the weighted fusion formula for the detection data of a single vehicle is as follows: ;

[0184] It is the weighted detection value of the i-th vehicle for the n-th street light;

[0185] It is a time weight (based on the freshness of the detection time);

[0186] It is a spatial weight (based on the distance from the standard monitoring point);

[0187] It is a credibility weight (based on the vehicle's historical accuracy).

[0188] It is the illuminance value of the streetlights for the i-th vehicle.

[0189] Multi-vehicle data time-series fusion is achieved through the following formula: This formula calculates the instantaneous state value of street light numbered n, taking into account the data of all vehicles involved in the monitoring (totaling N) and their respective weighting factors.

[0190] The comprehensive condition assessment model is used to comprehensively evaluate the condition of streetlights, and its formula is as follows: ; It is the current instantaneous state value based on multi-vehicle weighted fusion; It is a trend analysis value based on historical time series; It is a consistency evaluation value of multiple test data; This is used to adjust the weight of each item in the final evaluation.

[0191] This condition assessment model can effectively identify the degradation of streetlights. It not only utilizes current available data but also compares it with historical data to identify long-term trends in illuminance and ensures consistency in results from multiple tests on the same road segment. This allows for more precise maintenance and management of urban lighting systems.

[0192] S170. Based on the comparative analysis of the comprehensive illuminance value and historical data, determine the status of the streetlights to update the streetlight status file.

[0193] In this embodiment, the street light status profile refers to an electronic document that records the historical monitoring data of each street light and its status changes (normal, warning, or fault). These profiles not only help monitor the performance and health of individual street lights but also provide valuable data support for the entire lighting network.

[0194] In one embodiment, step S170 described above may include steps S171 to S172.

[0195] S171. Determine the judgment threshold based on the historical data and current environmental factors; wherein, the threshold is dynamically adjusted by combining the average and standard deviation of historical data with the weighted sum of environmental impact factors, and continuously updated using a sliding window mechanism to adapt to environmental changes, so as to obtain the judgment threshold.

[0196] In this embodiment, the judgment threshold refers to

[0197] In this step, the system first collects relevant environmental parameters, including but not limited to weather conditions, traffic density, seasonal variations, and time periods. Based on these real-time environmental parameters, the system calculates a comprehensive environmental impact factor. The formula is as follows: ;

[0198] These are weather condition factors (sunny = 1.0, cloudy = 1.1, rainy / foggy = 1.2); These are the weight values ​​for weather condition factors;

[0199] It is the traffic density factor (low density = 0.9, normal = 1.0, high density = 1.1); These are the weight values ​​for the traffic density factor;

[0200] It is a seasonal factor (spring / summer = 0.95, autumn / winter = 1.05); These are the weight values ​​for the seasonal factor;

[0201] It is a time-of-day factor (dusk = 1.1, late night = 1.0, early morning = 0.9); This represents the weight value of the time period factor.

[0202] The specific values ​​of each factor depend on the actual situation.

[0203] Next, the system dynamically adjusts historical data using a sliding window mechanism to adapt to environmental changes and calculates and judges thresholds accordingly. Specifically, the normal threshold... and warning status threshold Calculate according to the following formulas respectively:

[0204] ;

[0205] ;

[0206] in, as well as These are the mean and standard deviation, calculated based on historical data within the sliding window, respectively.

[0207] S172. Based on the comparison between the comprehensive illuminance value and the judgment threshold, determine the status of the street light to update the street light status file.

[0208] At this stage, the system will use the currently calculated comprehensive illuminance value The status of the streetlights is determined by comparing the results with a previously established threshold. The specific judgment logic is as follows:

[0209] Normal state: If ;

[0210] Warning status: If ;

[0211] Fault status: If .

[0212] Once the status of the streetlights is determined, the system automatically updates the corresponding streetlight status file. This step ensures the real-time performance and accuracy of the streetlight management system, enabling timely detection and handling of potential problems, thereby improving the reliability and efficiency of the public lighting system.

[0213] Furthermore, to further reduce the false alarm rate, when the system initially determines that a street light is abnormal, it will call upon data from other vehicles that have recently passed through that section of road for secondary verification. Only when the detection results from multiple vehicles consistently point to an anomaly will the fault status be finally confirmed. This multi-layered verification mechanism effectively improves the accuracy of the detection results and reduces false alarms caused by environmental interference.

[0214] In this embodiment, the threshold determination is actually performed using a threshold adaptive adjustment algorithm to accurately assess the state of the streetlights, thereby improving the reliability and efficiency of the public lighting system. The main steps are as follows:

[0215] The system first collects current environmental parameters, including but not limited to weather conditions, traffic density, seasonal changes, and time of day.

[0216] Based on the collected real-time environmental parameters, a comprehensive environmental impact factor is calculated.

[0217] A sliding window mechanism is used to update the mean and standard deviation of historical data to reflect the latest environmental conditions.

[0218] The judgment threshold is dynamically adjusted by combining the average and standard deviation of historical data with the weighted sum of environmental impact factors.

[0219] The current comprehensive illuminance value is compared with the dynamically calculated judgment threshold to output the status of the street light.

[0220] To reduce false alarms caused by environmental interference, when the system initially determines that a street light is abnormal, it will retrieve data from other vehicles that have recently passed through that section of road for secondary verification. Only when the detection results from multiple vehicles consistently point to an anomaly will the fault status be finally confirmed. This multi-layered verification mechanism not only improves the accuracy of the detection results but also ensures the reliability of the street light status assessment.

[0221] Furthermore, the system combines trend analysis with current status to provide early warnings. For repeated detections of the same road segment, the status score is weighted according to relevance weights, further improving the accuracy of the detection results. These measures effectively ensure the efficient operation and maintenance of the public lighting system.

[0222] The method in this embodiment utilizes different vehicles detecting the same streetlight at different times and locations to obtain a comprehensive dataset. This includes not only temporal differences (e.g., vehicle A passes a streetlight at 8 PM, while vehicle B passes it at 8:15 PM), but also spatial differences (e.g., the distance between the main lane and the auxiliary lane is 25 meters, while the distance between the auxiliary lane and the main lane is 30 meters).

[0223] Weights are assigned based on the freshness of the detection data, with more recent data considered more accurate and therefore given higher weights. Weights are also assigned based on the distance between the vehicle and the streetlight, with closer data points receiving higher weights to overcome the limitations of a single observation perspective. Finally, weights are assigned based on the vehicle's historical detection performance, with vehicles that have historically performed more accurately being given higher weights, thereby improving the overall reliability of the data.

[0224] Through the aforementioned weight allocation mechanism, the system can integrate detection data from different vehicles to form a comprehensive status profile for each street light.

[0225] To further improve the accuracy of the assessment, the system not only relies on historical statistical data to set the basic thresholds, but also incorporates real-time environmental impact factors for adjustment. These environmental factors consider multiple factors such as weather conditions, traffic density, seasonal variations, and time-of-day differences, ensuring that the thresholds can be dynamically adjusted according to changes in environmental conditions.

[0226] Compared to traditional single-vehicle static thresholding methods, this multi-vehicle collaborative approach significantly improves the scientific rigor and accuracy of threshold setting due to the use of more statistical samples and stronger environmental awareness. It can automatically adapt to different environmental conditions, effectively reducing the false positive rate and enhancing the overall system's detection reliability.

[0227] In summary, this advanced street light condition assessment model, through the integration of multi-vehicle collaborative data collection, precise weight allocation, and dynamic threshold adjustment, provides strong support for the maintenance of public lighting systems, ensuring efficient and reliable operation.

[0228] For example, suppose three cars (A, B, and C) detected the same streetlight at different times and locations, obtaining data such as... Figures 2 to 4 The data shown:

[0229] Vehicle A:

[0230] Image grayscale: 102;

[0231] Illuminance detected: 38 lux;

[0232] Vehicle B:

[0233] Image grayscale: 100;

[0234] Illuminance detected: 36 lux;

[0235] Vehicle C:

[0236] Image grayscale: 98;

[0237] Illuminance detected: 34 lux.

[0238] The system first uses image grayscale values ​​to verify the reliability of the illuminance data. This step is based on the premise that, under normal circumstances, the illuminance value of streetlights is positively correlated with the image grayscale value.

[0239] Calculate the correlation coefficient between illuminance and grayscale in each data set to identify potential interference or outliers. For example, the presence of interfering light sources such as oncoming headlights or LED advertising screens may cause an abnormally high illuminance sensor reading, but the overall grayscale of the image may not change significantly; in this case, the correlation coefficient will decrease significantly.

[0240] In this embodiment, the correlation coefficients of the three sets of data were calculated to be 0.85, 0.87 and 0.83, respectively, all of which are higher than the set threshold of 0.8, indicating that all data were not significantly interfered with and the illuminance values ​​were true and reliable.

[0241] Each set of effective illuminance data is assigned a corresponding weight based on three dimensions: time, space, and credibility.

[0242] Time weighting: More recent data has a higher weight.

[0243] Spatial weight: Data points closer to the target street light have higher weights.

[0244] Credibility weight: Weights are assigned based on the vehicle's historical inspection performance.

[0245] like Figure 5 as well as Figure 6 As shown, using the weighted average algorithm and combining the above weights, the comprehensive illuminance value of the street light is calculated to be 36.2 lux.

[0246] The final evaluation result only outputs the comprehensive illuminance value, without including grayscale values. This is because grayscale values ​​are mainly used for data quality verification, while road lighting standards (such as CJJ 45-2015) clearly stipulate that illuminance (lux) is used as the evaluation index.

[0247] In addition, such as Figures 7 to 8 As shown, grayscale values ​​are easily affected by factors such as camera parameters and exposure settings, making them unsuitable as a standardized evaluation metric. In contrast, the illuminance values ​​verified through multi-vehicle fusion have eliminated interference and possess high reliability.

[0248] The system determines whether the detection data belongs to the same street light by comparing the geographical coordinates of the vehicle when it detects the street light.

[0249] The integrated illuminance value is compared and analyzed with the historical data of the street light in the database to update the street light status file and realize continuous monitoring of the street light's operating status.

[0250] When streetlights malfunction and fail to illuminate, the problem can be clearly analyzed from historical data, and abnormal trends can also be detected from continuous data of individual vehicles.

[0251] In this way, the fusion of multi-vehicle collaborative detection data not only improves the accuracy and reliability of street light status assessment, but also enables efficient management and maintenance of public lighting systems.

[0252] This embodiment addresses the limitations of existing technologies in street light condition assessment by proposing a novel dynamic street light condition detection method based on multi-vehicle collaboration and multi-sensor-vision fusion. This method integrates multiple technologies to achieve efficient and accurate monitoring and assessment of street light conditions.

[0253] A network of illuminance sensors distributed across multiple mobile vehicles enables repeated detection of the same streetlight location at multiple time points. This method not only captures changes over different time periods but also effectively reduces random errors caused by single detections.

[0254] Data collected from different vehicles at the same geographical coordinate point are arranged chronologically to form a detailed long-term monitoring archive. This archive helps to comprehensively understand the historical performance of a specific street light and its changing trends over time.

[0255] By statistically analyzing data collected from multiple vehicles, outliers or random errors can be effectively identified and eliminated, thereby improving the reliability and accuracy of the overall detection results.

[0256] By utilizing multi-vehicle tracking data over a long period, a time-series model of streetlight brightness decay is constructed. This enables the system to issue early warnings before streetlight performance begins to degrade, facilitating timely maintenance and preventing malfunctions.

[0257] Cameras on different vehicles capture images of the same location from multiple angles, and the grayscale distribution features of these images are extracted to build a more comprehensive and detailed visual assessment model. This method not only provides richer information for status judgment but also enhances adaptability to complex environmental factors such as changes in lighting conditions.

[0258] These measures provide a more accurate and forward-looking solution for streetlight status detection, significantly improving the management efficiency and service quality of public lighting systems. Furthermore, this multi-vehicle collaborative approach offers new ideas and technical support for urban infrastructure monitoring.

[0259] The aforementioned multi-terminal collaborative road illuminance comprehensive assessment method constructs a streetlight geographic coordinate database, combines illuminance values, image grayscale features, and timestamp information collected from detection devices of different vehicles, and employs multi-vehicle collaborative multi-sensor and visual fusion technology to identify and eliminate interference spectra in the detection data. The validity of the data is verified based on the correlation coefficient between illuminance values ​​and average image grayscale values, as well as the relative coefficient of the spectrum corresponding to the streetlight illuminance values. Appropriate weights are assigned according to the geographical location of the streetlights to calculate the comprehensive illuminance value. By comparing and analyzing with historical data, the streetlight status is accurately determined and the status file is updated, thereby achieving precise monitoring and early warning of streetlight performance degradation. This method solves the problems of insufficient multi-vehicle collaborative monitoring mechanisms and inadequate spatiotemporal data analysis in existing technologies, effectively reduces random errors, captures the gradual process of brightness decay, and overcomes the limitations of a single visual assessment perspective, providing a more comprehensive and accurate streetlight status detection solution.

[0260] Figure 9 This is a schematic block diagram of a multi-terminal collaborative road illumination comprehensive evaluation system 300 provided in an embodiment of the present invention. Figure 9As shown, corresponding to the above-described multi-terminal collaborative road illumination comprehensive evaluation method, the present invention also provides a multi-terminal collaborative road illumination comprehensive evaluation system 300. This multi-terminal collaborative road illumination comprehensive evaluation system 300 includes a unit for executing the above-described multi-terminal collaborative road illumination comprehensive evaluation method, and the system can be configured in a server. Specifically, please refer to... Figure 9 The multi-terminal collaborative road illumination comprehensive evaluation system 300 includes a construction unit 301, an acquisition unit 302, an identification and elimination unit 303, an effectiveness determination unit 304, a weight determination unit 305, a fusion unit 306, and a comparative analysis unit 307.

[0261] The system comprises the following components: a construction unit 301 for constructing a street light geographic coordinate database; an acquisition unit 302 for acquiring street light illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data; an identification and removal unit 303 for identifying and removing interference spectra from the multi-vehicle detection data to obtain interference-free multi-vehicle detection data; a validity determination unit 304 for verifying the interference-free multi-vehicle detection data based on the correlation coefficient between street light illuminance values ​​and average image grayscale values, as well as the relative coefficient of the spectrum corresponding to the street light illuminance values, to determine the valid multi-vehicle detection data; a weight determination unit 305 for determining the weights of the valid multi-vehicle detection data based on the street light geographic coordinate database; a fusion unit 306 for determining a comprehensive illuminance value by combining the valid multi-vehicle detection data with the corresponding weights; and a comparison and analysis unit 307 for determining the street light status based on a comparison and analysis of the comprehensive illuminance value and historical data, to update the street light status file.

[0262] In one embodiment, the identification and elimination unit 303 is used to calculate the spectral similarity in the detection data of the multiple vehicles, confirm the detection data corresponding to the similarity meeting the requirements as real signals, and confirm the detection data corresponding to the similarity not meeting the requirements as interference signals, and eliminate the interference signals to obtain the multi-vehicle detection data with interference removed.

[0263] In one embodiment, the validity determination unit 304 includes:

[0264] The first determining subunit is used to verify the validity of the multi-vehicle detection data after removing interference based on the correlation coefficient between the street light illuminance value and the average gray value of the image, so as to determine the first valid data; the second determining subunit is used to calculate the spectral relative coefficient corresponding to the street light illuminance value on the first valid data, so as to determine the valid detection data of the multi-vehicle.

[0265] In one embodiment, the first determining subunit is configured to, for each vehicle, calculate the correlation coefficient between the street light illuminance value and the average gray value of the image based on the ratio of covariance to standard deviation of the detection data, in order to measure the internal consistency of the detection data of a single vehicle; for multiple vehicles, within the same time period, calculate the correlation coefficient between the street light illuminance value and the average gray value of the image based on the ratio of covariance to standard deviation of the detection data, and compare the correlation coefficients calculated for each vehicle, in order to measure the consistency and reliability of the detection data of multiple vehicles, and determine the first valid data;

[0266] Specifically, when the correlation coefficient of a vehicle deviates from the correlation coefficients of other vehicles, the weight of that vehicle is reduced.

[0267] In one embodiment, the second determining subunit includes:

[0268] The coefficient determination module is used to calculate the product of the spectral response and the exponentially decaying interference intensity function within the current time window for the first valid data, so as to obtain the spectral relative coefficient corresponding to the street lamp illuminance value; the data determination module is used to determine the valid detection data of multiple vehicles by using the relationship between the spectral relative coefficient corresponding to the street lamp illuminance value and a set threshold.

[0269] In one embodiment, the weight determination unit 305 includes:

[0270] The identification and association subunit is used to automatically identify and associate the detection data of multiple vehicles based on the street light geographic coordinate database and through a GPS matching algorithm when different vehicles pass through the same location.

[0271] The time weight determination subunit is used to allocate weights according to the time sequence of the effective detection data of the multiple vehicles within a specific time window to obtain time weights; the spatial weight determination subunit is used to allocate weights according to the distance between the vehicle and the standard detection point of the street light to obtain spatial weights; and the credibility weight determination subunit is used to allocate weights according to the historical detection accuracy of the vehicle to obtain credibility weights.

[0272] In one embodiment, the acquisition unit 302 is further configured to automatically adjust the length of the sliding window according to the traffic flow density, and adjust the sampling frequency of the key road section area in conjunction with the traffic flow density.

[0273] In one embodiment, the fusion unit 306 includes:

[0274] The weighted summation subunit is used to sum the effective detection data of each vehicle in combination with the weights to obtain a weighted detection value; the averaging subunit is used to average the weighted detection values ​​of all vehicles to obtain the instantaneous state value of the street light; the merging subunit is used to combine the instantaneous state value of the street light, the historical trend analysis value, and the consistency evaluation value of multiple detections according to their respective weight coefficients to obtain a comprehensive illuminance value.

[0275] In one embodiment, the comparison analysis unit 307 includes:

[0276] The threshold determination subunit is used to determine the judgment threshold based on the historical data and current environmental factors. The threshold is dynamically adjusted by combining the average and standard deviation of historical data with the weighted sum of environmental impact factors, and continuously updated using a sliding window mechanism to adapt to environmental changes. The status determination subunit is used to determine the status of the streetlights by comparing the comprehensive illuminance value with the judgment threshold, so as to update the streetlight status file.

[0277] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the aforementioned multi-terminal collaborative road illumination comprehensive evaluation system 300 and its various units can be found in the corresponding descriptions in the aforementioned method embodiments. For the sake of convenience and brevity, these details will not be repeated here.

[0278] The aforementioned multi-terminal collaborative road illumination comprehensive assessment system 300 can be implemented as a computer program, which can, for example... Figure 10 It runs on the computer device shown.

[0279] Please see Figure 10 , Figure 10 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0280] See Figure 10 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0281] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a multi-terminal collaborative road illumination comprehensive evaluation method.

[0282] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0283] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a multi-terminal collaborative road illumination comprehensive evaluation method.

[0284] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0285] The processor 502 is used to run the computer program 5032 stored in the memory to implement all the steps of the multi-terminal collaborative road illumination comprehensive evaluation method.

[0286] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0287] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0288] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein when executed by a processor, the computer program causes the processor to perform all steps of the multi-terminal collaborative road illumination comprehensive assessment method.

[0289] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0290] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0291] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of each unit is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0292] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the system of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0293] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0294] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multi-terminal collaborative method for comprehensive road illumination assessment, characterized in that, include: Construct a geographic coordinate database for streetlights; The system acquires street light illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data. Interference spectra in the detection data of the multiple vehicles are identified and removed to obtain interference-free detection data of the multiple vehicles. The detection data of the multi-vehicles after removing interference is verified based on the correlation coefficient between the street light illuminance value and the average gray value of the image, as well as the relative coefficient of the spectrum corresponding to the street light illuminance value, in order to determine the effective detection data of the multi-vehicles. The weights of the effective detection data for the multiple vehicles are determined based on the street light geographic coordinate database. The comprehensive illuminance value is determined by combining the effective detection data of the multiple vehicles with the corresponding weights. Based on the comparative analysis of the comprehensive illuminance value and historical data, the status of the streetlights is determined in order to update the streetlight status file.

2. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 1, characterized in that, The process of identifying and removing interference spectra from the detection data of the multiple vehicles to obtain interference-free detection data of the multiple vehicles includes: The spectral similarity of the detection data of the multiple vehicles is calculated. The detection data corresponding to the similarity that meets the requirements is confirmed as the real signal, and the detection data corresponding to the similarity that does not meet the requirements is confirmed as the interference signal. The interference signal is removed to obtain the multi-vehicle detection data with interference removed.

3. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 1, characterized in that, The method of verifying the interference-removed multi-vehicle detection data based on the correlation coefficient between streetlight illuminance values ​​and average image grayscale values, as well as the spectral relative coefficients corresponding to streetlight illuminance values, to determine the effective detection data for multiple vehicles includes: The effectiveness of the multi-vehicle detection data after removing interference is verified based on the correlation coefficient between the street light illuminance value and the average gray value of the image, so as to determine the first effective data; The spectral relative coefficients corresponding to the street light illuminance values ​​are calculated based on the first valid data to determine the valid detection data for multiple vehicles.

4. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 3, characterized in that, The effectiveness of the interference-removed multi-vehicle detection data is verified based on the correlation coefficient between street light illuminance values ​​and average image grayscale values ​​to determine the first valid data, including: For each vehicle, the correlation coefficient between the street light illuminance value and the average gray value of the image is calculated based on the ratio of covariance to standard deviation of the detection data to measure the internal consistency of the detection data for a single vehicle. For multiple vehicles, within the same time period, the correlation coefficient between the street light illuminance value and the average gray value of the image is calculated based on the ratio of covariance to standard deviation of the detection data, and the correlation coefficients calculated for each vehicle are compared to measure the consistency and reliability of the detection data for multiple vehicles and determine the first valid data. Specifically, when the correlation coefficient of a vehicle deviates from the correlation coefficients of other vehicles, the weight of that vehicle is reduced.

5. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 3, characterized in that, The step of calculating the spectral relative coefficient corresponding to the street light illuminance value based on the first valid data to determine the valid detection data for multiple vehicles includes: For the first valid data, calculate the product of the spectral response and the exponentially decaying interference intensity function within the current time window to obtain the spectral relative coefficient corresponding to the street light illuminance value; The relationship between the spectral relative coefficient corresponding to the street light illuminance value and a set threshold is used to determine the effective detection data for multiple vehicles.

6. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 1, characterized in that, The step of determining the weights of the effective detection data for the multiple vehicles based on the street light geographic coordinate database includes: When different vehicles pass through the same location, the detection data of the multiple vehicles are automatically identified and associated based on the street light geographic coordinate database and a GPS matching algorithm. Within a specific time window, weights are assigned based on the temporal order of the valid detection data of the multiple vehicles to obtain time weights; The spatial weights are obtained by assigning weights based on the distance between the vehicle and the standard street light detection point; The reliability weight is obtained by assigning weights based on the historical detection accuracy of the vehicle.

7. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 1, characterized in that, The process of acquiring streetlight illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data includes: The sliding window length is automatically adjusted based on traffic density, and the sampling frequency of key road sections is adjusted accordingly.

8. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 1, characterized in that, The determination of the comprehensive illuminance value by combining the effective detection data of the multiple vehicles with corresponding weights includes: The valid detection data for each vehicle are weighted and summed according to the aforementioned weights to obtain a weighted detection value; The instantaneous state value of the street light is obtained by averaging the weighted detection values ​​of all vehicles. The instantaneous state value, historical trend analysis value, and consistency evaluation value of the street light are combined according to their respective weighting coefficients to obtain the comprehensive illuminance value.

9. The multi-terminal collaborative road illumination comprehensive evaluation method according to claim 1, characterized in that, The step of determining the street light status based on the comparative analysis of the comprehensive illuminance value and historical data, and updating the street light status file, includes: The judgment threshold is determined based on the historical data and current environmental factors. The threshold is dynamically adjusted by combining the average and standard deviation of historical data with the weighted sum of environmental impact factors, and continuously updated using a sliding window mechanism to adapt to environmental changes. The status of the streetlights is determined by comparing the comprehensive illuminance value with the judgment threshold, so as to update the streetlight status file.

10. A multi-terminal collaborative road illumination comprehensive assessment system, characterized in that, include: Building unit, used to build street light geographic coordinate database; The acquisition unit is used to acquire street light illuminance values, image grayscale features, and timestamps collected from detection devices on different vehicles to obtain multi-vehicle detection data. An identification and elimination unit is used to identify and eliminate interference spectra in the detection data of the multiple vehicles to obtain interference-free detection data of the multiple vehicles. The validity determination unit is used to verify the interference-removed multi-vehicle detection data based on the correlation coefficient between the street light illuminance value and the average gray value of the image and the spectral relative coefficient corresponding to the street light illuminance value, so as to determine the valid detection data of the multi-vehicle. A weight determination unit is used to determine the weights of the effective detection data of the multiple vehicles based on the street light geographic coordinate database. The fusion unit is used to determine the comprehensive illuminance value by combining the effective detection data of the multiple vehicles with corresponding weights. The comparison and analysis unit is used to determine the status of the streetlights based on the comparison and analysis of the comprehensive illuminance value and historical data, so as to update the streetlight status file.

Images