A tunnel lighting method, apparatus, equipment and storage medium

Abstract

This invention relates to the field of tunnel lighting technology, and more particularly to a tunnel lighting method, apparatus, equipment, and storage medium. The method involves analyzing monitoring system data based on a preset scene recognition model to obtain scene analysis results. If the scene analysis result indicates an emergency lighting mode, the monitoring system data and a preset length coefficient are calculated to obtain the length of the affected area. Lighting parameters for the luminaires are generated based on the length of the affected area and a preset emergency lighting basic parameter library. If the scene analysis result indicates a peak lighting mode, lighting parameters for the luminaires are generated based on the tunnel length and a preset lighting threshold range. The lighting status of the preset tunnel lighting system is adjusted based on the lighting parameters. Through monitoring system data acquisition, scene recognition, and sub-mode lighting control, emergency and peak modes can be accurately identified, improving tunnel traffic safety and operational management.

Description

Technical Field

[0001] This invention relates to the field of tunnel lighting technology, and in particular to a tunnel lighting method, apparatus, equipment, and storage medium. Background Technology

[0002] Traditional tunnel lighting systems often employ fixed-time, fixed-brightness control methods, making it difficult to adaptively adjust to real-time traffic flow and emergencies within the tunnel. While some systems possess simple brightness adjustment functions, they rely on manual mode switching, resulting in delayed response and cumbersome operation, failing to meet the rapid management needs of peak traffic flow and emergencies. Furthermore, some existing tunnel lighting systems suffer from incomplete data coverage and low accuracy in identifying scenarios such as accidents and congestion, hindering the achievement of safe, efficient, and energy-saving tunnel lighting management. Summary of the Invention

[0003] In order to overcome the shortcomings of the prior art, the present invention aims to provide a tunnel lighting method, apparatus, device and storage medium.

[0004] The first aspect of this invention provides a tunnel lighting method, comprising: collecting monitoring system data and performing scene analysis on the monitoring system data according to a preset scene recognition model to obtain scene analysis results; if the scene analysis result is an emergency lighting mode, calculating the monitoring system data and a preset length coefficient to obtain the length of the affected area; generating lighting parameters for luminaires based on the length of the affected area and a preset emergency lighting basic parameter library; if the scene analysis result is a peak lighting mode, collecting the tunnel length and generating lighting parameters for luminaires based on the tunnel length and a preset lighting threshold range; and adjusting the lighting state of a preset tunnel lighting system according to the lighting parameters for luminaires.

[0005] Furthermore, the calculation of the monitoring system data and the preset length coefficient to obtain the length of the affected area includes: extracting the starting point mileage station and the ending point mileage station from the monitoring system data; and calculating the length coefficient, the starting point mileage station and the ending point mileage station to obtain the length of the affected area.

[0006] Furthermore, the step of generating lighting parameters for luminaires based on the length of the affected area and a preset emergency lighting basic parameter library includes: analyzing monitoring system data based on a preset target detection model and a preset edge detection algorithm to obtain the accident area; and generating lighting parameters for luminaires based on the accident area, the length of the affected area, and the emergency lighting basic parameter library.

[0007] Furthermore, the step of analyzing the monitoring system data based on a preset target detection model and a preset edge detection algorithm to obtain the accident area includes: obtaining video frame data and mileage marker data from the monitoring system data; analyzing the video frame data based on the target detection model and edge detection algorithm to obtain the influence extension length; and constructing the accident area according to the preset tunnel width, mileage marker data, influence extension length, and influence area length.

[0008] Furthermore, the analysis of video frame data based on the target detection model and edge detection algorithm to obtain the influence extension length includes: detecting video frame data based on the target detection model and a preset anchor box matching algorithm to obtain target selection features; comparing and analyzing the target selection features according to the edge detection algorithm and preset standard vehicle contour features to obtain vehicle deformation features; and determining the influence extension length based on the target selection features and vehicle deformation features.

[0009] Furthermore, the step of generating lighting parameters based on the accident area, the length of the affected area, and the emergency lighting basic parameter library includes: retrieving lamp location data from a preset lamp location database based on the accident area; retrieving brightness parameters and flicker mode from the emergency lighting basic parameter library based on the emergency lighting mode; and generating lighting parameters based on the lamp location data, the length of the affected area, the brightness parameters, and the flicker mode.

[0010] Furthermore, the step of generating lighting parameters based on tunnel length and a preset lighting threshold range includes: obtaining vehicle driving data from monitoring system data; analyzing the vehicle driving data based on the lighting threshold range and peak lighting mode to obtain a dimming strategy; calculating the lighting threshold range and tunnel length based on a preset gradient brightness calculation formula to obtain gradient brightness; and generating lighting parameters based on gradient brightness and dimming strategy.

[0011] Furthermore, a tunnel lighting device includes: an analysis module for collecting monitoring system data and performing scene analysis on the monitoring system data according to a preset scene recognition model to obtain scene analysis results; a calculation module for calculating the length of the affected area based on the monitoring system data and a preset length coefficient if the scene analysis result is an emergency lighting mode; a first parameter generation module for generating lighting parameters for the luminaires based on the length of the affected area and a preset emergency lighting basic parameter library; a second parameter generation module for collecting the tunnel length and generating lighting parameters for the luminaires based on the tunnel length and a preset lighting threshold range if the scene analysis result is a peak lighting mode; and a state adjustment module for adjusting the lighting state of the preset tunnel lighting system according to the lighting parameters for the luminaires.

[0012] Furthermore, a tunnel lighting device includes: a memory and at least one processor, the memory storing instructions; at least one processor invokes the instructions in the memory to cause the tunnel lighting device to perform the various steps of the tunnel lighting method described above.

[0013] Furthermore, a computer-readable storage medium stores instructions that, when executed by a processor, implement the various steps of the tunnel lighting method described above.

[0014] In the technical solution of this invention, by collecting monitoring system data, intelligent scene recognition, and mode-based lighting control, the entire process of tunnel lighting system is made intelligent, precise, and efficient. This solution provides a reliable basis for scene-based control by accurately identifying emergency lighting mode and peak lighting mode. In emergency mode, the length of the affected area is calculated by combining monitoring system data and length coefficient, and the lighting parameters of the lamps are automatically matched with the emergency parameter library to improve the efficiency and accuracy of accident handling. In peak lighting mode, the lighting parameters of the lamps are adaptively generated according to the tunnel length and lighting threshold, so as to meet the lighting needs of traffic while achieving energy saving and consumption reduction. Finally, the lighting status is dynamically adjusted according to the lighting parameters of the lamps to achieve on-demand lighting and stable operation, improve the response speed, control accuracy and economy of tunnel lighting, and effectively enhance the tunnel traffic safety and operation management level. Attached Figure Description

[0015] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a first flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 2 This is a second flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 3 This is a third flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 4 This is a fourth flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 5 A fifth flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 6 A sixth flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 7 A seventh flowchart of a tunnel lighting method provided in an embodiment of the present invention; Figure 8This is a schematic diagram of the structure of a tunnel lighting device provided in an embodiment of the present invention; Figure 9 This is a structural schematic diagram of a tunnel lighting device provided in an embodiment of the present invention. Detailed Implementation

[0016] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of a tunnel lighting method according to the present invention includes: 101. Collect data from the monitoring system and perform scene analysis on the monitoring system data according to the preset scene recognition model to obtain scene analysis results; In this embodiment, the collected monitoring system data includes full data collected synchronously from millimeter-wave radar, high-definition video surveillance, and vehicle flow counters within the tunnel, covering the entire tunnel area. Data is collected in segments according to tunnel mileage markers, with a focus on traffic-congested sections such as tunnel entrances, exits, curves, and lane-changing areas. The collected full monitoring system data (after simple noise reduction and standardization preprocessing to ensure data accuracy) is input into a preset scene recognition model. The scene recognition model performs real-time analysis of the data to identify the current operating scenario of the tunnel, ultimately outputting the scene analysis results. The core of the scene analysis results includes emergency lighting mode and peak lighting mode, providing a clear basis for subsequent implementation of different lighting control strategies for different scenarios. The preset scene recognition model is trained and generated based on a deep learning algorithm, accurately identifying the characteristics of two core scenarios: when the monitoring system detects an accident signal (such as vehicle collision, flame, or equipment failure), it is determined to be in emergency lighting mode; when the detected vehicle flow reaches a peak threshold (which can be adjusted according to the actual tunnel capacity), it is determined to be in peak lighting mode. The model boasts high accuracy and fast response speed (≤100ms), ensuring timely lighting control. 102. If the scene analysis result is emergency lighting mode, then calculate the length of the affected area by using the monitoring system data and the preset length coefficient. In this embodiment, when the scene analysis determines that it is an emergency lighting mode, the monitoring system data and the preset length coefficient are calculated to obtain the length of the affected area, ensuring the accuracy of the affected area length. This provides accurate length parameter support for subsequent accident area construction and emergency lighting control, effectively improving the handling efficiency of the tunnel emergency lighting system. 103. Generate lighting parameters for luminaires based on the length of the affected area and the preset emergency lighting basic parameter library; In this embodiment, lighting parameters of the lamps are automatically generated based on the length of the affected area and the preset emergency lighting basic parameter library, so as to achieve accurate parameter matching and rapid output, provide a reliable control basis for tunnel emergency lighting, and improve the accuracy of emergency response. 104. If the scene analysis result is peak lighting mode, then collect the tunnel length and generate lighting parameters for the lamps based on the tunnel length and the preset lighting threshold range. In this embodiment, when the peak lighting mode is determined, the lighting parameters of the lamps are generated by collecting the tunnel length and combining it with the preset lighting threshold range. The lighting parameters can be accurately matched according to the actual length of the tunnel to meet the traffic lighting needs during peak hours, achieving both safety and energy saving, and improving the intelligence and economy of the tunnel lighting system. 105. Adjust the lighting status of the preset tunnel lighting system according to the lighting parameters of the lamps; In this embodiment, the lighting status of the tunnel lighting system is adaptively adjusted according to the lighting parameters of the lamps, which can realize precise and dynamic control of the lighting status, match the lighting needs in the tunnel in real time, improve the stability and reliability of the lighting system, optimize the lighting effect, reduce energy consumption, and improve the intelligent management level of tunnel lighting. In this embodiment, by collecting monitoring system data, intelligent scene recognition, and mode-based lighting control, the tunnel lighting system achieves intelligent, precise, and efficient operation throughout the entire process. This solution accurately identifies emergency lighting mode and peak lighting mode, providing a reliable basis for scene-based control. In emergency mode, the length of the affected area is calculated by combining monitoring system data and length coefficients, and lighting parameters of the lamps are automatically generated by matching the emergency parameter library, improving the efficiency and accuracy of accident handling. In peak lighting mode, lighting parameters of the lamps are adaptively generated based on the tunnel length and lighting threshold, achieving energy saving and consumption reduction while meeting the lighting needs of traffic. Finally, the lighting status is dynamically adjusted according to the lighting parameters of the lamps to achieve on-demand lighting and stable operation, improving the response speed, control accuracy, and economy of tunnel lighting, and effectively enhancing tunnel traffic safety and operation management level.

[0018] Please see Figure 2 A second embodiment of a tunnel lighting method according to the present invention specifically includes: 201. Extract the starting point mileage and ending point mileage from the monitoring system data; In this embodiment, the starting point mileage and ending point mileage are extracted from the monitoring system data to ensure that the extracted parameters are accurate and perfectly matched with the tunnel mileage system. This lays a solid foundation for the subsequent calculation of the length of the affected area, effectively improving the accuracy and response efficiency of tunnel emergency response and meeting the real-time needs of emergency scenarios. 202. Calculate the length coefficient, starting point mileage, and ending point mileage to obtain the length of the affected area; In this embodiment, the initial impact length of the accident is first obtained by subtracting the starting point mileage from the ending point mileage; then, the initial impact length is multiplied by a preset length coefficient to finally obtain the length of the affected area (the calculation formula can be simplified to: length of affected area = (ending point mileage - starting point mileage) × length coefficient); the calculation result is a quantified length value (unit: meters), which not only covers the current actual impact range of the accident, but also supplements the safety redundancy through the length coefficient, ensuring that the subsequently constructed accident area can fully cover the core area of ​​the accident and the warning area that may spread, providing an accurate range basis for emergency lighting; In this embodiment, the starting and ending mileage markers are extracted from the monitoring system data to ensure that the parameters are accurate and precisely matched with the tunnel mileage marker system, laying a solid foundation for subsequent calculations. Through standardized calculation logic, the initial impact length of the accident is first calculated, and then the length of the affected area is obtained by combining it with a preset length coefficient. The calculation process is clear and reproducible. The result is a quantitative value that not only covers the actual impact range of the accident at present, but also supplements the safety redundancy through the length coefficient, ensuring that the subsequent accident area fully covers the core area and the warning area. This effectively improves the accuracy and response efficiency of tunnel emergency response, provides a precise range basis for emergency lighting, and adapts to the real-time needs of emergency scenarios.

[0019] Please see Figure 3 A third embodiment of a tunnel lighting method according to the present invention specifically includes: 301. Analyze the monitoring system data based on the preset target detection model and preset edge detection algorithm to obtain the accident area; In this embodiment, a preset target detection model is used to identify and locate targets in the monitoring system data. Accident-related targets are extracted from video or image data, and the location, range, and category of the targets are initially determined to complete the coarse localization of the accident targets. Then, a preset edge detection algorithm is used to extract edge features from the same monitoring data to accurately delineate the target outline, boundary lines, and damage and distortion features, further refining and calibrating the target boundary and the scope of the accident's impact. The target location information output by the target detection is fused and matched with the precise outline information obtained by the edge detection to comprehensively determine the spatial range affected by the accident, and finally, a complete and accurate accident area is obtained. For example, when a vehicle collision occurs in a tunnel, the target detection model first identifies the vehicle involved in the accident and defines its approximate location and coverage area. Then, the edge detection algorithm extracts the edge contours of the vehicle's deformation, damage, and scattered objects. Based on the edge features, the boundary extending outward from the accident is determined. Combining the analysis results of both methods, a rectangular accident area containing the core area of ​​the accident and the surrounding impact range can be delineated. Relying on the preset target detection model and edge detection algorithm, the tunnel monitoring system data is accurately analyzed to efficiently obtain the accident area. It can quickly lock the accident-related targets, refine and calibrate the accident boundary, ensure accurate identification of the accident area, clarify the spatial range of the area, adapt to the emergency needs of sudden accidents in tunnels, and provide a reliable spatial basis for the subsequent generation of lighting parameters for emergency lighting and emergency rescue and disposal. This effectively improves the accuracy and efficiency of tunnel emergency response, with standardized processes and strong adaptability. 302. Generate lighting parameters for luminaires based on the accident area, the length of the affected area, and the emergency lighting basic parameter library; In this embodiment, the emergency lighting basic parameter library provides standardized emergency parameters that are precisely adapted to the actual conditions of the accident area, ensuring that the lighting parameters of the lamps meet the needs of rescue and warning, providing support for the rapid activation of tunnel emergency lighting, effectively improving the accuracy of emergency response, and featuring a simple process and strong adaptability. In this embodiment, a preset target detection model and edge detection algorithm are used to analyze tunnel monitoring data. This enables rapid identification of accident targets, precise definition of the accident area, and clear spatial scope. It can efficiently adapt to emergency scenarios of sudden tunnel accidents, providing a reliable spatial basis for subsequent lighting control and rescue operations, and improving the accuracy and efficiency of emergency response. At the same time, the system combines the identified accident area with a standardized emergency lighting parameter library to automatically generate suitable lighting parameters for the lamps. This ensures that the lighting brightness, warning mode, and other parameters are highly matched with the needs of the accident site, meeting the requirements of rescue operations and safety warnings, and effectively improving the response speed and control level of the tunnel emergency lighting system.

[0020] Please see Figure 4 The fourth embodiment of a tunnel lighting method according to the present invention specifically includes: 401. Obtain video frame data and mileage marker data from the monitoring system; In this embodiment, the input video frame data is high-definition video frames of the accident area collected by the monitoring system, which have undergone preprocessing such as denoising, grayscale conversion, and scale normalization to ensure the accuracy of model detection. 402. Analyze video frame data based on target detection models and edge detection algorithms to obtain the influence on extension length; In this embodiment, the target detection model can quickly locate the accident target and clarify its scale and range, while the edge detection algorithm accurately extracts the target contour features to determine the severity of the accident. This method converts visual information into quantitative parameters to ensure that the influence extension length is dynamically adapted to the actual accident situation, providing core data support for the subsequent construction of the accident area and improving the response accuracy of tunnel emergency response. 403. The accident area is constructed based on the preset tunnel width, mileage marker data, affected extension length, and affected area length; In this embodiment, the preset tunnel width defines the lateral range of the accident area, ensuring full coverage of the tunnel width; the mileage marker data clarifies the longitudinal starting benchmark of the accident area, pinpointing the core location of the accident; the influence extension length defines the longitudinal extension distance of the accident area, covering the core area of ​​the accident and the surrounding warning zone; the influence area length further calibrates the longitudinal range, ensuring coverage of the entire affected area of ​​the accident; the construction logic is as follows: based on the mileage marker data, combined with the influence extension length and the influence area length, the longitudinal mileage range of the accident area is determined; based on the tunnel width, the lateral coverage range is determined, ultimately constructing a complete rectangular accident area that fully covers the affected area of ​​the accident without exceeding actual needs, providing clear spatial guidance for subsequent emergency lighting and rescue operations; In this embodiment, the high-definition video frames of the accident area are preprocessed through denoising and grayscale conversion to ensure the accuracy of subsequent algorithm detection. By using a target detection model and edge detection algorithm, visual information is converted into quantitative parameters to accurately determine the length of the impact extension, achieving dynamic adaptation to the actual scale and severity of the accident and improving the accuracy of emergency response. At the same time, mileage marker data is extracted to lock the core location of the accident, and the preset tunnel width, impact extension length, and impact area length are integrated to construct a complete accident area, ensuring full coverage of the accident's impact range. This provides clear spatial guidance for subsequent emergency lighting and rescue operations, improving the precision of tunnel emergency response.

[0021] Please see Figure 5 The fifth embodiment of a tunnel lighting method according to the present invention specifically includes: 501. Detect video frame data based on the target detection model and the preset anchor box matching algorithm to obtain target selection features; In this embodiment, the target detection model executes the following logic: A lightweight target detection model (such as YOLOv8n) is used, optimized for training in tunnel scenarios (samples include emergency targets such as vehicles, obstacles, and flames). Pixel-level target detection is performed on video frames. The model extracts visual features at different scales through a feature pyramid network, combined with an anchor box matching algorithm (the principle of the anchor box matching algorithm is: a series of anchor boxes of fixed size and proportion are pre-set at different positions and scales in the video frame; after the target detection model extracts visual features at different scales in the video frame through the feature pyramid network, it compares and matches these visual features with the pre-set anchor boxes, calculates the similarity between the two, and filters out targets related to the accident (vehicles, obstacles, etc.). The target selection process involves selecting the anchor frame that best matches the outline of the target (e.g., objects), then fine-tuning and calibrating the matched anchor frames to accurately determine the target's location and range, thus completing the target selection. This provides precise support for subsequent extraction of target geometric features and delineation of vehicle deformation analysis areas. The target selection feature output consists of standardized structured data, containing three key types of information: ① Target category (e.g., small cars, large trucks, multiple vehicles stacked); ② Target geometric features (coordinates, length, and width of the selection box, reflecting the actual area occupied by the target); ③ Target quantity (single target, multiple targets, reflecting the scale of the accident). This feature clearly defines the "analysis object," providing precise pixel areas for subsequent vehicle deformation feature extraction. 502. Based on the edge detection algorithm and the preset standard vehicle contour features, the target bounding box features are compared and analyzed to obtain the vehicle deformation features; In this embodiment, for the pixel region defined by the target bounding box feature, the Canny edge detection algorithm is used to extract the actual edge contour of the target. This algorithm accurately extracts the continuous edges of the target through Gaussian filtering for noise reduction, gradient calculation, non-maximum suppression, and dual threshold screening, eliminating background interference such as road surface and tunnel wall. The extracted actual edge contour is compared point by point with the standard vehicle contour features. By calculating three quantitative indicators, namely "contour overlap", "edge damage rate", and "contour distortion angle", vehicle deformation features are generated: ① Slight deformation (overlap ≥ 80%, damage rate < 10%): such as minor scratches; ② Moderate deformation (overlap 50%-80%, damage rate 10%-30%): such as vehicle dents or rollovers; ③ Severe deformation (overlap < 50%, damage rate ≥ 30%): such as vehicle disintegration or multiple vehicles crushed and stacked. This feature directly reflects the severity of the accident and is the core basis for determining the extension length. 503. Determine the influencing extension length based on the target selection features and vehicle deformation features; In this embodiment, the scale of the accident is determined based on the number of targets and their geometric dimensions in the target selection feature; the severity of the accident is determined based on the classification results of vehicle deformation features; the system presets a standardized "feature-length" mapping rule, matching the corresponding influence extension length value according to the combination of "target number and deformation degree". For example: single target - slight deformation corresponds to a shorter extension length (suitable for minor scrape accidents); single target - moderate deformation, single target - severe deformation, or multiple targets - slight deformation corresponds to a medium extension length (suitable for vehicle rollover, minor rear-end collision accidents); multiple targets - moderate deformation; multiple targets - severe deformation corresponds to a longer extension length (suitable for multi-vehicle chain rear-end collisions, vehicle disintegration accidents); In this embodiment, a lightweight YOLOv8n model optimized for tunnel scenarios is used in conjunction with an anchor-frame matching algorithm to accurately extract standardized and structured target selection features, defining a precise range for subsequent analysis. Based on the Canny edge detection algorithm and quantitative index comparison, the vehicle deformation level is objectively determined. By fusing accident scale (target selection features) and severity (vehicle deformation features) and combining preset mapping rules to dynamically match the influence extension length, precise adaptation is achieved. This solution fully reuses existing monitoring data without requiring additional equipment, offering high efficiency and standardized operation. It ensures reasonable subsequent accident area definition, providing accurate data support for emergency lighting, while also considering economy and versatility, making it widely adaptable to various tunnel emergency scenarios.

[0022] Please see Figure 6 The sixth embodiment of a tunnel lighting method according to the present invention specifically includes: 601. Retrieve lamp location data from the preset lamp location database based on the accident area; In this embodiment, a pre-set lamp location database stores standardized structured data of all lighting fixtures in the tunnel, including the lamp's unique ID, installation mileage marker, lateral installation location (corresponding area for the left lane, middle lane, and right lane), and rated parameters (rated brightness, adjustable flicker range). The lamp location data precisely corresponds to the tunnel mileage markers, consistent with the mileage range definition logic of the "accident area." The system uses the determined accident area (with a clear longitudinal mileage range and lateral width range) as the search condition, automatically filters in the lamp location database, accurately matches all lighting fixtures within the accident area, and simultaneously retrieves the complete location data of these fixtures, laying a solid foundation for the subsequent generation of lighting parameters. 602. Based on the emergency lighting mode, retrieve the brightness parameters and flicker mode from the emergency lighting basic parameter database; In this embodiment, the emergency lighting basic parameter library is preset by the system and is specifically adapted to the emergency lighting mode. The library stores standardized brightness parameters and flicker modes corresponding to emergency scenarios. The parameter settings conform to the tunnel emergency rescue specifications and can be directly used for subsequent lamp parameter allocation. When the system determines that it has entered the emergency lighting mode, it will automatically retrieve the corresponding brightness parameters and flicker modes from the database without manual adjustment. The response speed is fast, ensuring that the emergency lighting parameters can be quickly and automatically retrieved and accurately matched to meet the real-time needs of accident handling. 603. Generate lighting parameters for the luminaires based on the luminaire location data, the length of the affected area, the brightness parameters, and the flicker mode; In this embodiment, relying on a pre-set standardized lamp location database, the complete location data of lamps within the accident area can be accurately filtered and retrieved. This data precisely corresponds to the tunnel mileage markers and the logic for defining the accident area, avoiding the generation of invalid lamp lighting parameters and laying a solid foundation for subsequent parameter generation. Simultaneously, through the emergency lighting basic parameter library, brightness parameters and flicker modes that conform to emergency specifications are automatically retrieved without manual adjustment, providing a rapid response and adapting to the real-time needs of accident handling. Finally, the lamp location data, brightness parameters, and flicker modes are integrated to generate lamp lighting parameters, achieving precise adaptation of emergency lighting. This not only improves the efficiency of emergency lighting response but also ensures the visibility and warning requirements for emergency rescue. The process is standardized, easy to operate, and adaptable to various tunnel emergency scenarios, combining economic efficiency and promotional value.

[0023] Please see Figure 7 The seventh embodiment of a tunnel lighting method according to the present invention specifically includes: 701. Obtain vehicle driving data from the monitoring system; In this embodiment, the extracted vehicle driving data is standardized structured data, specifically including three types of core information: ① Real-time vehicle mileage marker (accurate to 1 meter, corresponding to the mileage coordinates of the tunnel lighting deployment, providing a basis for subsequent segmented dimming); ② Vehicle driving lane (clearly indicating the left, middle, and right lanes of the vehicle, adapting to the lighting needs of different lanes); ③ Vehicle driving speed (accurate to 1 km / h, assisting in judging the degree of road congestion). 702. Analyze vehicle driving data based on the lighting threshold range and peak lighting mode to obtain a dimming strategy; In this embodiment, the lighting threshold range is the system's preset peak lighting brightness standard, divided according to tunnel section type (entrance section, transition section, middle section, and exit section). Each section has a clearly defined upper and lower brightness limit (e.g., the brightness threshold range for the entrance section is 500 lux-800 lux, and for the middle section, it is 300 lux-500 lux). The core function is to standardize the brightness range of the dimming strategy, ensuring that the lighting effect meets both traffic safety requirements and avoids energy waste and glare caused by excessive brightness. The scene analysis execution logic includes segmented positioning: based on the vehicle's real-time mileage marker, the tunnel is divided into several equal sections (e.g., every 5... The system uses a 0-meter interval as a segment to clearly define the specific road segment where each vehicle is located, achieving precise division of tunnel segments and providing a spatial basis for segmented lighting adjustments. Status determination: Based on vehicle speed, the system determines the congestion level of each road segment. A vehicle speed ≤20km / h for at least 3 seconds is used as the congestion standard; 20km / h-60km / h is the normal peak traffic standard; and >60km / h is the off-peak / peak traffic standard. Simultaneously, based on vehicle lanes, the system calculates vehicle density for each lane and road segment (e.g., the number of vehicles per 50-meter segment). Finally, based on the lighting threshold range and peak lighting mode requirements, the system targets different congestion levels and lanes for different road segments. A differentiated dimming strategy was developed, with the core rules as follows (tailored to vehicle driving data characteristics): Congested road sections (vehicle speed ≤ 20km / h): The dimming strategy is to "maintain the upper limit of the corresponding road section's lighting threshold," while adjusting the lane lighting uniformity according to the vehicle's lane to ensure visual clarity when vehicles decelerate, avoiding rear-end collisions and minor accidents caused by congestion; Normal peak-hour road sections (20km / h-60km / h): The dimming strategy is to "maintain the middle value of the corresponding road section's lighting threshold," balancing traffic safety and energy conservation, adapting to the vehicle's normal driving visibility needs, and avoiding glare; Off-peak / peak-hour road sections (> 60km / h): Adjust... The lighting strategy is to "maintain the lower limit of the corresponding road segment lighting threshold" to minimize energy consumption while meeting basic traffic needs. For the middle lane (where vehicle speed is relatively high), the lighting uniformity is appropriately increased; for the two side lanes (which are prone to congestion and frequent vehicle starts and stops), the brightness is appropriately increased to adapt to the traffic needs of different lanes. Standardized segmented and lane-specific dimming strategies are output in the format of "road segment mileage range, lane, brightness target value, lighting uniformity requirement", such as "K1+000m-K1+050m-middle lane-brightness 500 lux-uniformity ≥90%", providing a clear basis for subsequent gradual brightness calculation and luminaire lighting parameter generation. 703. Calculate the lighting threshold range and tunnel length according to the preset gradient brightness calculation formula to obtain the gradient brightness; In this embodiment, the tunnel length can be divided into segment lengths (entrance segment, transition segment, middle segment, and exit segment) as the spatial basis for calculating the gradual brightness, ensuring that the gradual range accurately matches the actual tunnel length. The gradual brightness calculation formula adopts a linear gradual formula, calculating the gradual brightness segment by segment to ensure smooth brightness change (gradient rate ≤ 50 lux / 10 meters), avoiding visual abrupt changes, and strictly adhering to the lighting threshold range. The specific formulas include the following (adapted to the characteristics of each tunnel segment): Gradual brightness at the entrance: In the formula, The brightness (lux) at a certain point in the entrance section is gradually changing (from real-time lighting system data). The real-time illuminance outside the tunnel (can be obtained from environmental data of the monitoring system). The upper limit of the entrance section lighting threshold (lux). This is the distance (in meters) from this point (the end of the entrance section) to the tunnel entrance. The total length of the entrance section (meters); its core function is to achieve a smooth transition between external tunnel lighting and entrance section lighting, avoiding the "black hole effect"; Gradual brightness transition: , In the formula, The brightness (lux) at a certain point in the transition section is gradually changing (from real-time lighting system data). This is the lower limit of the lighting threshold (lux) for the middle section. This is the distance (in meters) from the end of the transition section to the end of the entrance section. The total length of the transition section (meters) is used to achieve a smooth transition from the high brightness of the entrance section to the moderate brightness of the middle section, thereby reducing driver visual fatigue. Gradual brightness transition in the middle section: = Fixed value (take the median value of the lighting threshold for the corresponding road section), no gradual change is required, ensuring uniform lighting in the middle section, adapting to the normal driving needs of vehicles, and simplifying the calculation process; Gradual brightness at the exit section: , In the formula, The brightness (lux) at a certain point in the exit section gradually changes. Real-time illuminance at the tunnel exit. This is the distance (in meters) from the point (end of the exit section) to the point (end of the middle section). The total length of the exit section (meters); its core function is to achieve a smooth transition between the lighting in the middle section and the external lighting of the tunnel, avoiding the "white hole effect"; The calculated gradual brightness values ​​for each section and mileage point of the tunnel are used to form a "mileage marker - gradual brightness" correspondence table to ensure that the brightness at each location meets the gradual requirements and does not exceed the lighting threshold range. At the same time, it accurately corresponds to the mileage marker in the vehicle driving data, providing an accurate brightness benchmark for the subsequent generation of lighting parameters. 704. Generate lighting parameters for the luminaire based on the gradual brightness and dimming strategy; In this embodiment, by acquiring vehicle driving data and combining it with preset lighting threshold ranges and peak lighting modes, differentiated dimming strategies are formulated for different road segments and lanes through segmented positioning and congestion determination. This ensures safe passage through congested sections while achieving energy conservation and consumption reduction in uncongested sections, balancing safety and economy. Simultaneously, relying on the linear gradient brightness calculation formula and combining it with the length of each tunnel segment, a smooth transition of illumination is achieved inside and outside the tunnel and in each road segment, effectively avoiding the "black hole effect" and "white hole effect," improving driver visual comfort, and reducing visual fatigue. Finally, the gradient brightness and dimming strategies are integrated to generate suitable lighting parameters for the lamps, forming adaptive lighting control. This requires no manual intervention, has strong adaptability, and can be widely applied to various types of tunnels, comprehensively optimizing the tunnel lighting experience during peak hours.

[0024] The above describes a tunnel lighting method according to an embodiment of the present invention. The following describes a tunnel lighting device according to an embodiment of the present invention. Please refer to [link / reference]. Figure 8 One embodiment of a tunnel lighting device according to the present invention includes: Analysis module 1 is used to collect data from the monitoring system and perform scene analysis on the monitoring system data according to a preset scene recognition model to obtain scene analysis results; Calculation module 2 is used to calculate the length of the affected area by analyzing the monitoring system data and the preset length coefficient if the scene analysis result is an emergency lighting mode. The first parameter generation module 3 is used to generate lighting parameters for lamps based on the length of the affected area and the preset emergency lighting basic parameter library; The second parameter generation module 4 is used to collect the tunnel length and generate lighting parameters for the lamps based on the tunnel length and the preset lighting threshold range if the scene analysis result is a peak lighting mode. The status adjustment module 5 is used to adjust the lighting status of the preset tunnel lighting system according to the lighting parameters of the lamps; In this embodiment, by collecting monitoring system data, intelligent scene recognition, and mode-based lighting control, the tunnel lighting system achieves intelligent, precise, and efficient operation throughout the entire process. This solution accurately identifies emergency lighting mode and peak lighting mode, providing a reliable basis for scene-based control. In emergency mode, the length of the affected area is calculated by combining monitoring system data and length coefficients, and lighting parameters of the lamps are automatically generated by matching the emergency parameter library, improving the efficiency and accuracy of accident handling. In peak lighting mode, lighting parameters of the lamps are adaptively generated based on the tunnel length and lighting threshold, achieving energy saving and consumption reduction while meeting the lighting needs of traffic. Finally, the lighting status is dynamically adjusted according to the lighting parameters of the lamps to achieve on-demand lighting and stable operation, improving the response speed, control accuracy, and economy of tunnel lighting, and effectively enhancing tunnel traffic safety and operation management level.

[0025] Figure 9 This is a schematic diagram of a tunnel lighting device 900 provided in an embodiment of the present invention. The tunnel lighting device 900 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 910 (e.g., one or more processors) and a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the tunnel lighting device 900. Furthermore, the processor 910 may be configured to communicate with the storage media 930 and execute a series of instruction operations in the storage media 930 on the tunnel lighting device 900 to implement the steps of the tunnel lighting method provided in the above-described method embodiments.

[0026] A tunnel lighting device 900 may further include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, MacOSX, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 9 The tunnel lighting device structure shown does not constitute a limitation on a tunnel lighting device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0027] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of a tunnel lighting method.

[0028] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0029] 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 computer-readable 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, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0030] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A tunnel lighting method, characterized in that, include: Collect data from the monitoring system and perform scene analysis on the monitoring system data based on a preset scene recognition model to obtain scene analysis results; If the scene analysis result is emergency lighting mode, then the monitoring system data and the preset length coefficient are calculated to obtain the length of the affected area; Lighting parameters for luminaires are generated based on the length of the affected area and a pre-set emergency lighting parameter library. If the scene analysis result is peak lighting mode, then the tunnel length is collected, and lighting parameters of the lamps are generated based on the tunnel length and the preset lighting threshold range; The lighting status of the preset tunnel lighting system is adjusted according to the lighting parameters of the lamps.

2. The tunnel lighting method as described in claim 1, characterized in that, The calculation of the length of the affected area based on the monitoring system data and the preset length coefficient includes: The starting point mileage and ending point mileage were extracted from the monitoring system data. The length coefficient, starting point mileage, and ending point mileage are calculated to obtain the length of the affected area.

3. The tunnel lighting method as described in claim 2, characterized in that, The process of generating lighting parameters for luminaires based on the length of the affected area and a preset emergency lighting basic parameter library includes: The monitoring system data is analyzed based on a preset target detection model and a preset edge detection algorithm to determine the accident area; Lighting parameters for luminaires are generated based on the accident area, the length of the affected area, and the emergency lighting basic parameter library.

4. A tunnel lighting method as described in claim 3, characterized in that, The method involves analyzing monitoring system data based on a preset target detection model and a preset edge detection algorithm to determine the accident area, including: Video frame data and mileage marker data are obtained from the monitoring system data; Video frame data is analyzed based on object detection models and edge detection algorithms to determine the influence on extension length; The accident area is constructed based on the preset tunnel width, mileage marker data, affected extension length, and affected area length.

5. A tunnel lighting method as described in claim 4, characterized in that, The analysis of video frame data based on the target detection model and edge detection algorithm to obtain the factors affecting the extension length includes: The target detection model and the preset anchor box matching algorithm are used to detect video frame data to obtain target selection features; The target bounding box features are compared and analyzed based on the edge detection algorithm and the preset standard vehicle contour features to obtain the vehicle deformation features; The influence extension length is determined based on the target selection features and vehicle deformation features.

6. A tunnel lighting method as described in claim 3, characterized in that, The generation of lighting parameters for luminaires based on the accident area, the length of the affected area, and the emergency lighting basic parameter library includes: The location data of the lamps is retrieved from the preset lamp location database based on the accident area; The brightness parameters and flicker mode are retrieved from the emergency lighting basic parameter database according to the emergency lighting mode; Lighting parameters for the luminaires are generated based on the luminaire location data, the length of the affected area, the brightness parameters, and the flicker mode.

7. A tunnel lighting method as described in claim 1, characterized in that, The process of generating lighting parameters for the luminaires based on the tunnel length and a preset lighting threshold range includes: Vehicle driving data is obtained from the monitoring system. The vehicle driving data is analyzed based on the lighting threshold range and peak lighting mode to obtain a dimming strategy; The lighting threshold range and tunnel length are calculated according to the preset gradient brightness calculation formula to obtain the gradient brightness; Lighting parameters for the luminaire are generated based on the gradual brightness and dimming strategy.

8. A tunnel lighting device, characterized in that, include: The analysis module is used to collect data from the monitoring system and perform scene analysis on the monitoring system data according to the preset scene recognition model to obtain scene analysis results. The calculation module is used to calculate the length of the affected area by combining the monitoring system data and the preset length coefficient if the scene analysis result is an emergency lighting mode. The first parameter generation module is used to generate lighting parameters for luminaires based on the length of the affected area and a preset emergency lighting basic parameter library. The second parameter generation module is used to collect the tunnel length and generate lighting parameters for the lamps based on the tunnel length and the preset lighting threshold range if the scene analysis result is a peak lighting mode. The status adjustment module is used to adjust the lighting status of the preset tunnel lighting system according to the lighting parameters of the lamps.

9. A tunnel lighting device, characterized in that, include: A memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the tunnel lighting device to perform the steps of the tunnel lighting method as claimed in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of a tunnel lighting method as described in any one of claims 1-7.

Images