A method, system, device and medium for evaluating the risk of electric leakage of street lamps based on submergence analysis

Abstract

The application discloses a street lamp electric leakage risk assessment method, system, device and medium based on submerged analysis, and relates to the technical field of street lamp risk assessment.The method comprises the following steps: based on the environmental basic data of a target area, simulating and generating an internal waterlogging water accumulation scene; based on the internal waterlogging water accumulation scene and a water accumulation depth threshold, delimiting a high-risk water immersion area of the street lamp; acquiring an image of a target street lamp in the high-risk area and identifying the coordinates of feature points at the lower edge of the maintenance door; according to the coordinates of the feature points, controlling a distance measuring device to measure the distance of the lower edge of the maintenance door, and obtaining the slant distance; based on the slant distance and carrier pose data, calculating the actual vertical height of the lower edge of the maintenance door from the ground; comparing the actual vertical height with the water accumulation depth threshold, and determining whether the street lamp is a high-risk street lamp with water immersion electric leakage. The application combines macroscopic submerged analysis and microscopic facility state diagnosis into a coherent technical chain, and significantly improves the intelligent level of public safety management and the resource investment efficiency.

Description

Technical Field

[0001] This invention belongs to the field of street light risk assessment technology, and in particular relates to a method, system, equipment and medium for assessing street light leakage risk based on flooding analysis. Background Technology

[0002] Currently, risk assessment methods for addressing the leakage risk of streetlights under flooding conditions mainly rely on historical accident statistics and human experience. These methods lack detailed simulations of the formation and spread of floodwater, making it difficult to combine Geographic Information Systems (GIS) and hydrodynamic models to achieve dynamic inundation analysis at the city scale. Therefore, existing assessment methods are often limited to macro-level risk zoning, failing to accurately correlate with the actual condition of specific streetlights, resulting in insufficient accuracy in identifying high-risk facilities and a lack of targeted preventative measures.

[0003] Regarding the assessment of a street light's flood resistance, the actual height of the bottom edge of the access door from the ground is a key parameter for determining its susceptibility to water immersion. Currently, this parameter is primarily obtained manually through on-site measurements using tools such as measuring tapes. This method is inefficient and susceptible to interference from various factors, including operator experience, road slope, and the measurement environment (such as the impact of parked vehicles), making it difficult to guarantee data consistency and accuracy. Given the tens of thousands of street light installations in cities, traditional measurement methods are clearly insufficient to meet the demands of large-scale, high-precision data collection, thus hindering the effective implementation of risk assessment and remedial measures.

[0004] According to urban road and related electrical facility safety regulations, a water depth of 50 centimeters is generally considered to significantly impede pedestrian movement. Simultaneously, water exacerbates the impact on the insulation performance of electrical equipment, significantly increasing the risk of electrical leakage. It is particularly important to note that the lower edge of the access door or the internal wiring terminals of most streetlights are installed at a specific height above the ground (e.g., 20–50 centimeters). If this installation height is lower than the predicted water depth, the streetlight is considered a high-risk facility for water immersion and electrical leakage. Therefore, accurately determining the height of the lower edge of the streetlight access door and combining it with the predicted water depth for risk assessment is a core element in improving the safety management of urban streetlights.

[0005] In summary, existing technologies lack an intelligent assessment method that can integrate flooding simulation analysis and image recognition technology to achieve efficient, accurate, and automated identification of leakage risks in urban streetlights. Summary of the Invention

[0006] In view of the above-mentioned defects in the existing technology, the purpose of this invention is to provide a method, system, device and medium for street light leakage risk assessment based on flooding analysis, so as to solve the technical problems of inaccurate risk assessment and low efficiency caused by relying on human experience in the existing technology, as well as the inability to effectively correlate macro flooding prediction with micro facility status, thus making it difficult to accurately and efficiently identify and warn of leakage risks of massive urban street lights.

[0007] This invention solves the above-mentioned technical problems through the following technical solution: a method for assessing street light leakage risk based on flooding analysis, comprising:

[0008] Obtain basic environmental data for the target area;

[0009] Based on the aforementioned environmental data, a simulated flooding scenario for the target area is generated.

[0010] Based on the aforementioned urban flooding scenarios and water depth thresholds, high-risk areas for street light flooding are identified.

[0011] Acquire images of target streetlights in the high-risk area of ​​streetlight flooding and identify the coordinates of feature points along the lower edge of their maintenance doors;

[0012] Based on the coordinates of the feature points, the ranging device is controlled to perform non-contact ranging on the lower edge of the street light maintenance door to obtain the slant distance;

[0013] Based on the slant distance and carrier pose data, the actual vertical height of the bottom edge of the street light maintenance door from the ground is calculated using trigonometric geometry; wherein, the carrier pose data refers to the pose data of the device equipped with the ranging device.

[0014] The actual vertical height is compared with the water depth threshold to determine whether the street light is a high-risk street light for water immersion and leakage.

[0015] In this embodiment, by simulating the scenario of urban flooding, the risk assessment of street light leakage is based on a scientific hydrological and hydrodynamic model, replacing the traditional method that relies on historical data and human experience. This achieves a leap from fuzzy experience-based assessment to accurate model prediction, solves the problem of ambiguous risk area definition, and significantly improves the accuracy of early warning.

[0016] Based on image recognition of feature point coordinates and control of the ranging device for non-contact ranging, it completely replaces the manual measurement method using a measuring tape, realizing a leap from inefficient manual measurement to intelligent automatic measurement, solving the problems of low efficiency and insufficient accuracy in the census; at the same time, it avoids interference from factors such as operational errors and road slope, and ensures centimeter-level measurement accuracy through trigonometric geometry, providing a reliable data foundation for precise rectification.

[0017] This invention first uses macroscopic simulation to identify key areas of interest, and then performs precise individual condition diagnosis of street lighting facilities within those areas. This "surface-point" combined strategy greatly improves the targeting of risk assessment and the efficiency of resource utilization, avoids blind investigation, and forms a complete technical chain from city-level risk perception to facility-level risk identification.

[0018] Furthermore, the environmental baseline data includes historical rainstorm meteorological data, digital elevation model data, and underground drainage network data; the simulation of the waterlogging scenario in the target area specifically involves: constructing a one-dimensional-two-dimensional coupled hydrodynamic model to simulate the rainstorm waterlogging process in the target area;

[0019] In the one-dimensional-two-dimensional coupled hydrodynamic model: the one-dimensional model constructs the network topology based on the underground drainage network data and solves for the water flow within the network based on the Saint-Venant equation; the two-dimensional model constructs the surface model based on the digital elevation model data and solves for surface runoff based on the shallow water equation.

[0020] The historical rainstorm meteorological data is loaded into the two-dimensional model as the rainfall boundary condition; the one-dimensional model and the two-dimensional model are dynamically coupled at the rainwater inlet to simulate the dynamic exchange process of rainwater between the surface and the underground pipe network.

[0021] In this embodiment, a one-dimensional pipe network model (Saint-Venant equation) accurately simulates the drainage capacity, congestion, and dynamic flow changes of the underground pipe network. This captures drainage problems caused by insufficient pipe network capacity, improper slope, or incorrect connection relationships. A two-dimensional surface model (shallow water equation), based on high-precision DEM data, realistically simulates the collection, flow path, velocity, and accumulation process of rainwater on the ground in different depressions. This accurately predicts the extent, depth, and direction of water accumulation, rather than just a few isolated water accumulation points. The dynamic coupling of the two models at the storm drain inlets not only simulates the smooth drainage of rainwater through the inlets but also accurately reproduces the complete process of rainwater overflowing from manholes and storm drain inlets to the surface when the pipe network is saturated. This is a key mechanism for accurately predicting urban flooding, especially severe flooding, avoiding the significant errors caused by analyzing the surface and underground systems separately. Therefore, through one-dimensional and two-dimensional dynamic coupling simulation, the entire chain of physical processes of "rainfall-surface runoff-pipeline drainage-overflow and waterlogging" was reproduced completely and accurately for the first time in risk assessment, giving the risk prediction results a solid scientific basis and extremely high credibility.

[0022] Furthermore, based on the aforementioned urban flooding scenarios and water depth thresholds, high-risk areas for street light flooding are designated, specifically including:

[0023] Extract the maximum water depth distribution data and water accumulation range from the aforementioned waterlogging scenario;

[0024] Within the waterlogged area, sub-regions where the maximum water depth exceeds the water depth threshold are marked as high-risk areas for street light flooding.

[0025] In this embodiment, by extracting depth distribution data and using threshold filtering, it is possible to accurately identify the core areas within a large area of ​​accumulated water where the water depth truly reaches a dangerous level (e.g., ≥50cm). This allows subsequent inspection and rectification resources (such as mobile inspection vehicles and maintenance teams) to be precisely deployed to the most dangerous locations, avoiding the waste of manpower and resources in low-risk areas and maximizing resource utilization efficiency.

[0026] The risk zone delineation in this invention no longer relies on experts' personal experience or vague judgment, but is entirely based on quantitative depth data derived from simulations and unified, clearly defined preset thresholds. This makes the risk assessment results repeatable, verifiable, and auditable, enhancing the scientific rigor and objectivity of risk determination and avoiding subjective assumptions.

[0027] Furthermore, the coordinates of feature points along the lower edge of the street light maintenance door are identified, specifically including:

[0028] The image of the target street light is processed by an image recognition algorithm to output the sub-pixel precision coordinates of the lower edge of the street light inspection door in the image coordinate system.

[0029] In this embodiment, by outputting sub-pixel-level precision coordinates, the feature point positioning error along the lower edge of the street light inspection door is significantly reduced from the centimeter level to the millimeter level. This leap in precision provides an extremely accurate physical aiming point for subsequent laser ranging, fundamentally ensuring the reliability of the vertical height measurement results and avoiding misjudgments and omissions caused by recognition errors. This not only ensures the accuracy of a single measurement but also greatly improves the reliability and success rate of the automated closed loop of "image recognition-guided ranging," providing a key technological guarantee for achieving large-scale, high-efficiency city-level street light surveys.

[0030] Furthermore, the image recognition algorithm is a trained deep learning key point detection model, which is trained using a street light image dataset containing multiple scenes.

[0031] In this embodiment, a deep learning key point detection model trained with multi-scenario data is employed to achieve highly robust recognition in complex environments. This model, by systematically learning the visual features of streetlights in various scenarios such as sunny days, rainy days, and nighttime, significantly improves its adaptability to complex conditions such as changes in lighting and weather interference. This ensures stable and reliable identification of streetlights and accurate positioning of the lower edge of maintenance doors even under day-night cycles and weather changes, enabling the 24 / 7 routine operation of risk assessment.

[0032] Compared to the limitations of traditional target detection methods that only output bounding boxes, the key point detection model can directly locate the specific structural feature of the lower edge of the maintenance door, fundamentally avoiding the secondary error introduced by the estimation of the bounding box center point, and significantly improving the positioning accuracy of feature point coordinates.

[0033] Furthermore, the ranging device includes a servo gimbal and a laser rangefinder mounted on the servo gimbal;

[0034] Based on the coordinates of the feature points, the ranging device is controlled to perform non-contact ranging on the lower edge of the street light maintenance door, specifically including:

[0035] Control commands are generated based on the coordinates of the feature points to drive the servo gimbal to move, so that the laser beam emitted by the laser rangefinder is precisely aligned with the lower edge of the street light maintenance door, and the straight-line distance, i.e., the slant distance, between the laser rangefinder and the lower edge of the street light maintenance door is obtained.

[0036] In this embodiment, by introducing a servo gimbal, a fully automated closed-loop operation from image recognition to precise distance measurement is achieved. Based on the feature point coordinates output by the visual algorithm, the system generates control commands in real time, driving the servo gimbal to adjust the spatial orientation of the laser rangefinder, ensuring that its emitted laser beam can stably and accurately aim at the lower edge of the streetlight maintenance door. This process completely replaces the traditional manual aiming method, eliminating human error and significantly improving measurement efficiency and consistency.

[0037] As a type of highly rigid and precisely calibrable mechanical structure, the servo gimbal provides a stable and reliable physical measurement benchmark for the system. The installation relationship between the laser rangefinder and the servo gimbal remains constant after calibration, ensuring that the relative pose parameters between the gimbal and the moving platform are known in any pointing state. This provides an indispensable and reliable basis for subsequent fusion of pose data and slant range information, and for calculating the vertical height using trigonometric geometry, thus guaranteeing the measurement accuracy and data reliability at the hardware level.

[0038] Furthermore, the actual vertical height of the bottom edge of the street light maintenance door from the ground is calculated using trigonometric geometry, specifically including:

[0039] Based on the instantaneous absolute vertical height of the ranging device and the pitch angle of the ranging beam after attitude correction, the actual vertical height is calculated using trigonometric relationships.

[0040] The instantaneous absolute vertical height of the ranging device is obtained by adding the absolute elevation of the carrier provided in real time by the integrated navigation system to a fixed vertical calibration distance;

[0041] The absolute elevation of the carrier refers to the real-time height of the reference point of the integrated navigation system in the absolute coordinate system, and the fixed vertical calibration distance refers to the vertical distance between the launch center of the ranging device and the reference point of the integrated navigation system.

[0042] In this embodiment, by fusing the real-time absolute elevation of the carrier provided by the integrated navigation system (absolute geographic coordinates from GPS / INS) with the pre-calibrated fixed vertical calibration height (which remains constant), a stable instantaneous absolute vertical height in the geographic coordinate system (i.e., the absolute coordinate system) is dynamically synthesized. This transforms the measurement reference from a relative platform that sways with the carrier to an absolute reference fixed to the earth, thereby eliminating the interference of the carrier's own movement on the measurement reference surface in principle.

[0043] Regardless of road surface undulations, the system can continuously acquire the absolute elevation of the carrier with centimeter-level accuracy through GPS / INS fusion calculation, ensuring extremely high accuracy and reliability of the measurement benchmark. The resulting vertical height data exhibits excellent consistency and comparability, providing crucial technical support for achieving large-scale, standardized city-level facility surveys.

[0044] Furthermore, the calculation process for the elevation angle of the ranging beam after attitude correction includes:

[0045] Based on the real-time attitude angle of the carrier, a rotation matrix is ​​constructed from the carrier coordinate system to the navigation coordinate system;

[0046] Using the rotation matrix, the original direction vector of the ranging beam in the carrier coordinate system is transformed to obtain the corrected direction vector in the navigation coordinate system;

[0047] Based on the vertical component and horizontal projection of the correction direction vector, the pitch angle relative to the real horizontal plane is calculated using inverse trigonometric functions, thus obtaining the pitch angle of the ranging beam after attitude correction.

[0048] When a vehicle (such as a car or drone) travels on a slope or bumpy road, its pitch and roll attitude causes the original pitch angle of the ranging beam to deviate significantly from the true horizontal plane. This invention constructs a rotation matrix to transform the beam direction from the tilted vehicle coordinate system to the absolutely vertical navigation coordinate system, thereby completely eliminating the angular deviation introduced by the vehicle's attitude. This process ensures from the data source that the pitch angle is relative to the true horizontal plane of the Earth, laying the foundation for accurate altitude measurement.

[0049] This invention employs a rotation matrix to process three-dimensional spatial attitude changes, replacing empirical estimations or simplified models that rely on specific road conditions. The universality and determinism of this method ensure that regardless of the vehicle's tilt state, the system can output the corrected pitch angle through a unified algorithm, completely avoiding uncertainties introduced by subjective human judgment or environmental differences, and guaranteeing the consistency and repeatability of measurement data processing across the entire city.

[0050] Based on the same concept, the present invention also provides a street light leakage risk assessment system based on flooding analysis, comprising:

[0051] The area delineation unit is used to acquire basic environmental data of the target area; based on the basic environmental data, it simulates and generates a flooding scenario in the target area; based on the flooding scenario and the water depth threshold, it delineates high-risk areas for street light flooding.

[0052] The mobile inspection platform includes an inspection vehicle, and an image acquisition unit, a ranging device, a combined navigation system, and a processing unit installed on the inspection vehicle.

[0053] The image acquisition unit is used to acquire images of target streetlights in the high-risk area of ​​streetlight flooding;

[0054] The integrated navigation system is used to provide real-time position and pose data of the inspection vehicle;

[0055] The processing unit is used to process the image of the target street light in real time and identify the coordinates of feature points on the lower edge of its maintenance door; based on the coordinates of the feature points, it controls the ranging device to perform non-contact ranging on the lower edge of the street light maintenance door to obtain the slant distance; based on the slant distance and the real-time pose data of the inspection vehicle, it calculates the actual vertical height of the lower edge of the street light maintenance door from the ground using trigonometric geometry; and compares the actual vertical height with a water depth threshold to determine whether the street light is a high-risk street light for water immersion and leakage.

[0056] Based on the same concept, the present invention also provides an electronic device, including a memory, a processor, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the street light leakage risk assessment method based on flooding analysis as described above.

[0057] Based on the same concept, the present invention also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implements the street light leakage risk assessment method based on flooding analysis as described above.

[0058] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0059] This invention generates urban flooding scenarios through macro-hydrological and hydrodynamic simulation, and for the first time links city-level flood risk prediction with specific facilities, realizing a scientific, refined, and forward-looking assessment of street light flooding risk, and completely changing the vague definition mode that relies on historical data and human experience.

[0060] This invention integrates image recognition and automatic ranging technologies to achieve automated, high-precision, and non-contact measurement of the actual height of the lower edge of inspection doors. This solves the problems of low efficiency, large errors, and strong susceptibility to environmental interference associated with manual measurement, providing technical feasibility for large-scale city-level surveys.

[0061] This invention innovatively combines macro-level flooding analysis with micro-level facility condition diagnosis into a coherent technological chain, forming a complete closed loop of risk area prediction → precise target identification → automatic condition diagnosis → risk level determination. This makes risk management decisions more data-driven and significantly improves the intelligence level and resource allocation efficiency of public safety management. Attached Figure Description

[0062] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only one embodiment of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a flowchart of the street light leakage risk assessment method based on flooding analysis in an embodiment of the present invention;

[0064] Figure 2 This is a block diagram of the street light leakage risk assessment system based on flooding analysis in an embodiment of the present invention. Detailed Implementation

[0065] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. 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.

[0066] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0067] Example 1

[0068] like Figure 1As shown in the figure, the street light leakage risk assessment method based on flooding analysis provided by this embodiment of the invention includes the following steps:

[0069] Step S1: Obtain basic environmental data for the target area.

[0070] In this embodiment, the environmental foundation data includes historical heavy rainfall meteorological data, digital elevation model (DEM) data, and underground drainage network data. The historical heavy rainfall meteorological data is preferably design heavy rainfall pattern data with a return period of not less than 5 years. This data can characterize typical rainfall events of moderate to high intensity, providing engineering-significant rainfall boundary conditions for urban flooding simulation. The DEM data forms the basis for constructing a two-dimensional surface model, containing high-precision surface topographic information for accurately calculating surface runoff paths, water flow direction, and waterlogged areas. The underground drainage network data is the core data for constructing a one-dimensional hydraulic model, including at least the pipe diameter, slope, connection relationships, and storm drain location information. This data comprehensively describes the topology and hydraulic characteristics of the underground drainage system.

[0071] Step S2: Based on environmental data, simulate and generate a flooding scenario in the target area.

[0072] In one specific embodiment of the present invention, based on environmental baseline data, a simulated flooding scenario for a target area is generated, specifically including:

[0073] Step S2.1: Model construction and initialization.

[0074] A one-dimensional-two-dimensional coupled hydrodynamic model was constructed to simulate the rainstorm-induced flooding process in the target area. The one-dimensional model was constructed by establishing an accurate underground pipe network topology based on the underground drainage network data (including pipe diameter, slope, connection relationships, and storm drain locations) obtained in step S1. The one-dimensional model was solved using the Saint-Venant equations to simulate the flow rate, velocity, and water level changes of rainwater within the pipes.

[0075] Two-dimensional model construction: Based on the digital elevation model data obtained in step S1, a high-precision surface model of the target area is constructed. The two-dimensional model is solved based on the diffusion wave approximation of the shallow water equation to simulate the collection, flow, and diffusion of rainwater on the surface, and to accurately determine the surface flow direction and catchment depressions.

[0076] Step S2.2: Model Coupling and Driving.

[0077] The one-dimensional model and the two-dimensional model are dynamically coupled at the rainwater inlet (i.e., the entrance for rainwater to enter the underground drainage network) to achieve accurate simulation of the dynamic exchange process of rainwater between the surface and the underground network (including the flow from the surface into the network and the overflow from the network to the surface).

[0078] The historical rainstorm meteorological data obtained in step S1 (such as the design rainstorm pattern with a return period of not less than 5 years) is used as the rainfall boundary condition and loaded onto the two-dimensional model to drive the simulation of the entire urban flooding process.

[0079] Step S2.3: Simulation execution and result extraction.

[0080] An initialized and coupled one-dimensional and two-dimensional hydrodynamic model was run to dynamically simulate surface water accumulation during the entire rainfall process. From the simulation results, two key indicators, surface water depth and water accumulation range, were extracted to construct a waterlogging scenario for the target area.

[0081] Step S3: Based on the urban flooding scenario and the water depth threshold, delineate the high-risk area for street light flooding.

[0082] In one specific embodiment of the present invention, based on urban flooding scenarios and water depth thresholds, high-risk areas for street light flooding are delineated, specifically including:

[0083] Step S3.1: Extract key parameters of water accumulation.

[0084] From the waterlogging scenario generated in step S2, two core spatial distribution data are extracted: one is the maximum water depth distribution data of each location point in the entire simulation area; the other is the waterlogging range of all locations where waterlogging has occurred during the entire simulation process.

[0085] Step S3.2: Set the risk assessment threshold.

[0086] Based on urban infrastructure safety regulations and electrical equipment waterproofing requirements, a unified water depth threshold (e.g., 50 cm) should be set. This threshold is the critical value for determining whether streetlights pose a risk of water immersion and electrical leakage.

[0087] Step S3.3: Perform spatial analysis and region delineation.

[0088] Within the waterlogged area determined in step S3.1, spatial query and filtering are performed to delineate all geographical units whose maximum waterlogged depth exceeds the waterlogged depth threshold as a continuous or discrete sub-region.

[0089] Step S3.4: Generate a high-risk area map.

[0090] The sub-areas defined in step S3.3 are marked on electronic maps or GIS systems and output as high-risk areas for street light flooding, forming an intuitive flood risk prediction map. This flood risk prediction map serves as the core decision-making basis, providing a clear target work area for subsequent precise inspections of street light facilities.

[0091] Step S4: Obtain images of target streetlights in high-risk areas of streetlight flooding and identify the coordinates of feature points along the lower edge of their maintenance doors.

[0092] In a specific embodiment of the present invention, an inspection vehicle equipped with an image acquisition unit (e.g., a high-definition camera), a ranging device (e.g., a laser rangefinder), and an AI image recognition unit is dispatched to inspect the high-risk area for street light flooding designated in step S3. The image acquisition unit automatically acquires visible light images of the target street lights within the high-risk area for street light flooding.

[0093] The acquired visible light image is input into the AI ​​image recognition unit, which is equipped with a trained deep learning key point detection model. The deep learning key point detection model is used to analyze the visible light image of the target street light in real time, accurately identify the street light pole and directly locate the key feature point of the lower edge of the maintenance door, and finally output the sub-pixel precision coordinates of the lower edge of the maintenance door in the image coordinate system.

[0094] In a specific embodiment of the present invention, the deep learning keypoint detection model is trained using a street light image dataset containing various scenarios such as sunny days, rainy days, and nighttime. The specific training process is existing technology. Specifically, the deep learning keypoint detection model is preferably based on a feature point regression model of a convolutional neural network.

[0095] Step S5: Based on the coordinates of the feature points, control the ranging device to perform non-contact ranging on the lower edge of the street light maintenance door to obtain the slant distance.

[0096] In a specific embodiment of the present invention, based on the coordinates of the feature points, the ranging device is controlled to perform non-contact ranging on the lower edge of the street light maintenance door to obtain the slant distance, specifically including:

[0097] Step S5.1: Coordinate transformation and command generation.

[0098] The inspection vehicle is also equipped with a control unit, and a ranging device (such as a laser rangefinder) is mounted on the servo gimbal, which is connected to the control unit. The control unit receives the feature point coordinates of the lower edge of the inspection door with sub-pixel accuracy from step S4, and combines them with the real-time attitude data of the inspection vehicle. Through a pre-calibrated camera-laser rangefinder joint geometric model, the control unit calculates the feature point coordinates in real time into the horizontal azimuth and pitch angle control commands required to drive the servo gimbal.

[0099] In a specific embodiment of the present invention, the specific calculation process for the horizontal azimuth and pitch angle control commands required to drive the servo gimbal includes:

[0100] Step S5.11: Using the camera's intrinsic parameter matrix, transform the coordinates of the feature points along the lower edge of the inspection door from the image coordinate system to the camera coordinate system to obtain a three-dimensional normalized direction vector. ,in, They represent direction vectors respectively. The components along the x, y, and z axes. At this point, the direction vector... The reference is tilted along with the vehicle body, which represents the three-dimensional direction vector of the laser beam in the tilted carrier coordinate system.

[0101] Step S5.12: Obtain real-time attitude data (pitch angle) of the inspection vehicle provided by the integrated navigation system (GPS / INS). Roll angle and heading angle Based on real-time attitude data, a rotation matrix is ​​constructed from the tilted vehicle coordinate system to the horizontal navigation coordinate system. ; rotate matrix With the three-dimensional normalized direction vector Multiply to obtain the corrected direction vector. ,in, They represent direction vectors respectively. Components along the x, y, and z axes. Corrected direction vector. Vehicle tilt error has been eliminated, representing the projection of the laser beam relative to the Earth's true horizontal and vertical directions.

[0102] Step S5.13: Based on the camera-laser rangefinder joint geometric model, the corrected direction vector... Transform to the laser rangefinder coordinate system to obtain a direction vector in the laser rangefinder coordinate system.

[0103] Step S5.14: Decompose the direction vector in the laser rangefinder coordinate system, and calculate the required horizontal azimuth and elevation azimuth angles of the emitted beam using inverse trigonometric functions to obtain the control command.

[0104] The camera-laser rangefinder joint geometric model is a mathematical model, determined through precise calibration, that describes the spatial position and attitude relationship between the camera and the laser rangefinder, such as rotation matrices and translation vectors.

[0105] Step S5.2: Servo gimbal aiming.

[0106] The control unit sends the horizontal azimuth and pitch angle control commands generated in step S5.1 to the servo pan-tilt unit. The servo pan-tilt unit rotates its laser rangefinder according to the control commands, dynamically adjusting the spatial direction of the laser beam to precisely align it with the feature point at the lower edge of the streetlight inspection door.

[0107] Step S5.3: Laser ranging and data acquisition.

[0108] After the laser beam is stably aligned with the feature point on the lower edge of the street light maintenance door, the laser rangefinder is triggered to perform one or more non-contact distance measurements to obtain and record the straight-line distance, i.e., the slant distance, between the emission center of the laser rangefinder and the feature point on the lower edge of the street light maintenance door.

[0109] Step S6: Based on the slant distance and carrier pose data, calculate the actual vertical height of the bottom edge of the street light maintenance door from the ground using trigonometric geometry.

[0110] In a specific embodiment of the present invention, based on slant distance and carrier pose data (i.e., inspection vehicle pose data), the actual vertical height of the lower edge of the street light maintenance door from the ground is calculated using trigonometric geometry, specifically including:

[0111] Step S6.1: Dynamically obtain the instantaneous absolute vertical height.

[0112] Although the laser rangefinder is mounted in a fixed position relative to the inspection vehicle, the vehicle experiences vertical fluctuations due to road bumps and suspension deformation during operation. Therefore, the instantaneous absolute vertical height is not a static constant, but a dynamic value.

[0113] The vehicle's pose data includes its absolute elevation and attitude data. The absolute elevation of the vehicle is acquired in real time through a GPS / INS integrated navigation system. This absolute elevation refers to the real-time height (i.e., real-time Z-coordinate) of the integrated navigation system's reference point in an absolute coordinate system (such as WGS-84). The vehicle's absolute elevation is then added to a pre-calibrated fixed vertical distance (i.e., the vertical distance between the laser rangefinder's transmission center and the integrated navigation system's reference point) to dynamically synthesize the instantaneous absolute vertical height of the laser rangefinder. This step establishes a stable vertical measurement reference in the absolute coordinate system, unaffected by vehicle vibrations.

[0114] For GPS: the reference point of the integrated navigation system usually coincides with the phase center of the GPS antenna; for INS (Inertial Measurement Unit): the reference point of the integrated navigation system coincides with the measurement center of the IMU.

[0115] In a deeply coupled integrated navigation system, the GPS antenna and IMU are mounted separately on the vehicle body, and there exists a fixed spatial relationship between them (i.e., a three-dimensional translation vector). This translation vector can be accurately measured through a one-time precision system calibration. Subsequently, the measurements from GPS and IMU are unified to a common, virtual reference point for the integrated navigation system. In practice, to simplify calculations and calibration, the phase center of the GPS antenna is often directly defined as the reference point for the integrated navigation system.

[0116] Step S6.2: Calculate the pitch angle after attitude correction.

[0117] Based on the real-time attitude data (pitch angle, roll angle, and heading angle) of the inspection vehicle, a rotation matrix is ​​constructed from the vehicle coordinate system to the navigation coordinate system. Using this rotation matrix, the original direction vector of the ranging beam in the vehicle coordinate system is transformed to obtain the corrected direction vector in the navigation coordinate system. Based on the vertical component and horizontal projection of the corrected direction vector, the pitch angle relative to the real horizontal plane is calculated by inverse trigonometric functions, thus obtaining the pitch angle of the ranging beam after attitude correction.

[0118] The corrected direction vector here is the corrected direction vector obtained in step S5.12. Therefore, the formula for calculating the elevation angle of the ranging beam after attitude correction is:

[0119] (1)

[0120] in, This indicates the elevation angle of the ranging beam after attitude correction; Represents the arctangent trigonometric function; These represent the corrected direction vectors. Components on the x, y, and z axes. This ensures that no matter how the inspection vehicle is tilted, the actual vertical height calculated using this method is relative to the true horizontal plane of the Earth.

[0121] Step S6.3: Perform trigonometric geometry solution.

[0122] Subtract the slant distance measured in step S5 and the attitude-corrected pitch angle obtained in step S6.2 from the instantaneous absolute vertical height obtained in step S6.1. The product of the sine values ​​is used to calculate the actual vertical height of the bottom edge of the street light maintenance door from the ground. The specific formula is as follows:

[0123] (2)

[0124] in, This indicates the actual vertical height of the bottom edge of the street light maintenance door from the ground. Indicates the instantaneous absolute vertical height; Indicates the slope distance.

[0125] Step S7: Compare the actual vertical height with the water depth threshold to determine whether the street light is a high-risk street light for water immersion and leakage.

[0126] The preset water depth threshold is invoked (i.e., the threshold set in step S3.2, for example, 50 cm). This water depth threshold is determined comprehensively based on urban infrastructure safety regulations, electrical equipment insulation safety standards, and pedestrian wading safety height. It is a unified and objective critical value for determining whether streetlights have a risk of water immersion and leakage.

[0127] The actual vertical height calculated in step S6 The height of the bottom edge of the inspection door from the ground is compared in real time with the water depth threshold.

[0128] If the actual vertical height If the water depth threshold is less than or equal to the street light's depth, then the street light is considered a high-risk street light for water immersion and leakage.

[0129] If the actual vertical height >Water depth threshold: If the water depth threshold is reached, the street light is determined to be a low-risk or safe street light.

[0130] Streetlights identified as high-risk will be recorded in a list of high-risk streetlights for water immersion and electrical leakage. This list must include at least the streetlight's unique identifier, geographic coordinates, actual vertical height, and risk level. Simultaneously, the locations of high-risk streetlights will be highlighted (e.g., red dots) on electronic maps or GIS systems, generating a spatial distribution map of high-risk streetlights. This provides direct decision-making support for subsequent precise remediation, emergency dispatch, and safety early warning.

[0131] Example 2

[0132] like Figure 2 As shown, this embodiment of the invention also provides a street light leakage risk assessment system based on flooding analysis. The assessment system includes an area delineation unit and a mobile inspection platform. The mobile inspection platform includes an inspection vehicle, and an image acquisition unit, a ranging device, a combined navigation system, and a processing unit installed on the inspection vehicle. The processing unit includes an AI image recognition unit and a control unit.

[0133] The area delineation unit is used to obtain basic environmental data of the target area; based on the basic environmental data, a flooding scenario of the target area is simulated and generated; based on the flooding scenario and the water depth threshold, a high-risk area for street light flooding is delineated.

[0134] The image acquisition unit is used to acquire images of target streetlights in the high-risk area for streetlight flooding as defined by the area delineation unit.

[0135] The integrated navigation system is used to provide real-time position and orientation data for the inspection vehicle.

[0136] The AI ​​image recognition unit is used to process images of target streetlights in real time and identify the coordinates of feature points along the lower edge of their inspection doors.

[0137] The control unit is used to control the ranging device to perform non-contact ranging on the lower edge of the street light maintenance door according to the coordinates of the feature points to obtain the slant distance; based on the slant distance and carrier pose data, the actual vertical height of the lower edge of the street light maintenance door from the ground is calculated by trigonometric geometry; the actual vertical height is compared with the water depth threshold to determine whether the street light is a high-risk street light for water immersion and leakage.

[0138] In some specific embodiments of the present invention, the street light leakage risk assessment system can combine the features of the street light leakage risk assessment method in Embodiment 1 of the present invention, and vice versa, which will not be repeated here.

[0139] Example 3

[0140] This invention also provides an electronic device, which includes a memory, a processor, and a computer program or instructions stored in the memory. The processor executes the computer program or instructions to implement the street light leakage risk assessment method based on flooding analysis in this invention.

[0141] Although not shown, the electronic device includes a processor that can perform various appropriate operations and processes based on programs and / or data stored in read-only memory (ROM) or loaded from a storage portion into random access memory (RAM). The processor can be a multi-core processor or may contain multiple processors. In some embodiments, the processor may include a general-purpose main processor and one or more specialized coprocessors, such as a central processing unit, graphics processing unit (GPU), neural network processor (NPU), digital signal processor (DSP), etc. Various programs and data required for device operation are also stored in RAM. The processor, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0142] The processor and memory described above are used together to execute programs / instructions stored in the memory. When the program / instructions are executed by the computer, they can implement the methods, steps, or functions described in the above embodiments.

[0143] Although not shown, embodiments of the present invention also provide a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implements the street light leakage risk assessment method based on flooding analysis in embodiments of the present invention.

[0144] Readable storage media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0145] The above description only discloses specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or modifications that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating a risk of electric leakage of a streetlight based on submersion analysis, characterized by, The evaluation method comprises: acquiring environmental basic data of a target area; based on the environmental basic data, simulating an internal flooding water accumulation scene of the target area; based on the internal flooding water accumulation scene and a water accumulation depth threshold, demarcating a high water immersion risk area of street lamps; acquiring an image of a target street lamp in the high water immersion risk area of street lamps and identifying feature point coordinates of a lower edge of a maintenance door thereof; according to the feature point coordinates, controlling a distance measuring device to perform non-contact distance measurement on the lower edge of the maintenance door of the street lamp to obtain a slant distance; based on the slant distance and carrier pose data, calculating an actual vertical height of the lower edge of the maintenance door of the street lamp from the ground by a trigonometric method, wherein the carrier pose data refers to pose data of a device carrying the distance measuring device; comparing the actual vertical height with the water accumulation depth threshold to determine whether the street lamp is a high water immersion risk street lamp.

2. The method of claim 1, wherein the method is characterized by, The environmental basic data comprises historical heavy rain meteorological data, digital elevation model data and underground drainage pipe network data; the simulating an internal flooding water accumulation scene of the target area specifically comprises: constructing a one-dimensional-two-dimensional coupled hydrodynamic model to simulate a heavy rain internal flooding process of the target area; in the one-dimensional-two-dimensional coupled hydrodynamic model: a one-dimensional model constructs a pipe network topology based on the underground drainage pipe network data and solves water flow in the pipe network based on Saint-Venant equation; a two-dimensional model constructs a ground surface model based on the digital elevation model data and solves surface overland flow based on shallow water equation; the historical heavy rain meteorological data is loaded to the two-dimensional model as a rainfall boundary condition; the one-dimensional model and the two-dimensional model are dynamically coupled at a rainwater inlet to simulate a dynamic exchange process of rainwater between the ground surface and the underground pipe network.

3. The method of claim 1, wherein the method is characterized by, Based on the internal flooding water accumulation scene and the water accumulation depth threshold, demarcating a high water immersion risk area of street lamps specifically comprises: extracting maximum water accumulation depth distribution data and a water accumulation range from the internal flooding water accumulation scene; in the water accumulation range, marking a sub-area with a maximum water accumulation depth exceeding the water accumulation depth threshold as a high water immersion risk area of street lamps.

4. The method of claim 1, wherein the method is characterized by, Identifying feature point coordinates of a lower edge of a street lamp maintenance door specifically comprises: processing the image of the target street lamp by an image recognition algorithm to output sub-pixel level precision coordinates of the lower edge of the street lamp maintenance door in an image coordinate system.

5. The method of claim 1, wherein the method further comprises: determining a risk level of the electric leakage of the street lamp based on the analysis result. The distance measuring device comprises a servo gimbal and a laser range finder arranged on the servo gimbal; According to the feature point coordinates, controlling the distance measuring device to perform non-contact distance measurement on the lower edge of the maintenance door of the street lamp specifically comprises: generating a control instruction according to the feature point coordinates to drive the servo gimbal to move so that a laser beam emitted by the laser range finder accurately aims at the lower edge of the maintenance door of the street lamp and a straight line distance between the laser range finder and the lower edge of the maintenance door, i.e. a slant distance, is obtained.

6. The method of claim 1 to 5, wherein, Calculating an actual vertical height of the lower edge of the maintenance door of the street lamp from the ground by a trigonometric method specifically comprises: based on an instantaneous absolute vertical height of the distance measuring device and an attitude corrected distance measuring beam pitch angle, calculating the actual vertical height by a trigonometric relationship; The instantaneous absolute vertical height of the distance measuring device is obtained by adding a fixed vertical calibration distance to the absolute height of the carrier provided by the integrated navigation system in real time. The absolute height of the carrier refers to the real-time height of the reference point of the integrated navigation system in the absolute coordinate system, and the fixed vertical calibration distance refers to the vertical distance between the emission center of the distance measuring device and the reference point of the integrated navigation system.

7. The method of claim 6, wherein the method further comprises: The solving process of the pitch angle of the attitude-corrected ranging beam includes: Based on the real-time attitude angle of the carrier, a rotation matrix from the carrier coordinate system to the navigation coordinate system is constructed; Using the rotation matrix, the original direction vector of the ranging beam in the carrier coordinate system is converted to obtain a corrected direction vector in the navigation coordinate system; Based on the vertical component and horizontal projection of the corrected direction vector, the pitch angle relative to the real horizontal plane is calculated by the inverse trigonometric function, that is, the pitch angle of the attitude-corrected ranging beam is obtained.

8. A system for assessing risk of electric leakage of a street light based on submersion analysis, characterized by, The evaluation system includes: The region delimiting unit is used to obtain the environmental basic data of the target region; based on the environmental basic data, the waterlogging accumulation water scene of the target region is simulated and generated; based on the waterlogging accumulation water scene and the water depth threshold, the high-risk water immersion area of the street lamp is delimited; The mobile inspection platform includes an inspection vehicle and an image acquisition unit, a distance measuring device, an integrated navigation system and a processing unit arranged on the inspection vehicle; The image acquisition unit is used to acquire the image of the target street lamp in the high-risk water immersion area of the street lamp; The integrated navigation system is used to provide real-time pose data of the inspection vehicle; The processing unit is used to process the image of the target street lamp in real time, identify the feature point coordinates of the lower edge of the maintenance door, control the distance measuring device to perform non-contact ranging on the lower edge of the street lamp maintenance door according to the feature point coordinates to obtain the slant distance, calculate the actual vertical height of the lower edge of the street lamp maintenance door from the ground based on the slant distance and the real-time pose data of the inspection vehicle by the triangular geometry method, and compare the actual vertical height with the water depth threshold to determine whether the street lamp is a high-risk street lamp with water immersion and leakage.

9. An electronic device comprising a memory, a processor, and a computer program or instructions stored on the memory, wherein the computer program or instructions, when executed by the processor, cause the electronic device to perform the method of any one of claims 1-8. The processor executes the computer program or instruction to realize the street lamp leakage risk evaluation method based on flooding analysis in any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, The computer program or instruction is executed by the processor to realize the street lamp leakage risk evaluation method based on flooding analysis in any one of claims 1-7.

Images