Multi-node collaborative radar induction lamp intelligent deployment method and device

Abstract

The invention provides a multi-node collaborative radar induction lamp intelligent deployment method and device, and relates to the technical field of multi-node collaborative analysis, and the method comprises the steps: collecting and obtaining a regional three-dimensional map of a target region, and carrying out the layout of K radar induction lamps; performing proximity induction lamp detection to generate K pieces of proximity induction lamp detection information; defining graph connection attributes, and establishing an induction lamp node topological structure; performing moving target sensing to obtain K moving target sensing data; performing density grade division to obtain density grade data of K moving targets; uploading to a data processing center, and carrying out multi-node collaborative analysis to obtain a multi-node collaborative management scheme; and the information is issued to K radar induction lamps for illumination management and induction management. According to the invention, the technical problem of insufficient illumination or energy waste caused by the fact that each induction lamp in the deployment of the radar induction lamp in the prior art normally works independently and cannot be cooperatively adjusted according to the state of the adjacent induction lamp is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-node collaborative analysis, and in particular to a multi-node collaborative radar sensor light intelligent deployment method and device. Background Art

[0002] In large public areas, how to deploy radar sensor lights to avoid lighting blind spots and excessive overlapping areas has always been a difficult problem. Traditional sensor light deployment is often based on experience or fixed rules, which makes it difficult to accurately cover the entire target area. It is easy to have blind spots that cannot be sensed or multiple lights repeatedly covering the same area. Blind spots cause safety hazards, while overlapping areas waste lighting resources and increase energy consumption. How to reasonably deploy sensor lights to accurately cover the area has become one of the main challenges in the deployment of sensor lights.

[0003] At the same time, in traditional induction lamp deployment, each induction lamp usually works independently and cannot be coordinated and adjusted according to the status or load of adjacent induction lamps. Some induction lamps may be overloaded. For example, when the target density is high, a single induction lamp needs to frequently adjust the brightness and sensing range, while other induction lamps may be in a low-load state. In this case, some induction lamps are prone to premature damage. At the same time, unbalanced load also leads to unreasonable energy consumption distribution, resulting in energy waste. Summary of the invention

[0004] The present application provides a multi-node collaborative radar sensor light intelligent deployment method and device, aiming to solve the technical problem that in the prior art radar sensor light deployment, each sensor light usually works independently and cannot be coordinated and adjusted according to the status of adjacent sensor lights, resulting in insufficient lighting or energy waste.

[0005] The first aspect disclosed in the present application provides a method for intelligent deployment of multi-node collaborative radar sensor lights, the method comprising: acquiring a regional three-dimensional map of a target area, deploying K radar sensor lights based on the regional three-dimensional map, and acquiring K deployment coordinates and K dynamic sensing ranges according to the deployment results, wherein K is an integer greater than 1; based on the K deployment coordinates, detecting neighboring sensor lights through a wireless communication module built into the radar sensor light to generate K neighboring sensor light detection information; defining a graph connection attribute, topologically connecting the K neighboring sensor light detection information based on the graph connection attribute, and establishing a sensor light node topology structure; and moving the K radar sensor lights according to a preset time period. Target sensing, obtaining K mobile target sensing data, wherein the K mobile target sensing data include K mobile target density data; dividing the K mobile target density data into density levels according to preset density levels to obtain K mobile target density level data; uploading the K mobile target density level data to a data processing center through the K radar sensor lights, performing multi-node collaborative analysis of the K radar sensor lights through a multi-node collaborative management model in the data processing center and combining the sensor light node topology structure to obtain a multi-node collaborative management solution; issuing the multi-node collaborative management solution to the K radar sensor lights to perform lighting management and sensing management of the K radar sensor lights.

[0006] In a second aspect disclosed in the present application, a multi-node collaborative radar sensor light intelligent deployment device is provided, and the device is used for the above-mentioned multi-node collaborative radar sensor light intelligent deployment method, and the device includes: a radar sensor light deployment module, the radar sensor light deployment module is used to collect and obtain a regional three-dimensional map of the target area, and deploy K radar sensor lights based on the regional three-dimensional map, and obtain K deployment coordinates and K dynamic sensing ranges according to the deployment results, wherein K is an integer greater than 1; a proximity sensor light detection module, the proximity sensor light detection module is used to perform proximity sensor light detection based on the K deployment coordinates through the built-in wireless communication module of the radar sensor light, and generate K proximity sensor light detection information; a topological connection module, the topological connection module is used to define graph connection attributes, and topologically connect the K proximity sensor light detection information based on the graph connection attributes to establish a sensor light node topology structure; a moving target sensing module, the moving target sensing module is used to According to a preset time period, the K radar sensing lights are used to sense mobile targets and obtain K mobile target sensing data, wherein the K mobile target sensing data include K mobile target density data; a density level division module, the density level division module is used to perform density level division on the K mobile target density data according to preset density levels to obtain K mobile target density level data; a multi-node collaborative analysis module, the multi-node collaborative analysis module is used to upload the K mobile target density level data to a data processing center through the K radar sensing lights, and through a multi-node collaborative management model in the data processing center, in combination with the sensing light node topology structure, perform multi-node collaborative analysis of the K radar sensing lights to obtain a multi-node collaborative management solution; a lighting management module, the lighting management module is used to send the multi-node collaborative management solution to the K radar sensing lights to perform lighting management and sensing management of the K radar sensing lights.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring three-dimensional maps and deploying K radar sensor lights, the deployment positions of the sensor lights can be flexibly designed according to actual environmental conditions to ensure that the coverage area of ​​the radar sensor lights is optimal, avoiding blind spots and unnecessary overlaps, and thus achieving precise coverage; based on the detection of adjacent sensor lights and the establishment of a topological structure of sensor light nodes, it is possible to ensure that each sensor light communicates and coordinates with the surrounding sensor lights, thereby enhancing the stability and efficiency of the overall sensing system; mobile target sensing performed according to a preset cycle can monitor mobile targets in the coverage area in real time, and obtain real-time mobile target density data based on the target's activity. Combined with the division of density levels, the system can dynamically adjust the parameters of the sensor lights according to different target distributions. This real-time monitoring and dynamic adjustment can ensure the lighting system The system and sensing system can adapt to the complex and changeable target activity environment, and can respond in time and make appropriate adjustments regardless of whether the target activity is frequent or rare; the density level data of each radar sensor light node is uploaded to the data processing center, and a multi-node collaborative management model is used to conduct collaborative analysis among multiple nodes to generate an optimized management plan. This management method can not only effectively coordinate the work of adjacent sensor lights to avoid excessive burden on a single sensor light, but also achieve load balancing of the entire sensor light network, effectively avoiding waste of resources; the multi-node collaborative management plan is issued to realize the automated lighting management and sensing management of K radar sensor lights. Through this intelligent sensing and lighting adjustment, not only can regional safety and visual comfort be ensured, but also energy consumption can be greatly reduced, achieving a technical effect of high efficiency and energy saving.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a multi-node collaborative radar sensor light intelligent deployment method provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the structure of a multi-node collaborative radar sensor light intelligent deployment device provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: radar sensor light deployment module 10, proximity sensor light detection module 20, topological connection module 30, mobile target sensing module 40, density level division module 50, multi-node collaborative analysis module 60, lighting management module 70. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a method and device for intelligent deployment of multi-node coordinated radar sensor lights, thereby solving the technical problem that in the prior art, each sensor light usually works independently and cannot be coordinated and adjusted according to the status of adjacent sensor lights, resulting in insufficient lighting or energy waste.

[0013] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a multi-node collaborative radar sensor light intelligent deployment method, the method comprising: A regional three-dimensional map of the target area is acquired, K radar sensor lights are deployed based on the regional three-dimensional map, and K deployment coordinates and K dynamic sensing ranges are acquired according to the deployment results, where K is an integer greater than 1.

[0015] The boundary information of the target area can be obtained through actual measurement tools, such as laser scanners, to determine the physical scope of the target area. Based on the boundary information of the target area, the environmental information in the target area is collected, including terrain, buildings, obstacles, light conditions, etc. The target area is 3D modeled according to the environmental information to obtain a 3D map of the area, providing a basis for subsequent layout analysis.

[0016] By analyzing the three-dimensional map, the layout points of K radar sensor lights are determined. The selection of layout points needs to meet the following conditions. First, the sensing range of the radar sensor light should be able to cover the target area to ensure that there are no blind spots. Secondly, the communication and sensing functions between the sensor lights cannot be seriously interfered with. Therefore, the distance and position between the sensor lights should be considered to avoid too many overlapping areas. According to the three-dimensional map, the optimal K layout points are selected to maximize the coverage and minimize interference. Through the layout results after the three-dimensional map analysis, the specific layout coordinates of K radar sensor lights are obtained to obtain K layout coordinates. The dynamic sensing range of the radar sensor light refers to the sensing distance and angle of each sensor light under different conditions. The dynamic sensing range can be adjusted according to the real-time changes in the environment, such as the movement of the target, the change of the obstruction, etc., and can be obtained according to the technical specifications of the sensor.

[0017] Based on the K layout coordinates, proximity sensor light detection is performed through the wireless communication module built into the radar sensor light to generate K proximity sensor light detection information.

[0018] Each radar sensor light is equipped with a wireless communication module for communication between sensor lights. Through the wireless communication module, K radar sensor lights can send and receive signals to each other and identify their neighboring sensor lights. After each radar sensor light is activated at its layout coordinates, it sends detection signals to the surroundings through the built-in wireless communication module. These signals are usually in the form of broadcasts. All other radar sensor lights within the detection range can receive the signals. The radar sensor lights that receive the signals will respond and return their own identification information, such as ID, coordinates, communication signal strength, etc. Each radar sensor light determines the distance and direction of its neighboring sensor lights by calculating the received signal strength and response time. Each radar sensor light generates neighboring sensor light detection information based on the number of neighboring sensor lights detected, the relative distance and direction.

[0019] A graph connection attribute is defined, and the K neighboring sensor lamp detection information is topologically connected based on the graph connection attribute to establish a sensor lamp node topology structure.

[0020] In the topological structure of the sensor light, each radar sensor light is a node, and the wireless connection between them is an edge. In order to represent the connection between the sensor lights, the graph connection properties are defined, including defining the weight of each edge according to factors such as the strength and distance of the wireless signal. Generally, the connection with stronger signal strength or shorter distance will be given a higher weight to reflect its better communication quality; an adjacency matrix is ​​defined to represent the topological structure. The elements in the matrix indicate whether there is a direct connection between the sensor lights. If there is a connection between sensor light A and sensor light B, the matrix elements corresponding to A and B are 1, otherwise they are 0.

[0021] The layout coordinates and detection information of each radar sensor light are mapped to nodes in the graph. Based on the detection information of neighboring sensor lights, such as signal strength and distance, the edges between each node are connected to form a complete topological graph. In the process of graph connection, the graph can also be optimized through algorithms. For example, by screening connections with low signal strength or high latency, the edges in the topological structure are ensured to represent high-quality connections. The final established sensor light node topology provides the basis for subsequent multi-node collaborative analysis.

[0022] According to a preset time period, the K radar sensing lights are used to sense moving targets, and K moving target sensing data are obtained, wherein the K moving target sensing data include K moving target density data.

[0023] The preset time period is set according to the needs of the actual application scenario. If the moving targets in the target area are dense or frequent, a shorter time period can be set. For example, it can be set to collect moving target data every 5 seconds, 10 seconds or 30 seconds.

[0024] Each radar sensor light uses its built-in radar sensing module to detect moving targets in the area. The radar senses the movement of the target by emitting electromagnetic waves and receiving reflected signals. This process can detect the speed, direction and distance of the target. Within a preset time period, K radar sensor lights simultaneously sense the moving targets within their coverage area and generate K moving target sensing data. Each radar sensor light can capture the number of moving targets within its coverage area. By dividing the number of moving targets by the sensing area of ​​the radar sensor light, the corresponding moving target density data is calculated.

[0025] According to the preset density level, the K moving target density data are divided into density levels to obtain K moving target density level data.

[0026] The preset density level is a pre-defined mobile target density level standard. The density can be divided into different levels according to the actual application scenario. For example, less than 2 targets per square meter in a certain area can be defined as low density, 2 to 5 targets per square meter can be defined as medium density, and more than 5 targets per square meter can be defined as high density.

[0027] According to the preset density level standard, the mobile target density data obtained by each radar sensor light is classified. For example, assuming that the density data of a sensor light is 3 targets / square meter, it will be classified as a medium density level. After the density level classification, the density data of each radar sensor light will correspond to a specific density level. In this way, K radar sensor lights will generate K corresponding density level data, which respectively represent the target density in the coverage area of ​​each sensor light.

[0028] The density level data of the K mobile targets are uploaded to the data processing center through the K radar sensor lights. Through the multi-node collaborative management model in the data processing center and combined with the sensor light node topology structure, multi-node collaborative analysis of the K radar sensor lights is performed to obtain a multi-node collaborative management solution.

[0029] After completing the mobile target sensing, each radar sensor light uploads the collected mobile target density level data to the data processing center through the wireless communication network. In the data processing center, there is a multi-node collaborative management model, which optimizes the management and control of the overall system based on the collaborative operation of multiple sensor light nodes. First, the model performs a single-node analysis on the mobile target density level data of each sensor light and generates a preliminary lighting and sensing management plan, including brightness adjustment and sensing sensitivity adjustment suitable for the sensor light. On the basis of the single-node analysis, the management model further performs a multi-node collaborative analysis based on the topological structure to optimize the collaborative relationship between multiple adjacent sensor lights. After the multi-node collaborative analysis, a multi-node collaborative management plan is generated, which includes the specific lighting and sensing settings of each radar sensor light.

[0030] The multi-node collaborative management solution is sent to the K radar sensor lights to perform lighting management and sensing management of the K radar sensor lights.

[0031] After the data processing center completes the formulation of the multi-node collaborative management plan, it sends the plan to each radar sensor light through the wireless communication network. Based on the received management plan, each radar sensor light adjusts its lighting brightness, lighting range, sensing sensitivity, and sensing range accordingly. For example, when the density of moving targets in an area increases, multiple adjacent sensor lights will synchronously increase the lighting brightness and sensing sensitivity to form a linked group of sensor lights to ensure that the area is fully covered. Through the collaborative operation of adjacent nodes, the pressure of sensing and lighting can be dispersed and the service life of the equipment can be extended.

[0032] Furthermore, the method comprises: Interactively obtain the regional boundary of the target area, collect environmental information within the regional boundary, and obtain regional environmental information; use the regional boundary as a constraint to perform three-dimensional modeling on the regional environmental information, and obtain a regional three-dimensional map based on the regional three-dimensional model; interactively obtain the original lighting layout information of the target area, and obtain M original lighting areas of M original lighting points in the original lighting layout information; fit the M original lighting areas to the regional three-dimensional map, perform lighting area analysis, and obtain a lighting point adjustment table; increase, decrease, move and adjust the M original lighting points according to the lighting point adjustment table, and layout the K radar sensing lights according to the adjusted points; after the layout is completed, obtain K layout coordinates of the K radar sensing lights according to the adjusted points, and interactively obtain the K dynamic sensing ranges based on the basic parameters of the K radar sensing lights.

[0033] Use automated means to determine the boundaries of the region, for example, use drones or LiDAR to scan the target area, thereby automatically generating boundary data, which may include the contour lines, walls or natural obstacles of the target area. Based on the obtained regional boundaries, the scope of environmental information collection is limited to the boundaries to ensure that the modeling results are consistent with the actual area. A variety of tools can be used to collect environmental information in the region, including laser scanners, drones, radar sensors, etc. Specific environmental information includes terrain features, buildings and obstacles, lighting conditions, etc. This information is integrated to obtain regional environmental information as the basis for subsequent modeling and analysis.

[0034] By using regional environmental information and combining boundary data to create a three-dimensional model of the target area, Building Information Modeling (BIM) can be used to generate a three-dimensional model. The Building Information Model can convert the collected point cloud data into a specific model under a three-dimensional coordinate system, and integrate environmental information from multiple sources into the three-dimensional model to generate a regional three-dimensional model. The model is not only a representation of a two-dimensional plane, but also includes detailed three-dimensional data such as the height of buildings, the undulations of terrain, and the height of trees. The regional three-dimensional map is extracted from the regional three-dimensional model. Through the three-dimensional map, users can view the target area from different perspectives and understand the difficulty of deploying radar sensor lights and possible obstacles.

[0035] The original lighting layout information of the target area is obtained through the lighting management system, including the specific coordinates of M original lighting lamps and the working parameters of the lighting lamps, such as the lighting range, etc. According to the position and lighting range of each lighting lamp, its original lighting area on the three-dimensional map is calculated. These areas represent the specific areas that each lighting lamp can illuminate.

[0036] The lighting range of each original lighting lamp is projected into the 3D model to ensure that its lighting area corresponds to environmental features such as terrain and buildings. After the fitting is completed, the existing lighting coverage is analyzed, including the identification of lighting blind spots (parts in the area without lighting coverage) and lighting overlapping areas (parts of the same area covered by multiple lighting lamps). Based on the analysis results, a lighting point adjustment table is generated. This adjustment table contains adjustment suggestions for each original lighting point, such as moving, increasing or decreasing, to optimize the overall lighting effect.

[0037] According to the lighting point adjustment table, the existing M original lighting points are adjusted, including adding new lighting in some areas if there are lighting blind spots; reducing the number of lighting if there are lighting overlaps in some areas; and moving the installation positions of some lighting according to the adjustment table to optimize lighting coverage. After the lighting adjustment is completed, K radar sensor lights are deployed according to the optimized lighting layout.

[0038] When the K radar sensor lights are deployed, the specific deployment coordinates of each sensor light are recorded to obtain K deployment coordinates. The basic parameters of each sensor light, including the sensing range of the sensor light, are obtained to obtain the dynamic sensing range of each radar sensor light. The dynamic sensing range is the size of the sensing area that the sensor light can automatically adjust according to real-time environmental changes. For example, when fewer moving targets are detected in the target area, the sensor light can reduce the sensing range to save energy; when the target activities are intensive, the sensing range can be expanded.

[0039] Furthermore, the method of fitting the M original lighting areas to the regional three-dimensional map, performing lighting area analysis, and obtaining a lighting point adjustment table includes: The M original lighting areas are fitted to the three-dimensional map of the area to obtain P lighting blind areas and Q lighting overlapping areas; with the goal of minimizing the P lighting blind areas and the Q lighting overlapping areas, the lighting point positions are adjusted to obtain the lighting point position adjustment table.

[0040] The lighting areas of M original lighting lamps are fitted to the three-dimensional map. This process projects the lighting range, angle, height and other parameters of each lighting lamp onto the three-dimensional model of the area to truly reflect the actual coverage area of ​​each lighting lamp. Environmental factors such as buildings, terrain, obstacles, etc. are considered in the three-dimensional map to ensure that the lighting range of the lighting lamp is consistent with the actual terrain.

[0041] Lighting blind spots refer to areas without lighting coverage in the fitted three-dimensional map. These blind spots may be caused by insufficient lighting range of existing lighting lamps, obstruction by buildings, or large distances between lighting lamps. By calculating the lighting coverage of each lighting lamp and analyzing the gaps between lighting lamps, we can identify which areas are not covered by lighting. In this way, we can determine the location, size, and shape of P lighting blind spots.

[0042] The lighting overlap area refers to the area where the lighting range of two or more lighting lamps overlap. These areas usually have excessive lighting, which may cause energy waste or uneven lighting brightness. By calculating the overlap of the lighting range of each lighting lamp, Q lighting overlap areas are identified. These areas usually show problems of excessive light or uneven brightness.

[0043] The first optimization goal is to reduce or eliminate P lighting blind spots to ensure that the entire target area is covered by lighting. The reduction of blind spots helps to improve safety and visibility in the area, especially in places with important facilities or frequent pedestrian activities. The second optimization goal is to reduce the lighting overlap area. By reducing the overlapping area, energy consumption can be reduced and unnecessary waste of brightness can be avoided.

[0044] Adjust the lighting positions. Specifically, in areas with many blind spots, add more lights to cover the blind spots. In areas with many overlapping lighting areas, reduce the overlap by reducing lights or moving the positions of lights. Based on the above analysis, generate a lighting position adjustment table, which lists the position adjustment suggestions for all M original lights, including the addition, reduction, and movement of lights.

[0045] Furthermore, the method of performing multi-node collaborative analysis on the K radar sensor lights to obtain a multi-node collaborative management solution includes: Based on the mobile target sensing records of historical time, extract the historical mobile target density data set of multiple time points and multiple sensing positions to obtain the historical mobile target density level data set; formulate lighting-sensing schemes for the historical mobile target density level data set one by one to obtain a sample lighting-sensing scheme set, wherein the lighting-sensing scheme includes lighting brightness, lighting range, sensing sensitivity, and sensing range; based on the neural network, train the historical mobile target density level data set and the sample lighting-sensing scheme set to obtain a single-node lighting-sensing management sub-model; input the K mobile target density level data into the single-node lighting-sensing management sub-model in sequence, and output K lighting-sensing schemes of the K radar sensor lights; based on the sensor light node topology structure, according to the pre-built multi-node collaborative management sub-model, perform collaborative analysis on the K lighting-sensing schemes to obtain K collaborative lighting-sensing schemes, and integrate the K collaborative lighting-sensing schemes to obtain the multi-node collaborative management scheme, wherein the single-node lighting-sensing management sub-model and the multi-node collaborative management sub-model are cascade structures in the multi-node collaborative management model.

[0046] Extract the saved mobile target sensing data records of multiple time periods and multiple sensor light locations in the historical time. These data may include the number, speed, density, distribution range, etc. of mobile targets. The time span of historical records can be days, weeks or months, depending on the application scenario of the system. Extract data at multiple key time points from historical data. For example, target activities in different time periods may be different, such as changes in target density during the day and night, weekdays and weekends; sensing location refers to the target data sensed by radar sensor lights at different physical locations, ensuring that the mobile target activity data in each area can be captured.

[0047] By analyzing the sensing records at each time point and each sensing position, the mobile target density data of the area is calculated. The density is the number of mobile targets per unit area within the coverage of each sensing light. According to the preset density level standard, the historical density data is graded to obtain a historical mobile target density level data set.

[0048] Lighting-sensing scheme formulation refers to adjusting the lighting brightness, lighting range, sensing sensitivity and sensing range of the sensor lamp for different density levels. Specifically, in high-density areas, the lighting brightness needs to be higher to ensure that the target activity area can be fully illuminated; in low-density areas, the brightness can be appropriately reduced to save energy. The lighting range of the sensor lamp will be adjusted according to the distribution of the target, and areas with higher density require a larger range of lighting. In high-density areas, the sensitivity of the sensor lamp is usually set higher to quickly respond to changes in moving targets; in low-density areas, the sensitivity can be reduced. Depending on the breadth of the target activity, the sensing range will be adjusted at different density levels. The sensing range determines the physical range of the radar sensor lamp that can detect the target. For each density level, a corresponding lighting-sensing scheme is formulated, including lighting brightness, lighting range, sensing sensitivity, and sensing range.

[0049] The input of the neural network includes a set of historical mobile target density level data and a set of sample lighting-sensing schemes. Each set of input data represents a point in time, a density level of a sensor light location, and a corresponding lighting-sensing scheme. It outputs the optimal lighting-sensing parameter settings for each sensor light. The goal is to dynamically adjust the lighting and sensing parameters of the sensor light according to the current mobile target density.

[0050] Specifically, the historical moving target density data and sample lighting-sensing schemes will be divided into training sets and validation sets. The training set is used to adjust the parameters of the neural network, and the validation set is used to test the generalization ability of the model. The neural network is trained using the back-propagation algorithm. During the training process, the model will continuously adjust its weights so that it can accurately predict the appropriate lighting-sensing scheme based on the input density level data. After the training is completed, a single-node lighting-sensing management sub-model is obtained, which can automatically generate the optimal lighting and sensing settings for each sensor light based on the real-time moving target density data.

[0051] The mobile target density level data of K radar sensor lights are respectively input into the single-node lighting-sensing management sub-model. The model outputs the corresponding lighting-sensing scheme based on the input density level data. For K radar sensor lights, K independent lighting-sensing schemes are generated. These schemes are optimized under the independent conditions of each single node, without considering the mutual influence between the nodes.

[0052] The multi-node collaborative management sub-model adjusts the lighting and sensing parameters between adjacent sensor lights according to the sensor light node topology. When a sensor light is in a high-load state, such as covering a high-density area, its adjacent low-load sensor lights can work together to share the load by increasing the sensing sensitivity or expanding the sensing range. Through the analysis of the multi-node collaborative management sub-model, the K independently generated lighting-sensing schemes are further optimized. Finally, K collaborative lighting-sensing schemes are output. These schemes not only take into account the independent situation of each node, but also the mutual influence and collaborative effect between adjacent nodes.

[0053] For the multi-node collaborative management model, the single-node lighting-sensing management sub-model first outputs the lighting-sensing solution according to the individual needs of each sensor lamp, and the multi-node collaborative management sub-model further collaboratively optimizes these solutions. The two form a cascade structure. This cascade structure ensures that each sensor lamp can adjust itself according to real-time data, while realizing multi-node collaborative optimization on a global scale, avoiding local optimal situations and improving the overall performance of the entire system.

[0054] Furthermore, the method of formulating lighting-sensing solutions for the historical mobile target density level data set one by one to obtain a sample lighting-sensing solution set includes: Extract the first historical mobile target density level data, match them in the preset density-lighting brightness association table and the preset density-sensing sensitivity association table, and obtain the first lighting brightness and the first sensing sensitivity; extract the first historical mobile target density data, and obtain the first historical mobile target position set; based on the first historical mobile target position set, perform the minimum circumscribed circle calculation, take the center of the minimum circumscribed circle as the mobile target distribution center, and take the radius of the minimum circumscribed circle as the mobile target distribution radius, to obtain the first mobile target distribution area; generate the first lighting range and the first sensing range based on the first mobile target distribution area; integrate the first lighting brightness, the first sensing sensitivity, the first lighting range, and the first sensing range to generate a first sample lighting-sensing scheme, and add the first sample lighting-sensing scheme to the sample lighting-sensing scheme set.

[0055] A density-illumination brightness association table is predefined, which matches the relationship between the density level of the moving target and the illumination brightness. For example, a higher density level corresponds to a higher illumination brightness to provide sufficient illumination. Similarly, the density-sensing sensitivity association table associates the moving target density with the sensing sensitivity. For example, in a high-density area, the sensing sensitivity should be set higher to quickly respond to the movement of the target.

[0056] The first historical mobile target density level data is randomly extracted from the historical mobile target density level data set as the analysis object, and the extracted first historical mobile target density level data is matched with the above two association tables to obtain the optimal lighting brightness and sensing sensitivity under the density level as the first lighting brightness and the first sensing sensitivity, respectively.

[0057] According to the first historical mobile target density data, the specific location data of each mobile target are extracted. These location data are based on the coordinate position of the target in space detected by the sensor light. The spatial coordinates of these mobile targets are combined into the first historical mobile target position set, which represents the specific distribution of multiple mobile targets in the coverage area of ​​the sensor light within a certain time period.

[0058] The minimum circumscribed circle is a geometric concept, which refers to the smallest circle that can completely surround all given points. Based on the first historical mobile target position set, the minimum circumscribed circle is calculated. The center of the calculated minimum circumscribed circle represents the distribution center of the mobile target, and the radius represents the maximum range of the target activity.

[0059] According to the distribution radius of the minimum circumscribed circle, the corresponding first illumination range is generated. The illumination range should be large enough to cover the entire distribution area of ​​the moving target, and a certain redundancy should be considered to prevent insufficient light in the edge area. For example, if the targets are concentrated in a small area, the illumination range can be relatively small, and if the targets are scattered, the illumination range should be expanded accordingly. Similar to the illumination range, the first sensing range is also adjusted according to the radius of the minimum circumscribed circle. The sensing range should be large enough to ensure that the movement of the target can be detected.

[0060] The obtained first lighting brightness, first sensing sensitivity, first lighting range and first sensing range are integrated together to form a complete first sample lighting-sensing scheme, and the sample scheme is added to a sample lighting-sensing scheme set, which includes lighting-sensing schemes generated under multiple historical density data for subsequent model training.

[0061] Furthermore, the collaborative analysis of the K lighting-sensing solutions to obtain K collaborative lighting-sensing solutions includes: Based on the K lighting-sensing schemes, K lighting brightnesses and K lighting ranges are extracted, and L overflow lighting brightnesses and L overflow lighting ranges that meet the lighting brightness threshold and the lighting range threshold are extracted, and the corresponding L load overflow sensing lamp nodes are located, L≤K; based on the L load overflow sensing lamp nodes, a neighboring node search is performed in the sensing lamp node topology structure to obtain L neighboring node sets; synchronous lighting brightness enhancement and synchronous lighting range enhancement are performed on the L neighboring node sets, and the K collaborative lighting-sensing schemes are obtained according to the enhancement results.

[0062] Extract the lighting brightness and lighting range from each lighting-sensing scheme, and obtain K lighting brightnesses and K lighting ranges. Pre-set lighting brightness thresholds and range thresholds, which are used to determine whether the brightness or range of the sensor light node is too large and exceeds the reasonable range. From the extracted K lighting brightness and lighting ranges, identify those nodes that exceed the preset thresholds. For example, the brightness of some sensor light nodes is too high, which will lead to increased energy consumption; the lighting range of some nodes is too large, which will lead to too many overlapping areas. These node parameters that exceed the threshold are regarded as overflow lighting brightness and range. Locate these sensor light nodes with overflow brightness or range and mark them as load overflow nodes. The number of load overflow nodes L≤K, that is, the number of nodes with load overflow does not exceed the total number of nodes K.

[0063] For each sensor light node with overflowing load, a neighboring node search is performed based on the topological structure. The search process is to find other sensor light nodes that are physically connected to these overflowing nodes. For each overflowing node, a corresponding set of neighboring nodes is formed. These neighboring nodes are used to assist in handling the overflow problem. Through collaborative operations with neighboring nodes, the load of the overflowing node can be adjusted to reduce excessive brightness or excessive lighting range.

[0064] After obtaining the set of neighboring nodes, the lighting brightness of these neighboring nodes is adjusted synchronously. The purpose is to let multiple nodes share the lighting task and reduce the load of overflow nodes. For example, when the lighting brightness of a node is too high, the neighboring nodes can increase the brightness synchronously to disperse the lighting task and reduce the brightness of the overflow nodes. Brightness enhancement can be achieved by gradually increasing the brightness of neighboring nodes, making the overall lighting effect more uniform rather than concentrating on one node.

[0065] Similar to brightness adjustment, the lighting range is also adjusted through the coordinated operation of neighboring nodes. When the lighting range of a node is too large, the neighboring nodes can synchronously expand their own lighting range to reduce the coverage of overflow nodes. By coordinating the lighting ranges of multiple nodes, it is possible to avoid a single node covering too large an area, reduce unnecessary overlaps, and optimize the lighting distribution of the entire system. By adjusting the synchronous brightness and range of L overflow nodes and their neighboring nodes, K new collaborative lighting-sensing schemes are generated. These schemes are based on the original ones, after load optimization and collaborative adjustment, to ensure the balance of the overall lighting and sensing system.

[0066] Furthermore, the collaborative analysis of the K lighting-sensing solutions to obtain K collaborative lighting-sensing solutions further includes: A second sensor light node is randomly extracted, and second moving target sensing data and a second lighting-sensing scheme of the second sensor light node are obtained, wherein the second moving target sensing data also includes a second moving target flow frequency, and the second lighting-sensing scheme includes a second sensing sensitivity and a second sensing range; based on a preset flow frequency threshold, a flow frequency deviation is calculated for the second moving target flow frequency, and a second sensing adjustment coefficient is generated according to the calculation result, wherein the second sensing adjustment coefficient has positive and negative properties; when the second sensing adjustment coefficient belongs to a preset adjustment coefficient interval, the second sensing sensitivity and the second sensing range are independently adjusted based on the second sensing adjustment coefficient to generate a second adjusted sensing sensitivity and a second adjusted sensing range; when the second sensing adjustment coefficient does not belong to the preset adjustment coefficient interval and is a positive number, a synchronous adjustment instruction is generated; based on the synchronous adjustment instruction, while the second sensing sensitivity and the second sensing range are independently adjusted based on the second sensing adjustment coefficient, the neighboring nodes of the second sensor light node are synchronously adjusted, and the K collaborative lighting-sensing schemes are obtained according to the adjustment result.

[0067] A node is randomly selected from all radar sensor light nodes as the second sensor light node and the analysis object. The second sensor light node is used as the index to obtain the second mobile target sensing data and the second lighting-sensing scheme. The second mobile target sensing data also includes the second mobile target flow frequency, which indicates the activity frequency of the mobile target and describes the frequency of movement of the mobile target in a specific time period. The higher the flow frequency, the more frequent the activity of the mobile target. The second lighting-sensing scheme includes the second sensing sensitivity and the second sensing range.

[0068] A flow frequency threshold is preset as a standard for judging whether the target activity is abnormally active or relatively quiet. The threshold can be determined based on historical data or system design goals. The actual moving target flow frequency of the second sensor light node is compared with the preset flow frequency threshold, and the deviation of the flow frequency is calculated. This deviation indicates the difference between the actual activity frequency of the target and the expected frequency. According to the flow frequency deviation, a second sensing adjustment coefficient is generated. The coefficient is used to guide the adjustment of the sensing sensitivity and sensing range of the node. The adjustment coefficient can be positive or negative, depending on the deviation of the flow frequency. When the flow frequency is higher than the preset threshold, it indicates that the target activity is frequent, and a positive adjustment coefficient is generated to enhance the sensing sensitivity and expand the sensing range; when the flow frequency is lower than the preset threshold, it indicates that the target activity is less, and a negative adjustment coefficient is generated to reduce the sensing sensitivity and narrow the sensing range, thereby saving energy.

[0069] Define an adjustment coefficient interval to determine whether the adjustment coefficient is within a reasonable range. If the adjustment coefficient falls within this interval, it means that the deviation is within a controllable range. The parameters of the sensor light are fine-tuned according to the coefficient. In this case, the adjustment coefficient is directly applied to the induction sensitivity and induction range adjustment of the second sensor light node. Specifically, based on the adjustment coefficient, the sensitivity of the sensor light is adjusted. A positive adjustment coefficient will increase the sensitivity, so that the sensor light can detect the target more sensitively; a negative adjustment coefficient will reduce the sensitivity and reduce the response to low-frequency moving targets. Similarly, the sensing range is adjusted according to the adjustment coefficient. A positive adjustment coefficient will expand the sensing range and cover a larger physical area; a negative adjustment coefficient will narrow the sensing range and concentrate resources in a smaller area. By independently adjusting the sensing sensitivity and sensing range, a second adjusted sensing sensitivity and a second adjusted sensing range are generated. These adjusted parameters can better adapt to the current activity of the moving target and achieve accurate sensing and energy consumption optimization.

[0070] When the adjustment coefficient does not belong to the preset adjustment coefficient range, it means that the current mobile target flow frequency is significantly different from the expected one, and additional synchronous adjustment is required to further determine whether the adjustment coefficient is a positive number. If the adjustment coefficient is a positive number, it means that the mobile target flow frequency is significantly higher than the preset threshold, indicating that the target activity is frequent and the inductive load is increasing, and it is necessary to expand the inductive coverage and improve the sensitivity. In this case, a synchronous adjustment instruction is generated, which requires not only the current second induction light node to be adjusted, but also the other adjacent induction light nodes to balance the load and improve the overall induction effect.

[0071] Based on the synchronous adjustment instruction, the second sensor light node continues to be adjusted independently, including the adjustment of its sensing sensitivity and sensing range. Since the adjustment coefficient is a positive number, the sensing sensitivity of the node will be enhanced to ensure that it can quickly respond to the movement of the target, while expanding the sensing range to cover a larger area.

[0072] In order to disperse the load and optimize the overall system performance, according to the synchronous adjustment instruction, while adjusting the second sensor light node, its adjacent sensor light nodes are synchronously adjusted. This adjustment can prevent the overload of a single node, while allowing the adjacent areas to cooperate in sensing, improving the intelligence and stability of the entire sensor light network. Specifically, the sensing sensitivity of the adjacent nodes is synchronously improved to share part of the target detection task; similarly, the sensing range of the adjacent nodes is correspondingly expanded to ensure that the surrounding areas can be better covered and reduce excessive dependence on the central node. Through the synchronous adjustment of the second sensor light node and its adjacent nodes, new K collaborative lighting-sensing schemes are generated. These schemes not only take into account the adjustment of individual nodes, but also optimize the coordination of the entire sensor light network through the collaboration of adjacent nodes.

[0073] Furthermore, the method further comprises: The ambient light is detected by the light sensor built into the radar sensor light to obtain the ambient light intensity coefficient; and the overall brightness of the K radar sensor lights is adaptively adjusted according to the ambient light intensity coefficient.

[0074] Each radar sensor light has a built-in light sensor for real-time detection of natural light intensity in the surrounding environment. The light sensor can sense changes in light. For example, the light level in the environment will be significantly different under different light conditions such as day, night, cloudy, and sunny. The light sensor determines the light intensity of the current environment by detecting the amount of photons entering its sensing range, and generates an ambient light intensity coefficient based on the light intensity. The coefficient is a numerical value used to describe the light conditions of the current environment. Generally, a higher light intensity coefficient represents sufficient light, such as during the day; while a lower coefficient indicates insufficient light, such as at night or in a dark environment. The calculation of the light intensity coefficient can be based on a preset reference value. For example, in the case of strong sunlight during the day, the light sensor will detect a higher light level and generate a light intensity coefficient close to the reference maximum value; while at night, the light intensity coefficient will be close to the minimum value.

[0075] When the ambient light intensity coefficient changes, the overall brightness of the K radar sensor lights is adaptively adjusted. Each sensor light will dynamically adjust its brightness according to the light intensity detected at its location. Specifically, in a strong light environment, such as during the day, the brightness of the sensor light can be reduced according to the higher light intensity coefficient to reduce unnecessary power consumption; in a weak light environment, such as at night, the brightness of the sensor light can be increased according to the lower light intensity coefficient to ensure that there is sufficient light in the area to meet safety and functional requirements. By intelligently adjusting the brightness under different light conditions, it is possible to provide reasonable lighting brightness under different light conditions, which not only improves energy efficiency but also meets lighting needs.

[0076] In summary, the multi-node collaborative radar sensor light intelligent deployment method provided in the embodiment of the present application has the following technical effects: By acquiring three-dimensional maps and deploying K radar sensor lights, the deployment positions of the sensor lights can be flexibly designed according to actual environmental conditions to ensure that the coverage area of ​​the radar sensor lights is optimal, avoiding blind spots and unnecessary overlaps, and thus achieving precise coverage; based on the detection of adjacent sensor lights and the establishment of a topological structure of sensor light nodes, it is possible to ensure that each sensor light communicates and coordinates with the surrounding sensor lights, thereby enhancing the stability and efficiency of the overall sensing system; mobile target sensing performed according to a preset cycle can monitor mobile targets in the coverage area in real time, and obtain real-time mobile target density data based on the target's activity. Combined with the division of density levels, the system can dynamically adjust the parameters of the sensor lights according to different target distributions. This real-time monitoring and dynamic adjustment can ensure the lighting system The system and sensing system can adapt to the complex and changeable target activity environment, and can respond in time and make appropriate adjustments regardless of whether the target activity is frequent or rare; the density level data of each radar sensor light node is uploaded to the data processing center, and a multi-node collaborative management model is used to conduct collaborative analysis among multiple nodes to generate an optimized management plan. This management method can not only effectively coordinate the work of adjacent sensor lights to avoid excessive burden on a single sensor light, but also achieve load balancing of the entire sensor light network, effectively avoiding waste of resources; the multi-node collaborative management plan is issued to realize the automated lighting management and sensing management of K radar sensor lights. Through this intelligent sensing and lighting adjustment, not only can regional safety and visual comfort be ensured, but also energy consumption can be greatly reduced, achieving a technical effect of high efficiency and energy saving.

[0077] Embodiment 2 is based on the same inventive concept as the multi-node collaborative radar sensor light intelligent deployment method in the above embodiment. Figure 2 As shown, the embodiment of the present application provides a multi-node collaborative radar sensor light intelligent deployment device, the device comprising: A radar sensor light layout module 10, the radar sensor light layout module 10 is used to collect and obtain a regional three-dimensional map of the target area, and layout K radar sensor lights based on the regional three-dimensional map, and obtain K layout coordinates and K dynamic sensing ranges according to the layout results, wherein K is an integer greater than 1; a proximity sensor light detection module 20, the proximity sensor light detection module 20 is used to perform proximity sensor light detection based on the K layout coordinates through the built-in wireless communication module of the radar sensor light, and generate K proximity sensor light detection information; a topological connection module 30, the topological connection module 30 is used to define a graph connection attribute, and topologically connect the K proximity sensor light detection information based on the graph connection attribute to establish a sensor light node topology structure; a moving target sensing module 40, the moving target sensing module 40 is used to perform moving target sensing through the K radar sensor lights according to a preset time period, and obtain K mobile target sensing data, wherein the K mobile target sensing data include K mobile target density data; a density level division module 50, the density level division module 50 is used to perform density level division on the K mobile target density data according to a preset density level, and obtain K mobile target density level data; a multi-node collaborative analysis module 60, the multi-node collaborative analysis module 60 is used to upload the K mobile target density level data to a data processing center through the K radar sensor lights, and through a multi-node collaborative management model in the data processing center, combined with the sensor light node topology structure, perform multi-node collaborative analysis of the K radar sensor lights to obtain a multi-node collaborative management solution; a lighting management module 70, the lighting management module 70 is used to send the multi-node collaborative management solution to the K radar sensor lights, and perform lighting management and sensing management of the K radar sensor lights.

[0078] Furthermore, the device further includes a dynamic sensing range acquisition module to perform the following operation steps: Interactively obtain the regional boundary of the target area, collect environmental information within the regional boundary, and obtain regional environmental information; use the regional boundary as a constraint to perform three-dimensional modeling on the regional environmental information, and obtain a regional three-dimensional map based on the regional three-dimensional model; interactively obtain the original lighting layout information of the target area, and obtain M original lighting areas of M original lighting points in the original lighting layout information; fit the M original lighting areas to the regional three-dimensional map, perform lighting area analysis, and obtain a lighting point adjustment table; increase, decrease, move and adjust the M original lighting points according to the lighting point adjustment table, and layout the K radar sensing lights according to the adjusted points; after the layout is completed, obtain K layout coordinates of the K radar sensing lights according to the adjusted points, and interactively obtain the K dynamic sensing ranges based on the basic parameters of the K radar sensing lights.

[0079] Furthermore, the device also includes a lighting point adjustment table acquisition module to perform the following operation steps: fitting the M original lighting areas to the three-dimensional map of the area to obtain P lighting blind areas and Q lighting overlapping areas; adjusting the lighting points with the goal of minimizing the P lighting blind areas and Q lighting overlapping areas to obtain the lighting point adjustment table.

[0080] Furthermore, the device further includes a multi-node collaborative management solution acquisition module to perform the following operation steps: Based on the mobile target sensing records of historical time, extract the historical mobile target density data set of multiple time points and multiple sensing positions to obtain the historical mobile target density level data set; formulate lighting-sensing schemes for the historical mobile target density level data set one by one to obtain a sample lighting-sensing scheme set, wherein the lighting-sensing scheme includes lighting brightness, lighting range, sensing sensitivity, and sensing range; based on the neural network, train the historical mobile target density level data set and the sample lighting-sensing scheme set to obtain a single-node lighting-sensing management sub-model; input the K mobile target density level data into the single-node lighting-sensing management sub-model in sequence, and output K lighting-sensing schemes of the K radar sensor lights; based on the sensor light node topology structure, according to the pre-built multi-node collaborative management sub-model, perform collaborative analysis on the K lighting-sensing schemes to obtain K collaborative lighting-sensing schemes, and integrate the K collaborative lighting-sensing schemes to obtain the multi-node collaborative management scheme, wherein the single-node lighting-sensing management sub-model and the multi-node collaborative management sub-model are cascade structures in the multi-node collaborative management model.

[0081] Furthermore, the device further includes a solution set acquisition module to perform the following operation steps: Extract the first historical mobile target density level data, match them in the preset density-lighting brightness association table and the preset density-sensing sensitivity association table, and obtain the first lighting brightness and the first sensing sensitivity; extract the first historical mobile target density data, and obtain the first historical mobile target position set; based on the first historical mobile target position set, perform the minimum circumscribed circle calculation, take the center of the minimum circumscribed circle as the mobile target distribution center, and take the radius of the minimum circumscribed circle as the mobile target distribution radius, to obtain the first mobile target distribution area; generate the first lighting range and the first sensing range based on the first mobile target distribution area; integrate the first lighting brightness, the first sensing sensitivity, the first lighting range, and the first sensing range to generate a first sample lighting-sensing scheme, and add the first sample lighting-sensing scheme to the sample lighting-sensing scheme set.

[0082] Furthermore, the device also includes a lighting adjustment module to perform the following operation steps: Based on the K lighting-sensing schemes, K lighting brightnesses and K lighting ranges are extracted, and L overflow lighting brightnesses and L overflow lighting ranges that meet the lighting brightness threshold and the lighting range threshold are extracted, and the corresponding L load overflow sensing lamp nodes are located, L≤K; based on the L load overflow sensing lamp nodes, a neighboring node search is performed in the sensing lamp node topology structure to obtain L neighboring node sets; synchronous lighting brightness enhancement and synchronous lighting range enhancement are performed on the L neighboring node sets, and the K collaborative lighting-sensing schemes are obtained according to the enhancement results.

[0083] Furthermore, the device further includes a sensing and adjusting module to perform the following operation steps: A second sensor light node is randomly extracted, and second moving target sensing data and a second lighting-sensing scheme of the second sensor light node are obtained, wherein the second moving target sensing data also includes a second moving target flow frequency, and the second lighting-sensing scheme includes a second sensing sensitivity and a second sensing range; based on a preset flow frequency threshold, a flow frequency deviation is calculated for the second moving target flow frequency, and a second sensing adjustment coefficient is generated according to the calculation result, wherein the second sensing adjustment coefficient has positive and negative properties; when the second sensing adjustment coefficient belongs to a preset adjustment coefficient interval, the second sensing sensitivity and the second sensing range are independently adjusted based on the second sensing adjustment coefficient to generate a second adjusted sensing sensitivity and a second adjusted sensing range; when the second sensing adjustment coefficient does not belong to the preset adjustment coefficient interval and is a positive number, a synchronous adjustment instruction is generated; based on the synchronous adjustment instruction, while the second sensing sensitivity and the second sensing range are independently adjusted based on the second sensing adjustment coefficient, the neighboring nodes of the second sensor light node are synchronously adjusted, and the K collaborative lighting-sensing schemes are obtained according to the adjustment result.

[0084] Furthermore, the device also includes an overall brightness adjustment module to perform the following operation steps: The ambient light is detected by the light sensor built into the radar sensor light to obtain the ambient light intensity coefficient; and the overall brightness of the K radar sensor lights is adaptively adjusted according to the ambient light intensity coefficient.

[0085] Through the above-mentioned detailed description of a method for intelligent deployment of multi-node coordinated radar sensor lights in this specification, those skilled in the art can clearly understand a multi-node coordinated radar sensor light intelligent deployment device in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0086] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-node collaborative radar sensor light intelligent deployment method, characterized in that: The method comprises: Acquire a three-dimensional map of the target area, deploy K radar sensing lights based on the three-dimensional map, and obtain K deployment coordinates and K dynamic sensing ranges according to the deployment results, where K is an integer greater than 1; Based on the K layout coordinates, the proximity sensor light detection is performed through the wireless communication module built into the radar sensor light to generate K proximity sensor light detection information; Define a graph connection attribute, and perform topological connection on the K neighboring sensor lamp detection information based on the graph connection attribute to establish a sensor lamp node topology structure; According to a preset time period, the K radar sensing lights are used to sense a moving target, and K moving target sensing data are obtained, wherein the K moving target sensing data include K moving target density data; According to the preset density level, the K moving target density data are divided into density levels to obtain K moving target density level data; The K mobile target density level data are uploaded to the data processing center through the K radar sensor lights, and a multi-node collaborative analysis of the K radar sensor lights is performed through a multi-node collaborative management model in the data processing center in combination with the sensor light node topology structure to obtain a multi-node collaborative management solution; The multi-node collaborative management solution is sent to the K radar sensor lights to perform lighting management and sensing management of the K radar sensor lights.

2. A multi-node collaborative radar sensor light intelligent deployment method as claimed in claim 1, characterized in that: The method comprises: Interactively obtaining a region boundary of the target region, collecting environmental information within the region boundary, and obtaining regional environmental information; Taking the regional boundary as a constraint, three-dimensional modeling is performed on the regional environmental information, and a three-dimensional map of the region is obtained according to the regional three-dimensional model; Interactively obtain original lighting layout information of the target area, and obtain M original lighting areas of M original lighting points in the original lighting layout information; Fitting the M original lighting areas to the regional three-dimensional map, performing lighting area analysis, and obtaining a lighting point adjustment table; According to the lighting point adjustment table, the M original lighting points are adjusted by increasing, decreasing, moving, and distributing the K radar sensor lights according to the adjusted points; After the deployment is completed, K deployment coordinates of the K radar sensor lights are obtained according to the adjustment points, and the K dynamic sensing ranges are obtained by interacting with the basic parameters of the K radar sensor lights.

3. A multi-node coordinated radar sensor light intelligent deployment method as claimed in claim 2, characterized in that: The method of fitting the M original lighting areas to the regional three-dimensional map, performing lighting area analysis, and obtaining a lighting point adjustment table includes: Fitting the M original lighting areas to the regional three-dimensional map to obtain P lighting blind areas and Q lighting overlapping areas; With the goal of minimizing the P lighting blind areas and the Q lighting overlapping areas, the lighting point positions are adjusted to obtain the lighting point position adjustment table.

4. The multi-node coordinated radar sensor light intelligent deployment method according to claim 1, characterized in that: The method of performing multi-node collaborative analysis on the K radar sensor lights to obtain a multi-node collaborative management solution includes: Based on the historical mobile target sensing records, extract the historical mobile target density data set at multiple time points and multiple sensing locations to obtain the historical mobile target density level data set; Formulate lighting-sensing schemes for the historical mobile target density level data set one by one to obtain a sample lighting-sensing scheme set, wherein the lighting-sensing scheme includes lighting brightness, lighting range, sensing sensitivity, and sensing range; Based on a neural network, the historical mobile target density level data set and the sample lighting-sensing solution set are trained to obtain a single-node lighting-sensing management sub-model; Inputting the K mobile target density level data into the single-node lighting-sensing management sub-model in sequence, and outputting K lighting-sensing schemes of the K radar sensor lights; Based on the topological structure of the sensing light node, according to the pre-built multi-node collaborative management sub-model, the K lighting-sensing schemes are collaboratively analyzed to obtain K collaborative lighting-sensing schemes, and the K collaborative lighting-sensing schemes are integrated to obtain the multi-node collaborative management scheme, wherein the single-node lighting-sensing management sub-model and the multi-node collaborative management sub-model are cascade structures in the multi-node collaborative management model.

5. The multi-node coordinated radar sensor light intelligent deployment method as claimed in claim 4, characterized in that: The method of formulating lighting-sensing solutions for the historical mobile target density level data set one by one to obtain a sample lighting-sensing solution set includes: Extracting the first historical moving target density level data, matching it in a preset density-illumination brightness association table and a preset density-sensing sensitivity association table, and obtaining a first illumination brightness and a first sensing sensitivity; Extracting first historical moving target density data to obtain a first historical moving target position set; Based on the first historical moving target position set, a minimum circumscribed circle is calculated, the center of the minimum circumscribed circle is used as the moving target distribution center, and the radius of the minimum circumscribed circle is used as the moving target distribution radius, to obtain a first moving target distribution area; Generate a first lighting range and a first sensing range based on the first mobile target distribution area; The first lighting brightness, the first sensing sensitivity, the first lighting range, and the first sensing range are integrated to generate a first sample lighting-sensing solution, and the first sample lighting-sensing solution is added to the sample lighting-sensing solution set.

6. A multi-node coordinated radar sensor light intelligent deployment method as claimed in claim 5, characterized in that: The method of collaboratively analyzing the K lighting-sensing solutions to obtain K collaborative lighting-sensing solutions includes: Extract K lighting brightnesses and K lighting ranges based on the K lighting-sensing schemes, extract L overflow lighting brightnesses and L overflow lighting ranges that meet the lighting brightness threshold and lighting range threshold, and locate the corresponding L load overflow sensing lamp nodes, L≤K; Based on the L load overflow sensor lamp nodes, a neighboring node search is performed in the sensor lamp node topology structure to obtain L neighboring node sets; The synchronous lighting brightness enhancement and the synchronous lighting range enhancement are performed on the L neighboring node sets, and the K collaborative lighting-sensing schemes are obtained according to the enhancement results.

7. The multi-node coordinated radar sensor light intelligent deployment method as claimed in claim 5, characterized in that: The method further comprises: performing collaborative analysis on the K lighting-sensing schemes to obtain K collaborative lighting-sensing schemes. Randomly extract a second sensor light node, and obtain second moving target sensing data and a second lighting-sensing scheme of the second sensor light node, wherein the second moving target sensing data further includes a second moving target flow frequency, and the second lighting-sensing scheme includes a second sensing sensitivity and a second sensing range; Based on a preset flow frequency threshold, a flow frequency deviation is calculated for the second moving target flow frequency, and a second induction adjustment coefficient is generated according to the calculation result, wherein the second induction adjustment coefficient has positive and negative properties; When the second sensing adjustment coefficient belongs to the preset adjustment coefficient range, the second sensing sensitivity and the second sensing range are independently adjusted based on the second sensing adjustment coefficient to generate a second adjusted sensing sensitivity and a second adjusted sensing range; When the second sensing adjustment coefficient does not belong to the preset adjustment coefficient interval and is a positive number, generating a synchronous adjustment instruction; Based on the synchronous adjustment instruction, while the second sensing sensitivity and the second sensing range are independently adjusted based on the second sensing adjustment coefficient, the neighboring nodes of the second sensing lamp node are synchronously adjusted, and the K collaborative lighting-sensing schemes are obtained according to the adjustment results.

8. The multi-node coordinated radar sensor light intelligent deployment method according to claim 1, characterized in that: The method further comprises: The ambient light intensity coefficient is obtained by detecting the ambient light through the light sensor built into the radar sensor light; The overall brightness of the K radar sensor lights is adaptively adjusted according to the ambient light intensity coefficient.

9. A multi-node collaborative radar sensor light intelligent deployment device, characterized in that: A device for implementing a multi-node collaborative radar sensor light intelligent deployment method according to any one of claims 1 to 8, the device comprising: A radar sensor light layout module, the radar sensor light layout module is used to collect and obtain a regional three-dimensional map of the target area, layout K radar sensor lights based on the regional three-dimensional map, and obtain K layout coordinates and K dynamic sensing ranges according to the layout results, wherein K is an integer greater than 1; A proximity sensor light detection module, the proximity sensor light detection module is used to perform proximity sensor light detection based on the K layout coordinates through a wireless communication module built into the radar sensor light to generate K proximity sensor light detection information; A topological connection module, the topological connection module is used to define graph connection attributes, and to perform topological connection on the K neighboring sensor lamp detection information based on the graph connection attributes to establish a sensor lamp node topological structure; A moving target sensing module, the moving target sensing module is used to sense moving targets through the K radar sensing lights according to a preset time period, and obtain K moving target sensing data, wherein the K moving target sensing data include K moving target density data; A density level division module, the density level division module is used to divide the K moving target density data into density levels according to preset density levels to obtain K moving target density level data; A multi-node collaborative analysis module, which is used to upload the density level data of the K mobile targets to a data processing center through the K radar sensor lights, and to perform multi-node collaborative analysis of the K radar sensor lights through a multi-node collaborative management model in the data processing center and in combination with the sensor light node topology to obtain a multi-node collaborative management solution; A lighting management module, wherein the lighting management module is used to send the multi-node collaborative management solution to the K radar sensor lights to perform lighting management and sensing management of the K radar sensor lights.

Images