Street lamp illumination intelligent control system and method based on artificial intelligence

Abstract

The invention discloses a street lamp illumination intelligent control system and method based on artificial intelligence, and relates to the field of street lamp illumination intelligent control, and the system comprises a data collection module, an environment module, a driving module, an efficiency module and an automatic adjustment module. Carrying out vegetation scattering state, road reflection state and road fluctuation state analysis on the vegetation information and the road surface information to obtain an environment brightness value of each road area, carrying out pedestrian walking and vehicle driving state analysis on the pedestrian information and the vehicle information to obtain a vehicle driving brightness value of each road area, carrying out road brightness analysis on the street lamp information to obtain a road brightness value of each road area; according to the method, the brightness distribution value of each road area range is obtained, the environment brightness value of each road area and the driving brightness demand value of each road area are received, the illumination efficiency of each road area is judged, analyzed and analyzed with a set illumination efficiency threshold value, the illumination power of the street lamps is obtained and automatically adjusted, and the city management cost can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control of street lamp lighting, and in particular to an intelligent control system and method for street lamp lighting based on artificial intelligence. Background Art

[0002] Urban infrastructure is becoming more and more complete, but how to manage urban infrastructure has become a major focus at present. Among them, street light management in urban roads is particularly important. Traditional street lighting control often relies on manual adjustment of street light power, which cannot be adjusted in a timely and accurate manner, and also increases the cost of urban management. Intelligent street lighting control systems based on artificial intelligence have emerged.

[0003] When traditional street lighting is intelligently controlled, it is unable to automatically adjust and control the different lighting conditions of each road, resulting in traffic accidents due to insufficient brightness of street lights on some sections of road. The brightness of some sections of road is also set too high, which greatly increases the cost of urban management. Therefore, automatic adjustment and control of the different conditions of each road is a technical problem that needs to be solved.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to solve the technical problems raised by the above background technology, the present invention is proposed. The embodiments of the present invention provide an intelligent control system and method for street lighting based on artificial intelligence.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides an artificial intelligence-based intelligent control system for street lighting, comprising a data acquisition module, an environment module, a vehicle module, an efficiency module and an automatic adjustment module.

[0008] The data acquisition module is used to collect vegetation information, road surface information, pedestrian information, vehicle information and street light information, and send it to the environment module, vehicle module and efficiency module;

[0009] The environment module analyzes the scattering state of vegetation, the reflection state of road and the undulation state of road on the vegetation information and road surface information to obtain the environment brightness and scattering value of each road area;

[0010] The vehicle traffic module analyzes pedestrian and vehicle walking statuses based on pedestrian information and vehicle information to obtain vehicle traffic light demand values ​​for each road area;

[0011] The efficiency module performs road brightness analysis on the street lamp information to obtain the brightness distribution value of each road area, receives the ambient brightness dispersion value of each road area and the vehicle brightness requirement value of each road area, and performs determination and analysis on the lighting efficiency of each road area;

[0012] The automatic adjustment module is used to receive the comprehensive lighting efficiency coefficient of each road area, analyze it with the set lighting efficiency threshold, and obtain automatic adjustment processing of street lamp lighting power.

[0013] Furthermore, the environmental brightness scatter value analysis steps of each road area are as follows:

[0014] The reflectivity of the building surface and the ground reflectivity of each road area are obtained by the spectral reflectivity meter, and the reflectivity of the building surface and the ground reflectivity are summed to obtain the building-ground reflectivity of each road area; measurement points are set at a certain interval along the road direction of each road area, and the elevation of each measurement point is obtained by the total station, and the measurement points are sorted in the order of measurement, and the elevation of each measurement point is input into the three-dimensional coordinate system, and the adjacent measurement points are connected in sequence by line segments according to the measurement order, and the angle formed by the line segment formed by each measurement point and the previous adjacent sorted measurement point and the line segment formed by each measurement point and the next adjacent sorted measurement point are obtained to obtain the angle value jz of each measurement point i , i represents the number of the measuring point, the angles of each measuring point are averaged to obtain the mean value of the angles of the measuring points Jj, and the terrain undulation rate Dq of each road area is calculated;

[0015] The reflectivity of the building site, terrain undulation and plant shadow scatter value are processed through graphic construction, and the environmental brightness scatter value of each road area is obtained by analysis.

[0016] Furthermore, the steps of analyzing the plant shadow dispersion value are as follows:

[0017] The leaf scatter value, the total light intensity of leaf scatter and the surface value of leaf scatter are combined with the leaf area index value Yz and the crown and branch state value Gz to calculate the plant shadow scatter value Zy of each road area.

[0018] Furthermore, the crown and branch state value analysis steps are as follows:

[0019] Step 1: Obtain the spatial position and morphological information of tree crowns and branches in each road area through 3D laser scanning, select a plane parallel to the road cross-section as the projection plane, binarize the projected image to obtain a black-and-white binary image, with the tree branches as white pixels and the background as black pixels. Remove noise through corrosion and collision to obtain a binary image with noise removed, and traverse each pixel in the binary image;

[0020] Step 2: Count the number of white pixels in the eight neighboring pixels of the white pixel. When the number of white pixels is greater than 1 and the white pixels belong to different branch contours, the current pixel is determined to be an intersection. Starting from the intersection, the neighboring pixels of the current pixel are continuously checked along the selected branch contour to determine the position of the next pixel for tracking. When a new intersection is encountered, the position relationship between branch 1 and branch 2 at the previous intersection is recorded, and the position relationship between branch 1 and branch 2 at the new intersection is recorded. When the relative position relationship of the branches between the two intersections is reversed upside down, it is determined that there is an up-and-down crossing. The path of the current pixel is tracked. If it returns to the starting intersection, it is determined that a circle of winding is completed, and the number of winding circles is increased by 1.

[0021] Step 3: Repeat step 2 for all starting intersections and tracking paths in the image, traverse all intersections, obtain the total winding number of branches in each road area, and count the total number of intersections to obtain the total number of intersections in each road area;

[0022] Step 4: Get the identified intersections, identify the intersecting line segments of each intersection, get the associated line segment list of each intersection, combine the line segments in the associated line segment list in pairs, identify the pixel coordinates of the two endpoints of L1 for one set of line segments L1 and L2, and calculate the vector dot product of line segments L1 and L2 by formula. The magnitude of the vector L1 and the magnitude of the vector L2 The angle θ12 between line segments L1 and L2 is calculated by the formula, and the above operation is repeated to obtain the angle formed by each intersection corresponding to each intersecting line segment, and the maximum and minimum values ​​of the angle are counted, and the angle distribution value of each road area branch is obtained by subtracting the minimum value from the maximum value of the angle;

[0023] Step 4: Calculate the total winding number of branches in each road area, the total crossing number of branches in each road area and the angle distribution value of branches in each road area to obtain the crown state value Gz of each road area.

[0024] Furthermore, the steps for analyzing the leaf scattered deflection value and the leaf scattered total light intensity value are as follows:

[0025] A fixed laser light source position is placed on one side of the leaf pile in each road area, and a light detector is placed on the other side. Starting from the angle where the light detector is parallel to the incident light direction, it is rotated in sequence at a certain angle interval to obtain the received light intensity jq corresponding to each angular position, where the light intensity emitted by the laser light source is fixed and the light intensity is marked as fq. The received light intensity when the light detector is parallel to the incident light direction is obtained and marked as background light intensity bq. The leaf scattered light intensity sq corresponding to each angular position is obtained by analysis. A curve of scattered light intensity changing with angle is established with the scattering angle as the horizontal axis and the scattered light intensity as the vertical axis. The scattered light intensity curve is integrated when the angle changes from 0 to π / 2 to obtain the light intensity value of the forward scattering area. The light intensity value of the backscattering area is obtained by integrating when the angle changes from π / 2 to π, and the light intensity value of the forward scattering area is divided by the light intensity value of the backscattering area to obtain the scattered light value of the fallen leaves. The light intensity value of the forward scattering area and the light intensity value of the backscattering area are summed to obtain the total light intensity value of the fallen leaves. A planar light detection array is placed above the fallen leaves pile in each road area, and a laser light source with a fixed light intensity is turned on. The light intensity at each position of the plane is measured at the same time, and the light intensity at each position is compared and analyzed with the set reference light intensity threshold. When the light intensity at a position is greater than or equal to the set reference light intensity threshold, the position is classified as the scattered light distribution range, the boundary position of the scattered light distribution range is identified, and the surface value of the fallen leaves scattered light distribution is obtained by analysis.

[0026] Furthermore, the vegetation leaf area index value analysis steps are as follows:

[0027] Through indirect optical instruments, the initial light intensity Cq is emitted in the vegetation of each road area, and the emitted light is transmitted through the leaves of the vegetation. The light intensity transmitted through the leaves of the vegetation is received, the vegetation type of each road area is identified, and the extinction coefficient value of the vegetation is obtained. The leaf area index value Yz of the vegetation in each road area is calculated by the formula.

[0028] Furthermore, the steps of analyzing the vehicle lane brightness demand value of each road area are as follows:

[0029] Obtain the number of pedestrians and vehicles in each road area, and divide them by the area of ​​each road area to obtain the pedestrian density value and vehicle density value, add them together to obtain the density value of each road area; obtain the duration of the vertical and horizontal displacement of the eyeballs of pedestrians in each road area without exceeding the set pixel threshold through the eye tracking device, and mark it as the gaze duration of each pedestrian in each road area. When the gaze duration of each pedestrian is greater than or equal to a certain duration, the pedestrian is determined as a gaze point, and the number of gaze points in each road area is counted and divided by the total number of monitored people in the area to obtain the gaze point frequency. Divide the number of gaze points in each road area by the area of ​​the road area to obtain the gaze point density, and obtain the residence time of each gaze point in each road area, average it and obtain the gaze point frequency. The number of turns per unit time of each pedestrian in each road area and the tortuosity of the walking route are obtained by adding them up and calculating the average value to obtain the pedestrian movement trajectory complexity value of each road area. The walking route tortuosity refers to the ratio of the length of the walking path to the straight-line distance. The gaze point frequency, gaze point density, gaze point dwell time and movement trajectory complexity value are analyzed to obtain the pedestrian density heterogeneity coefficient; the turning speed and turning angle of the vehicles in each road area are obtained, added up and calculated the average value to obtain the vehicle corner complexity value of each road area, the pedestrian density heterogeneity coefficient and the vehicle corner complexity value are analyzed to obtain the density adjustment factor coefficient, and the density value of each road area is multiplied by the density adjustment factor coefficient to obtain the vehicle lighting demand value of each road area.

[0030] Furthermore, the lighting efficiency analysis steps of each road area are as follows:

[0031] Obtain the power of each street lamp in each road area and the corresponding street lamp luminous efficiency, analyze and obtain the luminous flux Gt of each road area, take the luminous center of each street lamp as the pole and the horizontal direction as the polar axis, establish the lamp light distribution curve, and obtain the angle range where the light intensity decays to a certain degree in the horizontal direction in the curve, and mark half of the angle range as the horizontal light distribution angle pθ of each street lamp. A certain degree refers to one third of the central light intensity. Obtain the height value lg of each street lamp, calculate the effective lighting width yk by formula, and obtain the spacing value LJ of each street lamp and the number of street lamps Lg, calculate by formula, obtain the lighting area Qm, and calculate by formula, obtain the bright cloth value Lb of each road area range;

[0032] The ambient light dispersion value of each road area and the vehicle light requirement value of each road area are marked as HLZ and CXL respectively, and analyzed with the light distribution value Lb of each road area to obtain the comprehensive lighting efficiency coefficient ZXL of each road area.

[0033] Furthermore, the street lamp lighting power automatic adjustment processing and analysis steps are as follows:

[0034] When the comprehensive lighting efficiency coefficient of the road area is less than the set lighting efficiency threshold lower limit, the power of the road area is determined to be abnormal, and the lighting power adjustment value is obtained through analysis. The street lamp lighting control system automatically increases the street lamp lighting power according to the bright power adjustment value;

[0035] When the comprehensive lighting efficiency coefficient of a road area is greater than the set lighting efficiency threshold upper limit, the power of the road area is determined to be abnormal, and the lighting power adjustment value is obtained through analysis. The street lamp lighting control system automatically reduces the street lamp lighting power according to the bright power adjustment value.

[0036] In a second aspect, the present invention provides an artificial intelligence-based intelligent control method for street lamp lighting, characterized in that it includes the following steps:

[0037] S1: The data acquisition module collects vegetation information, road surface information, pedestrian information, vehicle information and street light information, and sends it to the environment module, vehicle module and efficiency module;

[0038] S2: Receive vegetation information and road surface information through the environment module, and analyze the scattering state of vegetation, the reflection state of the road and the undulation state of the road accordingly to obtain the environmental brightness scattering value of each road area;

[0039] S3: The vehicle module receives pedestrian information and vehicle information, analyzes the pedestrian walking and vehicle driving status, and obtains the vehicle lighting demand value of each road area;

[0040] S4: The efficiency module receives street lamp information, analyzes road brightness, obtains brightness distribution values ​​of each road area, receives ambient brightness dispersion values ​​of each road area and vehicle brightness requirement values ​​of each road area, and determines and analyzes the lighting efficiency of each road area;

[0041] S5: The automatic adjustment module receives the comprehensive lighting efficiency coefficient of each road area, analyzes it with the set lighting efficiency threshold, and obtains automatic adjustment processing of street lamp lighting power.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention obtains the environmental brightness scatter value of each road area by analyzing the scattering state of vegetation, the road reflection state and the road undulation state of vegetation information and road surface information, obtains the vehicle brightness requirement value of each road area by analyzing the pedestrian walking and vehicle driving states of pedestrian information and vehicle information, obtains the road brightness analysis of street lamp information to obtain the brightness value of each road area, receives the environmental brightness scatter value of each road area and the vehicle brightness requirement value of each road area, determines and analyzes the lighting efficiency of each road area, can judge different lighting states of the road from the aspects of vegetation, road surface, pedestrians and vehicles and street lamp performance, and can timely and accurately analyze the lighting state of the road.

[0044] 2. The present invention receives the comprehensive lighting efficiency coefficient of each road area, analyzes it with the set lighting efficiency threshold, and automatically adjusts the lighting power of the street lamp, which can reduce the occurrence of traffic accidents due to insufficient brightness of street lamps on road sections and reduce the cost of urban management. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. The following drawings are not intentionally scaled according to the actual sizes, and the focus is on illustrating the main purpose of the present invention.

[0046] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present invention.

[0048] like Figure 1 As shown, an artificial intelligence-based intelligent control system for street lighting includes a data acquisition module, an environment module, a vehicle module, an efficiency module and an automatic adjustment module.

[0049] The data acquisition module is used to collect vegetation information, road surface information, pedestrian information, vehicle information and street light information, and send it to the environment module, vehicle module and efficiency module.

[0050] The environment module receives vegetation information and road surface information, and analyzes the scattering state of vegetation, the reflection state of the road, and the undulation state of the road based on the information to obtain the environmental brightness scattering value of each road area. The specific analysis is as follows:

[0051] Through indirect optical instruments, the initial light intensity Cq is emitted in the vegetation of each road area, and the emitted light is transmitted through the leaves of the vegetation. The light intensity received through the leaves of the vegetation is marked as Tq, and the vegetation types of each road area are identified, which are broad-leaved forest, shrub forest, coniferous forest and herbaceous vegetation. Their extinction coefficient values ​​correspond to a1, a2, a3 and a4, respectively, where a1>a2>a3>a4. The extinction coefficient value of the vegetation is obtained, marked as Xx, according to the formula Obtain the vegetation leaf area index value Yz of each road area;

[0052] The solution process of the crown and branch state value of each road area is as follows:

[0053] Step 1: Obtain the spatial position and morphological information of tree crowns and branches in each road area through 3D laser scanning, select a plane parallel to the road cross-section as the projection plane, binarize the projected image to obtain a black-and-white binary image, with the tree branches as white pixels and the background as black pixels. Remove noise through corrosion and collision to obtain a binary image with noise removed, and traverse each pixel in the binary image;

[0054] Step 2: Count the number of white pixels in the eight neighboring pixels of the white pixel. When the number of white pixels is greater than 1 and the white pixels belong to different branch contours, the current pixel is determined to be an intersection. Starting from the intersection, the neighboring pixels of the current pixel are continuously checked along the selected branch contour to determine the position of the next pixel for tracking. When a new intersection is encountered, the position relationship between branch 1 and branch 2 at the previous intersection is recorded, and the position relationship between branch 1 and branch 2 at the new intersection is recorded. When the relative position relationship of the branches between the two intersections is reversed upside down, it is determined that there is an up-and-down crossing. The path of the current pixel is tracked. If it returns to the starting intersection, it is determined that a circle of winding is completed, and the number of winding circles is increased by 1.

[0055] Step 3: Repeat step 2 for all starting intersections and tracking paths in the image, traverse all intersections, obtain the total winding number of branches in each road area, and count the total number of intersections to obtain the total number of intersections in each road area;

[0056] Step 4: Get the identified intersections, identify the intersecting line segments of each intersection, and obtain the associated line segment list [L1, L2, L3, ... LN] of each intersection, where N is the maximum value of the associated line segment number. Combine the line segments in the associated line segment list in pairs, and identify the two end pixel coordinates of L1 for one group of line segments L1 and L2, marked as (x1, y1) and (x2, y2) respectively, and the two end pixel coordinates of L2, marked as (x3, y3) and (x4, y4) respectively. According to the formula and Get the vector dot product of line segments L1 and L2 The magnitude of the vector L1 and the magnitude of the vector L2 According to the formula Obtain the angle θ12 between the line segments L1 and L2, and repeat the above operation to obtain the angle formed by each intersection corresponding to each intersecting line segment, and count the maximum and minimum values ​​of the angle, subtract the minimum value from the maximum value of the angle, and obtain the angle distribution value of each road area branch;

[0057] Step 4: Mark the total winding number of branches in each road area, the total crossing number of branches in each road area, and the angle distribution value of branches in each road area as Cr, Jj, and Jd, respectively, and perform normalization processing. According to the formula Gz=υ / (pop1×Cr+pop2×Jj+pop3×Jd), the crown state value Gz of each road area is obtained, where pop1, pop2, and pop3 are the set weight factor coefficients of the total winding number of branches, the total crossing number of branches, and the angle distribution value of branches, respectively. The specific values ​​are determined by professionals in this field. υ is the correction factor coefficient to promote the accuracy of the calculation. The specific value is 1.021;

[0058] A fixed laser light source position is placed on one side of the leaf pile in each road area, and a light detector is placed on the other side. Starting from the angle where the light detector is parallel to the incident light direction, it is rotated in sequence at a certain angle interval to obtain the received light intensity jq corresponding to each angular position, wherein the light intensity emitted by the laser light source is fixed, and the light intensity is marked as fq. The certain angle refers to 5°. The received light intensity when the light detector is parallel to the incident light direction is obtained, marked as background light intensity bq. According to the formula sq=(jq-bq) / fq, the leaf scattered light intensity sq corresponding to each angular position is obtained. With the scattering angle as the horizontal axis and the scattered light intensity as the vertical axis, a curve graph of the scattered light intensity changing with the angle is established. The scattered light intensity curve is integrated when the angle changes from 0 to π / 2 to obtain the forward scattering area light intensity value, and the scattered light intensity curve is integrated. The line is integrated when the angle changes from π / 2 to π to obtain the light intensity value of the backscattering area, and the light intensity value of the forward scattering area is divided by the light intensity value of the backscattering area to obtain the leaf scattering value, and the light intensity value of the forward scattering area and the light intensity value of the backscattering area are summed to obtain the total light intensity value of leaf scattering; a planar light detection array is placed above the leaf pile in each road area, and a laser light source with a fixed light intensity is turned on to measure the light intensity at each position of the plane at the same time, and the light intensity at each position is compared and analyzed with the set reference light intensity threshold. When the light intensity at a position is greater than or equal to the set reference light intensity threshold, the position is classified as a scattered light distribution range, the boundary position of the scattered light distribution range is identified, the boundary is decomposed into a number of triangles, and the area of ​​each triangle is summed to obtain the surface value of the leaf scattered light distribution;

[0059] The leaf scattered light value, leaf scattered light total intensity value and leaf scattered light distribution surface value are marked as Sp, Sq and Sf respectively, and normalized with the vegetation leaf area index value Yz and the crown branch value Gz. The plant shadow dispersion value Zy of each road area is obtained, where te1, te2, te3, te4 and te5 are the reference weight factor coefficients set by the leaf dispersion value, the leaf scattered total light intensity value, the leaf scattered light distribution surface value, the vegetation leaf area index value and the crown and branch state value, respectively. The specific values ​​are 1.315, 4.125, 3.121, 1.211 and 3.111, and e is a natural constant with a value of 2.718.

[0060] The reflectivity of the building surface and the ground reflectivity of each road area are obtained by the spectral reflectivity meter, and the reflectivity of the building surface and the ground reflectivity are summed to obtain the building-ground reflectivity of each road area; measurement points are set at a certain interval along the road direction of each road area, and the certain interval is 1m. The elevation of each measurement point is obtained by the total station, and the measurement points are sorted in the order of measurement, and the elevation of each measurement point is input into the three-dimensional coordinate system. The adjacent measurement points are connected in sequence by line segments in the measurement order, and the angle formed by the line segment formed by each measurement point and the previous adjacent sorted measurement point and the line segment formed by each measurement point and the next adjacent sorted measurement point are obtained to obtain the angle value jz of each measurement point i , i represents the number of the measuring point, i = 1, 2, 3, ..., n1, the angle of each measuring point is averaged to obtain the mean angle Jj of the measuring point, according to the set formula The terrain undulation rate Dq of each road area is obtained, and λ is the correction factor coefficient, and the specific value is determined by personnel in this professional field; the building reflectivity, terrain undulation rate and plant shadow dispersion value are normalized, and a cuboid is constructed by taking the terrain undulation rate and plant shadow dispersion value as the length and width of the bottom side of the cuboid respectively, and taking the sum of the plant shadow dispersion value and the terrain undulation rate as the height of the cuboid, and constructing a sphere inside the cuboid with the center of the cuboid as the center of the sphere, and specifically taking the building reflectivity as the radius of the sphere, identifying the volume of the irregular body formed by the cuboid and the sphere, and marking it as the environmental brightness dispersion value of each road area;

[0061] The vehicle module receives pedestrian information and vehicle information, analyzes the pedestrian and vehicle driving status, and obtains the vehicle lighting demand value of each road area. The specific analysis is as follows:

[0062] Obtain the number of pedestrians and vehicles in each road area, and divide them by the area of ​​each road area to obtain the pedestrian density value and the vehicle density value, add them together to obtain the density value of each road area; obtain the duration of the vertical and horizontal displacement of the eyeballs of pedestrians in each road area without exceeding the set pixel threshold through the eye tracking device, and mark it as the gaze duration of each pedestrian in each road area; when the gaze duration of each pedestrian is greater than or equal to a certain duration, the pedestrian is determined as a gaze point, and the certain duration is specifically 100 milliseconds. Count the number of gaze points in each road area and divide it by the total number of monitored people in the area to obtain the gaze point frequency; divide the number of gaze points in each road area by the area of ​​the road area to obtain the gaze point density; obtain the residence time of each gaze point in each road area, average it, obtain the dwell time of the gaze point, and obtain the frequency of each gaze point in each road area. The number of turns per unit time and the tortuosity of the walking route are added and averaged to obtain the pedestrian movement trajectory complexity value of each road area. The walking route tortuosity refers to the ratio of the length of the walking path to the straight-line distance. The gaze point frequency, gaze point density, gaze point dwell time and movement trajectory complexity value are weighted and multiplied by the corresponding weight factor coefficient to obtain the pedestrian density heterogeneity coefficient; the turning speed and turning angle of the vehicle in each road area are obtained, added and averaged to obtain the vehicle corner heterogeneity value of each road area, the pedestrian density heterogeneity coefficient and the vehicle corner heterogeneity value are normalized, and multiplied by the correction factor coefficient values ​​h1 and h2 respectively, and the sum is obtained to obtain the density adjustment factor coefficient, and the density of each road area is multiplied by the density adjustment factor coefficient to obtain the vehicle lighting demand value of each road area;

[0063] The efficiency module receives street light information, analyzes the road brightness, obtains the brightness value of each road area, receives the ambient brightness value of each road area and the vehicle brightness requirement value of each road area, and determines and analyzes the lighting efficiency of each road area. The specific analysis is as follows:

[0064] Obtain the power of each street lamp in each road area and the corresponding luminous efficiency of the street lamp, multiply the street lamp power and luminous efficiency, and sum them to obtain the luminous flux Gt of each road area. Take the luminous center of each street lamp as the pole and the horizontal direction as the polar axis to establish a lamp distribution curve. Each point on the curve represents the light intensity of the lamp in each angle direction. Obtain the angle range in the curve where the light intensity decays to a certain degree in the horizontal direction, and mark half of the angle range as the horizontal distribution angle pθ of each street lamp. A certain degree refers to one third of the central light intensity. Obtain the height value lg of each street lamp, and obtain the effective lighting width yk according to the formula yk=2×lg×tan pθ. Obtain the spacing value LJ of each street lamp and the number of street lamps Lg according to the formula

[0065] When yk<LJ, the area of ​​the lighting area Qm is obtained. According to the formula Lb=u×Gt / Qm, the bright cloth value Lb of each road area is obtained. u is the correction factor coefficient, and the specific value is 1.212;

[0066] The ambient light dispersion value of each road area and the required light value of each road area are marked as HLZ and CXL respectively, and normalized with the light distribution value Lb of each road area. The comprehensive lighting efficiency coefficient ZXL of each road area is obtained, where xox1, xox2 and xox3 are respectively the setting weight factors of the ambient light dispersion value of each road area, the vehicle light requirement value of each road area and the light distribution value of each road area. The specific values ​​are determined by professionals in this professional field.

[0067] The automatic adjustment module is used to receive the comprehensive lighting efficiency coefficient of each road area, analyze it with the set lighting efficiency threshold, and obtain the automatic adjustment processing of street lamp lighting power. The specific analysis is as follows:

[0068] When the comprehensive lighting efficiency coefficient of the road area is less than the set lighting efficiency threshold lower limit, the road area power is determined to be abnormal, the difference between the comprehensive lighting efficiency coefficient of the road area and the lighting efficiency threshold is calculated, and the efficiency bias value is obtained. The efficiency bias value is multiplied by the lighting power conversion coefficient to obtain the lighting power adjustment value, and the street lamp lighting control system automatically increases the street lamp lighting power according to the bright power adjustment value;

[0069] When the comprehensive lighting efficiency coefficient of the road area is greater than the set lighting efficiency threshold upper limit, the road area power is determined to be abnormal, the difference between the comprehensive lighting efficiency coefficient of the road area and the lighting efficiency threshold is calculated, and the efficiency bias value is obtained. The efficiency bias value is multiplied by the lighting power conversion coefficient to obtain the lighting power adjustment value, and the street lamp lighting control system automatically reduces the street lamp lighting power according to the bright power adjustment value;

[0070] When the comprehensive lighting efficiency coefficient of the road area is greater than or equal to the set lighting efficiency threshold lower limit value and less than or equal to the set lighting efficiency threshold upper limit value, it is determined that the lighting of the road area is normal and no corresponding operation is required.

[0071] An intelligent control method for street lighting based on artificial intelligence comprises the following steps:

[0072] S1: The data acquisition module collects vegetation information, road surface information, pedestrian information, vehicle information and street light information, and sends it to the environment module, vehicle module and efficiency module;

[0073] S2: Receive vegetation information and road surface information through the environment module, and analyze the scattering state of vegetation, the reflection state of the road and the undulation state of the road accordingly to obtain the environmental brightness scattering value of each road area;

[0074] S3: The vehicle module receives pedestrian information and vehicle information, analyzes the pedestrian walking and vehicle driving status, and obtains the vehicle lighting demand value of each road area;

[0075] S4: The efficiency module receives street lamp information, analyzes road brightness, obtains brightness distribution values ​​of each road area, receives ambient brightness dispersion values ​​of each road area and vehicle brightness requirement values ​​of each road area, and determines and analyzes the lighting efficiency of each road area;

[0076] S5: The automatic adjustment module receives the comprehensive lighting efficiency coefficient of each road area, analyzes it with the set lighting efficiency threshold, and obtains automatic adjustment processing of street lamp lighting power.

[0077] The above is an explanation of the present invention and should not be considered as a limitation thereof. Although several exemplary embodiments of the present invention have been described, it will be readily appreciated by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present invention. Therefore, all such modifications are intended to be included within the scope of the present invention as defined in the claims. It should be understood that the above is an explanation of the present invention and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present invention is defined by the claims and their equivalents.

Claims

1. An intelligent street lighting control system based on artificial intelligence, characterized in that: include: The data collection module is used to collect vegetation information, road surface information, pedestrian information, vehicle information and street light information, and send it to the environment module, vehicle module and efficiency module; The environment module analyzes the scattering state of vegetation, the reflection state of road and the undulation state of road based on the vegetation information and road surface information to obtain the environmental brightness and scattering value of each road area. The vehicle traffic module analyzes pedestrian and vehicle information and the status of pedestrians and vehicles, and obtains the vehicle traffic light demand value of each road area; The efficiency module analyzes the road brightness of the street lamp information to obtain the brightness distribution value of each road area, receives the ambient brightness dispersion value of each road area and the vehicle brightness demand value of each road area, and makes a judgment and analysis on the lighting efficiency of each road area; The automatic adjustment module is used to receive the comprehensive lighting efficiency coefficient of each road area, analyze it with the set lighting efficiency threshold, and obtain automatic adjustment processing of street lamp lighting power.

2. According to claim 1, the intelligent street lighting control system based on artificial intelligence is characterized in that: The steps for analyzing the ambient brightness value of each road area are as follows: The reflectivity of the building surface and the ground reflectivity of each road area are obtained by the spectral reflectivity meter, and the reflectivity of the building surface and the ground reflectivity are summed to obtain the building-ground reflectivity of each road area; measurement points are set at a certain interval along the road direction of each road area, and the elevation of each measurement point is obtained by the total station, and the measurement points are sorted in the order of measurement, and the elevation of each measurement point is input into the three-dimensional coordinate system, and the adjacent measurement points are connected in sequence by line segments according to the measurement order, and the angle formed by the line segment formed by each measurement point and the previous adjacent sorted measurement point and the line segment formed by each measurement point and the next adjacent sorted measurement point are obtained to obtain the angle value jz of each measurement point i , i represents the number of the measuring point, the angles of each measuring point are averaged to obtain the mean value of the angles of the measuring points Jj, and the terrain undulation rate Dq of each road area is calculated; The reflectivity of the building site, terrain undulation and plant shadow scatter value are processed through graphic construction, and the environmental brightness scatter value of each road area is obtained by analysis.

3. The intelligent street lighting control system based on artificial intelligence according to claim 2 is characterized in that: The steps of analyzing the plant shadow dispersion value are as follows: The leaf scatter value, the total light intensity of leaf scatter and the surface value of leaf scatter are combined with the leaf area index value Yz and the crown and branch state value Gz to calculate the plant shadow scatter value Zy of each road area.

4. The intelligent street lighting control system based on artificial intelligence according to claim 3 is characterized in that: The crown and branch state value analysis steps are as follows: Step 1: Obtain the spatial position and morphological information of tree crowns and branches in each road area through 3D laser scanning, select a plane parallel to the road cross-section as the projection plane, binarize the projected image to obtain a black-and-white binary image, with the tree branches as white pixels and the background as black pixels. Remove noise through corrosion and collision to obtain a binary image with noise removed, and traverse each pixel in the binary image; Step 2: Count the number of white pixels in the eight neighboring pixels of the white pixel. When the number of white pixels is greater than 1 and the white pixels belong to different branch contours, the current pixel is determined to be an intersection. Starting from the intersection, the neighboring pixels of the current pixel are continuously checked along the selected branch contour to determine the position of the next pixel for tracking. When a new intersection is encountered, the position relationship between branch 1 and branch 2 at the previous intersection is recorded, and the position relationship between branch 1 and branch 2 at the new intersection is recorded. When the relative position relationship of the branches between the two intersections is reversed upside down, it is determined that there is an up-and-down crossing. The path of the current pixel is tracked. If it returns to the starting intersection, it is determined that a circle of winding is completed, and the number of winding circles is increased by 1. Step 3: Repeat step 2 for all starting intersections and tracking paths in the image, traverse all intersections, obtain the total winding number of branches in each road area, and count the total number of intersections to obtain the total number of intersections in each road area; Step 4: Get the identified intersections, identify the intersecting line segments of each intersection, get the associated line segment list of each intersection, combine the line segments in the associated line segment list in pairs, identify the pixel coordinates of the two endpoints of L1 for one set of line segments L1 and L2, and calculate the vector dot product of line segments L1 and L2 by formula. The magnitude of the vector L1 and the magnitude of the vector L2 The angle θ12 between line segments L1 and L2 is calculated by the formula, and the above operation is repeated to obtain the angle formed by each intersection corresponding to each intersecting line segment, and the maximum and minimum values ​​of the angle are counted, and the angle distribution value of each road area branch is obtained by subtracting the minimum value from the maximum value of the angle; Step 4: Calculate the total winding number of branches in each road area, the total crossing number of branches in each road area and the angle distribution value of branches in each road area to obtain the crown state value Gz of each road area.

5. The intelligent street lighting control system based on artificial intelligence according to claim 3 is characterized in that: The analysis steps of the fallen leaf scattered value and the fallen leaf scattered total light intensity value are as follows: A fixed laser light source position is placed on one side of the leaf pile in each road area, and a light detector is placed on the other side. Starting from the angle where the light detector is parallel to the incident light direction, it is rotated in sequence at a certain angle interval to obtain the received light intensity jq corresponding to each angular position, where the light intensity emitted by the laser light source is fixed and the light intensity is marked as fq. The received light intensity when the light detector is parallel to the incident light direction is obtained and marked as background light intensity bq. The leaf scattered light intensity sq corresponding to each angular position is obtained by analysis. A curve of scattered light intensity changing with angle is established with the scattering angle as the horizontal axis and the scattered light intensity as the vertical axis. The scattered light intensity curve is integrated when the angle changes from 0 to π / 2 to obtain the light intensity value of the forward scattering area. The light intensity value of the backscattering area is obtained by integrating when the angle changes from π / 2 to π, and the light intensity value of the forward scattering area is divided by the light intensity value of the backscattering area to obtain the scattered light value of the fallen leaves. The light intensity value of the forward scattering area and the light intensity value of the backscattering area are summed to obtain the total light intensity value of the fallen leaves. A planar light detection array is placed above the fallen leaves pile in each road area, and a laser light source with a fixed light intensity is turned on. The light intensity at each position of the plane is measured at the same time, and the light intensity at each position is compared and analyzed with the set reference light intensity threshold. When the light intensity at a position is greater than or equal to the set reference light intensity threshold, the position is classified as the scattered light distribution range, the boundary position of the scattered light distribution range is identified, and the surface value of the fallen leaves scattered light distribution is obtained by analysis.

6. The intelligent street lighting control system based on artificial intelligence according to claim 2 is characterized in that: The vegetation leaf area index value analysis steps are as follows: Through indirect optical instruments, the initial light intensity Cq is emitted in the vegetation of each road area, and the emitted light is transmitted through the leaves of the vegetation. The light intensity transmitted through the leaves of the vegetation is received, the vegetation type of each road area is identified, and the extinction coefficient value of the vegetation is obtained. The leaf area index value Yz of the vegetation in each road area is calculated by the formula.

7. The intelligent street lighting control system based on artificial intelligence according to claim 1 is characterized in that: The steps for analyzing the vehicle lane brightness demand value of each road area are as follows: Obtain the number of pedestrians and vehicles in each road area, and divide them by the area of ​​each road area to obtain the pedestrian density value and vehicle density value, add them together to obtain the density value of each road area; obtain the duration of the vertical and horizontal displacement of the eyeballs of pedestrians in each road area without exceeding the set pixel threshold through the eye tracking device, and mark it as the gaze duration of each pedestrian in each road area. When the gaze duration of each pedestrian is greater than or equal to a certain duration, the pedestrian is determined as a gaze point, and the number of gaze points in each road area is counted and divided by the total number of monitored people in the area to obtain the gaze point frequency. Divide the number of gaze points in each road area by the area of ​​the road area to obtain the gaze point density, and obtain the residence time of each gaze point in each road area, average it and obtain the gaze point frequency. The number of turns per unit time of each pedestrian in each road area and the tortuosity of the walking route are obtained by adding them up and calculating the average value to obtain the pedestrian movement trajectory complexity value of each road area. The walking route tortuosity refers to the ratio of the length of the walking path to the straight-line distance. The gaze point frequency, gaze point density, gaze point dwell time and movement trajectory complexity value are analyzed to obtain the pedestrian density heterogeneity coefficient; the turning speed and turning angle of the vehicles in each road area are obtained, added up and calculated the average value to obtain the vehicle corner complexity value of each road area, the pedestrian density heterogeneity coefficient and the vehicle corner complexity value are analyzed to obtain the density adjustment factor coefficient, and the density value of each road area is multiplied by the density adjustment factor coefficient to obtain the vehicle lighting demand value of each road area.

8. The intelligent street lighting control system based on artificial intelligence according to claim 1 is characterized in that: The lighting efficiency analysis steps for each road area are as follows: Obtain the power of each street lamp in each road area and the corresponding street lamp luminous efficiency, analyze and obtain the luminous flux Gt of each road area, take the luminous center of each street lamp as the pole and the horizontal direction as the polar axis, establish the lamp light distribution curve, and obtain the angle range where the light intensity decays to a certain degree in the horizontal direction in the curve, and mark half of the angle range as the horizontal light distribution angle pθ of each street lamp. A certain degree refers to one third of the central light intensity. Obtain the height value lg of each street lamp, calculate the effective lighting width yk by formula, and obtain the spacing value LJ of each street lamp and the number of street lamps Lg, calculate by formula, obtain the lighting area Qm, and calculate by formula, obtain the bright cloth value Lb of each road area range; The ambient light dispersion value of each road area and the vehicle light requirement value of each road area are marked as HLZ and CXL respectively, and analyzed with the light distribution value Lb of each road area to obtain the comprehensive lighting efficiency coefficient ZXL of each road area.

9. The intelligent street lighting control system based on artificial intelligence according to claim 1 is characterized in that: The steps of automatically adjusting the street lamp lighting power and processing and analyzing are as follows: When the comprehensive lighting efficiency coefficient of the road area is less than the set lighting efficiency threshold lower limit, the power of the road area is determined to be abnormal, and the lighting power adjustment value is obtained through analysis. The street lamp lighting control system automatically increases the street lamp lighting power according to the bright power adjustment value; When the comprehensive lighting efficiency coefficient of a road area is greater than the set lighting efficiency threshold upper limit, the power of the road area is determined to be abnormal, and the lighting power adjustment value is obtained through analysis. The street lamp lighting control system automatically reduces the street lamp lighting power according to the bright power adjustment value.

10. An intelligent control method for street lighting based on artificial intelligence, characterized in that An artificial intelligence-based street lighting intelligent control system applied to any one of claims 1 to 9 comprises the following steps: S1: The data acquisition module collects vegetation information, road surface information, pedestrian information, vehicle information and street light information, and sends it to the environment module, vehicle module and efficiency module; S2: Receive vegetation information and road surface information through the environment module, and analyze the scattering state of vegetation, the reflection state of the road and the undulation state of the road accordingly to obtain the environmental brightness scattering value of each road area; S3: The vehicle module receives pedestrian information and vehicle information, analyzes the pedestrian walking and vehicle driving status, and obtains the vehicle lighting demand value of each road area; S4: The efficiency module receives street lamp information, analyzes road brightness, obtains brightness distribution values ​​of each road area, receives ambient brightness dispersion values ​​of each road area and vehicle brightness requirement values ​​of each road area, and determines and analyzes the lighting efficiency of each road area; S5: The automatic adjustment module receives the comprehensive lighting efficiency coefficient of each road area, analyzes it with the set lighting efficiency threshold, and obtains automatic adjustment processing of street lamp lighting power.

Images