An intelligent control system and method for street lamp lighting based on artificial intelligence

Abstract

The application discloses an intelligent control system and method for street lamp lighting based on artificial intelligence, and relates to the field of intelligent control of street lamp lighting.The system comprises a data acquisition module, an environment module, a vehicle module, an efficiency module and an automatic adjustment module, and comprises the following steps: analyzing the scattering state of vegetation, the reflection state of a road and the fluctuation state of a road based on vegetation information and road surface information to obtain the environment brightness value of each road area; analyzing the walking state of pedestrians and the driving state of vehicles based on pedestrian information and vehicle information to obtain the vehicle brightness demand value of each road area; analyzing the brightness of a road based on street lamp information to obtain the brightness distribution value of each road area; receiving the environment brightness value of each road area and the vehicle brightness demand value of each road area; determining and analyzing the lighting efficiency of each road area; analyzing the determined lighting efficiency with a set lighting efficiency threshold value; and obtaining automatic adjustment processing of the lighting power of the street lamp, so that the cost of city management can be reduced.

Description

TECHNICAL FIELD

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

[0002] City infrastructure is increasingly perfect, but how to manage city infrastructure has become a major focus. Among them, the management of street lamps in urban roads is particularly important. Traditional street lamp lighting control often relies on manual adjustment of street lamp power, which cannot timely and accurately adjust the street lamp power, and also increases the cost of city management. Therefore, an intelligent control system of street lamp lighting based on artificial intelligence is emerging.

[0003] Traditional street lamp lighting cannot automatically adjust and control different lighting states of each road during intelligent control, resulting in traffic accidents occurring due to insufficient brightness of some road sections, and also setting the brightness of some road sections too high, which greatly increases the cost of city management. Therefore, it is a technical problem to be solved to automatically adjust and control different states of each road.

[0004] In order to solve the above defects, a technical solution is provided. SUMMARY

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

[0006] The object of the present application can be achieved by the following technical solutions:

[0007] In a first aspect, the present application provides an intelligent control system of street lamp lighting based on artificial intelligence, 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 acquire vegetation information, road surface information, pedestrian information, vehicle information and street lamp information, and send them to the environment module, the vehicle module and the efficiency module;

[0009] The environment module analyzes the scattering state of vegetation, the reflection state of road and the fluctuation state of road of the vegetation information and the road surface information, and obtains the environment brightness value of each road area;

[0010] The vehicle module analyzes the walking state of pedestrians and the driving state of vehicles of the pedestrian information and the vehicle information, and obtains the vehicle brightness value of each road area;

[0011] The performance module analyzes the road light information to obtain the brightness value of each road area range, receives the ambient brightness value of each road area and the vehicle brightness demand value of each road area, and determines and analyzes the lighting performance of each road area;

[0012] The automatic adjustment module is used for receiving the comprehensive lighting performance coefficient of each road area, analyzing the set lighting performance threshold, and obtaining the automatic adjustment of the street lamp lighting power.

[0013] Further, the ambient brightness value analysis step of each road area is as follows:

[0014] The reflectivity of the building surface of each road area and the ground reflectivity of each road area are obtained by a spectral reflectance instrument, the reflectivity of the building surface is summed with the ground reflectivity to obtain the build-ground reflectivity of each road area, measurement points are set along the road direction of each road area at a certain interval, the elevations of the measurement points are obtained by a total station, the measurement points are sorted in the order of measurement, and the elevations of the measurement points are input into a three-dimensional coordinate system, adjacent measurement points are connected in sequence by a line segment according to the measurement order, and the included angle formed by each measurement point and the last adjacent sorted measurement point and the included angle formed by each measurement point and the next adjacent sorted measurement point are obtained to obtain the included angle value jz i of each measurement point, the included angle of each measurement point is calculated by the average value to obtain the average value of the included angle of the measurement point Jj, and the terrain relief rate Dq of each road area is calculated.

[0015] The build-ground reflectivity, the terrain relief rate and the plant shadow value are processed by a graphic construction to obtain the ambient brightness value of each road area.

[0016] Further, the plant shadow value analysis step is as follows:

[0017] The fallen leaf scattering deviation value, the fallen leaf scattering total light intensity value and the fallen leaf scattering light distribution area value are calculated by a formula together with the vegetation leaf area index value Yz and the crown branch state value Gz to obtain the plant shadow value Zy of each road area.

[0018] Further, the crown branch state value analysis step is as follows:

[0019] Step one: the spatial position and shape information of the tree crown of each road area are obtained by three-dimensional laser scanning, a plane parallel to the road cross section direction is selected as a projection plane, the projected image is binarized to obtain a black and white binary image, the tree branch part is white pixels and the background is black pixel value, noise is removed by corrosion and collision to obtain a noise-removed binary image, and each pixel in the binary image is traversed;

[0020] Step two: count the number of white pixels in the eight neighborhood pixels of the white pixel, when the number of white pixels is greater than 1 and the white pixels belong to different branch contours, then the current pixel is determined as a crossing point, from the crossing point, the neighborhood pixels of the current pixel are continuously checked to determine the position of the next pixel along the selected branch contour to realize tracking, when a new crossing point is encountered, the position relationship of branch one and branch two at the last intersection point is recorded, and the position relationship of branch one and branch two at the new crossing point is recorded, when the relative position relationship of the branches between the two crossing points is upside down, it is determined that there is an up-down crossing situation, the path of the current pixel is tracked, if it returns to the starting intersection point, it is determined that a winding has been completed, and the winding number is increased by 1;

[0021] Step three: repeat step two for all starting intersection points and tracking paths in the image, and when all intersection points are traversed, the total winding number of each road region branch is obtained, and the total intersection number of each road region branch is counted to obtain the total intersection number of each road region branch;

[0022] Step four: obtain the above identified intersection points, identify the intersection line segments of each intersection point to obtain the associated line segment list of each intersection point, combine the line segments of the associated line segment list two by two, identify the two end point pixel coordinates of line segment L1 and L2 in one group of line segments L1 and L2, and calculate the vector dot product of line segments L1 and L2 the modulus of vector L1 and the modulus of vector L2 Calculate the included angle θ12 between line segments L1 and L2, and repeat the above operation to obtain the included angle formed by each intersection point pair of intersection line segments, and count the maximum and minimum values of the included angle, and subtract the minimum value from the maximum value to obtain the angle distribution value of each road region branch.

[0023] Step four: calculate the total winding number of each road region branch, the total intersection number of each road region branch, and the angle distribution value of each road region branch to obtain the crown branch state value Gz of each road region.

[0024] Further, the fallen leaf scattering deviation value and the fallen leaf scattering total light intensity value analysis steps are as follows:

[0025] A fixed laser light source is placed beside the leaf pile in each road area, and a light detector is placed on the other side. The light detector is rotated at certain angle intervals from the angle parallel to the incident light direction, and the received light intensity jq corresponding to each angle position is obtained. 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 it is marked as background light intensity bq. The leaf scattering light intensity corresponding to each angle position is analyzed, and a scattering light intensity-angle curve is established with the scattering angle as the horizontal axis and the scattering light intensity as the vertical axis. The forward scattering region light intensity value is obtained by integrating the scattering light intensity curve with the angle changing from 0 to π / 2. The backward scattering region light intensity value is obtained by integrating the scattering light intensity curve with the angle changing from π / 2 to π. The leaf scattering deviation value is obtained by dividing the forward scattering region light intensity value by the backward scattering region light intensity value. The forward scattering region light intensity value and the backward scattering region light intensity value are summed to obtain the total leaf scattering light intensity value. A planar light detection array is placed above the leaf pile in each road area. A laser light source with fixed light intensity is turned on, and the light intensity at each position of the plane is measured. The light intensity at each position is compared with the set reference light intensity threshold value. When the light intensity at a position is greater than or equal to the set reference light intensity threshold value, the position is classified as a scattering light distribution range. The boundary position of the scattering light distribution range is identified, and the leaf scattering light distribution area value is obtained.

[0026] Further, the vegetation leaf area index value analysis step is as follows:

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

[0028] Further, the vehicle lighting demand value analysis step in each road area is as follows:

[0029] The number of pedestrians and the number of vehicles in each road area are obtained, and the number of pedestrians and the number of vehicles in each road area are divided by the area of each road area to obtain the pedestrian density value and the vehicle density value, which are added to obtain the density value of each road area; the eye tracking device is used to obtain the duration that the eye displacement of pedestrians in each road area in the vertical and horizontal directions does not exceed a set pixel threshold, which is marked as the gaze duration of each pedestrian in each road area, and when the gaze duration of each pedestrian is greater than or equal to a certain duration, the pedestrian is determined as a gaze point, 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, the number of gaze points in each road area is divided by the area of the road area to obtain the gaze point density, and the residence time of each gaze point in each road area is obtained, which is averaged to obtain the gaze point residence time, the number of turns per unit time and the walking route tortuosity of each pedestrian in each road area are obtained, added and averaged to obtain the pedestrian movement trajectory complexity value of each road area, and the walking route tortuosity is the ratio of the length of the walking path to the straight line distance. The gaze point frequency, the gaze point density, the gaze point residence time and the movement trajectory complexity value are analyzed to obtain the pedestrian density adjustment coefficient; the turning speed and the turning angle of the vehicle in each road area are obtained, added and averaged to obtain the vehicle angle value of each road area, and the pedestrian density adjustment coefficient and the vehicle angle 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 density value of each road area.

[0030] Further, the lighting efficiency analysis step of each road area is as follows:

[0031] The power of each street lamp in each road area and the corresponding light emitting efficiency of each street lamp are obtained, and the luminous flux Gt of each road area is analyzed to obtain the light emitting center of each street lamp as the pole point and the horizontal direction as the pole axis to establish the light distribution curve diagram, and the angle range in which the light intensity decays to a certain degree in the horizontal direction is obtained, and half of the angle range is marked as the horizontal light distribution angle pθ of each street lamp, and the certain degree refers to one third of the central light intensity, the height value lg of each street lamp is obtained, the lighting effective width yk is calculated by formula, the street lamp spacing value LJ and the street lamp number value Lg are obtained, the lighting area Qm is calculated by formula, and the brightness value Lb of each road area range is calculated by formula.

[0032] The environmental brightness value of each road area and the vehicle lighting density value of each road area are respectively marked as HLZ and CXL, and the brightness value Lb of each road area range is analyzed to obtain the comprehensive lighting efficiency coefficient ZXL of each road area.

[0033] Further, the automatic adjustment processing analysis step of the street lamp lighting power is as follows:

[0034] When the comprehensive lighting performance coefficient of the road area is less than the set lower limit value of the lighting performance threshold, it is determined that the power of the road area is abnormal, a lighting power adjustment value is obtained through analysis, and the lighting power of the street lamp is automatically increased by the street lamp lighting control system according to the lighting power adjustment value;

[0035] When the comprehensive lighting performance coefficient of the road area is greater than the set upper limit value of the lighting performance threshold, it is determined that the power of the road area is abnormal, a lighting power adjustment value is obtained through analysis, and the lighting power of the street lamp is automatically decreased by the street lamp lighting control system according to the lighting power adjustment value.

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

[0037] S1: A data acquisition module acquires vegetation information, road surface information, pedestrian information, vehicle information and street lamp information, and sends them to an environment module, a traffic module and a performance module;

[0038] S2: The environment module receives the vegetation information and the road surface information, and analyzes the scattering state of the vegetation, the reflection state of the road and the fluctuation state of the road according to the information, to obtain the environmental brightness scattering value of each road area;

[0039] S3: The traffic module receives the pedestrian information and the vehicle information, and analyzes the walking state of the pedestrians and the driving state of the vehicles, to obtain the traffic brightness demand value of each road area;

[0040] S4: The performance module receives the street lamp information, analyzes the brightness of the road, obtains the brightness distribution value of each road area, receives the environmental brightness scattering value of each road area and the traffic brightness demand value of each road area, and analyzes the lighting performance of each road area;

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

[0042] Compared with the prior art, the present application has the following advantages:

[0043] 1. The present application analyzes the scattering state of the vegetation, the reflection state of the road and the fluctuation state of the road according to the vegetation information and the road surface information, to obtain the environmental brightness scattering value of each road area, analyzes the walking state of the pedestrians and the driving state of the vehicles according to the pedestrian information and the vehicle information, to obtain the traffic brightness demand value of each road area, analyzes the brightness of the road according to the street lamp information, to obtain the brightness distribution value of each road area, receives the environmental brightness scattering value of each road area and the traffic brightness demand value of each road area, and analyzes the lighting performance of each road area, so that the lighting state of the road can be determined in terms of the vegetation, the road surface, the pedestrians and vehicles and the performance of the street lamp, and the lighting state of the road can be analyzed in time and accurately.

[0044] 2、The present application can reduce the traffic accidents caused by insufficient brightness of the street lamps, and can reduce the cost of city management. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. The following drawings are not drawn in scale, and the emphasis is on showing the main idea of the present application.

[0046] Figure 1 The system block diagram of the present application. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor also belong to the scope of protection of the present application.

[0048] As shown in Figure 1 A street lamp lighting intelligent control system based on artificial intelligence, comprising 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 acquire vegetation information, road surface information, pedestrian information, vehicle information and street lamp information, and send them to the environment module, the vehicle module and the efficiency module.

[0050] The vegetation information and the road surface information are received by the environment module, and the scattering state of the vegetation, the reflection state of the road and the undulation state of the road are analyzed accordingly, to obtain the environmental brightness scattering value of each road area. The specific analysis is as follows:

[0051] Through the indirect optical instrument, an initial light intensity Cq is emitted in the vegetation of each road area, and the emitted light is transmitted through the vegetation leaves, and the light intensity transmitted through the vegetation leaves is received and marked as Tq. The vegetation categories of each road area are identified, which are broadleaf forest, shrub forest, coniferous forest and herbaceous vegetation, and the extinction coefficient values are a1, a2, a3 and a4 respectively, wherein a1>a2>a3>a4. The extinction coefficient value of the vegetation is obtained and marked as Xx. According to the formula The vegetation leaf area index value Yz of each road area is obtained;

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

[0053] Step 1: Obtain the spatial location and morphological information of tree canopy branches in each road area through 3D laser scanning. Select a plane parallel to the cross-section of the road as the projection plane. Binarize the projected image to obtain a black and white binary image. The tree branches are white pixels and the background is black pixel values. Remove noise through erosion and collision to obtain a noise-removed binary image. Traverse each pixel in the binary image.

[0054] Step 2: Count the number of white pixels among the eight neighboring pixels of a white pixel. When the number of white pixels in the neighboring area is greater than 1 and the white pixels belong to different branch contours, the current pixel is determined to be an intersection point. Starting from the intersection point, continuously check the neighboring pixels of the current pixel along the selected branch contour to determine the position of the next pixel to achieve tracking. When a new intersection point is encountered, record the positional relationship between branch 1 and branch 2 at the previous intersection point, and record the positional relationship between branch 1 and branch 2 at the new intersection point. When the relative positional relationship of the branches between two intersection points is reversed, it is determined that there is an up-and-down crossing situation. Track the path of the current pixel. If it returns to the starting intersection point, it is determined that a loop of winding is completed, and the number of loops is increased by 1.

[0055] Step 3: Repeat Step 2 for all starting intersections and tracing paths in the image until all intersections are traversed, obtain the total number of entanglements of branches in each road area, and count the total number of intersections to obtain the total number of intersections of branches in each road area.

[0056] Step 4: Obtain the identified intersection points and identify the intersecting line segments at each intersection point to obtain a list of associated line segments [L1, L2, L3, ..., LN], where N is the maximum value of the associated line segment number. Combine the line segments in the associated line segment list in pairs. For one pair of line segments L1 and L2, identify the pixel coordinates of the two endpoints of L1, labeling them as (x1, y1) and (x2, y2) respectively, and the pixel coordinates of the two endpoints of L2, labeling them as (x3, y3) and (x4, y4) respectively. Then, use the formula... and Obtain the vector dot product of line segments L1 and L2. The magnitude of vector L1 and the magnitude of vector L2 According to the formula Obtain the angle θ12 between line segments L1 and L2, and repeat the above operation to obtain the angle formed by each intersecting line segment corresponding to each intersection point, and count the maximum and minimum values ​​of the angles. Subtract the minimum value from the maximum value of the angle to obtain the angle distribution value of the branches in each road area.

[0057] Step four: the total number of each road area branch, the total number of each road area branch intersection and the angle distribution value of each road area branch are marked as Cr, Jj and Jd respectively, normalized, and the crown branch state value Gz of each road area is obtained according to the formula Gz = υ / (pop1 × Cr + pop2 × Jj + pop3 × Jd), wherein pop1, pop2 and pop3 are respectively the total number of branches, the total number of branches and the angle distribution value of branches, and the specific numerical value is determined by the professional personnel, and υ is the correction factor, which promotes the accuracy of calculation, and the specific value is 1.021;

[0058] A fixed laser light source position is placed beside the leaf litter pile of each road area, and a light detector is placed on the other side. Starting from the angle parallel to the incident light direction of the light detector, the light detector is rotated at a certain angle interval to obtain the received light intensity jq corresponding to each angle position, wherein the light intensity emitted by the laser light source is fixed, the light intensity is marked as fq, and the certain angle is 5°. The received light intensity of the light detector parallel to the incident light direction is obtained and marked as background light intensity bq. According to the formula sq = (jq-bq) / fq, the leaf scattering light intensity sq corresponding to each angle position is obtained. The scattering angle is taken as the horizontal axis, and the scattering light intensity is taken as the vertical axis to establish the scattering light intensity curve with the angle changing. The forward scattering region light intensity value is obtained by integrating the scattering light intensity curve when the angle changes from 0 to π / 2. The backward scattering region light intensity value is obtained by integrating the scattering light intensity curve when the angle changes from π / 2 to π. The leaf scattering deviation value is obtained by dividing the forward scattering region light intensity value by the backward scattering region light intensity value. The sum of the forward scattering region light intensity value and the backward scattering region light intensity value is obtained to obtain the total leaf scattering light intensity value. A planar light detection array is placed above the leaf litter pile of each road area. A laser light source with fixed light intensity is turned on, and the light intensity of each position on the plane is measured. The light intensity of each position is compared with the set reference light intensity threshold value. When the light intensity of a position is greater than or equal to the set reference light intensity threshold value, the position is classified as a scattering light distribution range. The boundary position of the scattering light distribution range is identified. The boundary is decomposed into several triangles, and the sum of the areas of each triangle is obtained to obtain the leaf scattering light distribution area value.

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

[0060] The reflectivity of the building surface and the ground reflectivity of each road area are obtained by a spectral reflectance instrument, the building surface reflectivity and the ground reflectivity are summed to obtain the building-ground reflectivity of each road area; measurement points are set along the road direction of each road area at a certain interval, the certain interval is 1 m, the elevations of the measurement points are obtained by a total station, the measurement points are sorted in the order of measurement, and the elevations of the measurement points are input into a three-dimensional coordinate system, adjacent measurement points are connected in sequence by line segments according to the measurement order, and the included angles formed by each measurement point and the previous adjacent sorted measurement point and the included angles formed by each measurement point and the next adjacent sorted measurement point are obtained to obtain the included angle value jz i of each measurement point, i represents the number of the measurement point, i = 1, 2, 3,..., n1, the included angles of the measurement points are averaged to obtain the average value of the included angles of the measurement points Jj, and the formula is set to obtain the terrain fluctuation rate Dq of each road area, λ is a correction factor, and the specific value is determined by personnel in the professional field; the building-ground reflectivity, the terrain fluctuation rate and the plant shadow value are normalized, a cuboid is constructed with the terrain fluctuation rate and the plant shadow value as the length and width of the base respectively, and the sum of the plant shadow value and the terrain fluctuation rate as the height of the cuboid, a sphere is constructed inside the cuboid with the center of the cuboid as the center of the sphere, the radius of the sphere is the building-ground reflectivity, the volume of the special-shaped body formed by the cuboid and the sphere is identified, and marked as the environmental bright scattering value of each road area;

[0061] The vehicle module receives pedestrian information and vehicle information, analyzes the walking state of pedestrians and the driving state of vehicles, and obtains the vehicle bright demand value of each road area, and the specific analysis is as follows:

[0062] The number of pedestrians and the number of vehicles in each road area are obtained, and the number of pedestrians and the number of vehicles in each road area are divided by the area of each road area to obtain the pedestrian density value and the vehicle density value, which are added to obtain the density value of each road area; the eye tracking device is used to obtain the duration that the eye movement of the pedestrian in each road area in the vertical and horizontal directions does not exceed the set pixel threshold, which is marked as the gaze duration of each pedestrian in each road area, and 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 100 milliseconds; 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; the number of gaze points in each road area is divided by the area of the road area to obtain the gaze point density, and the residence time of each gaze point in each road area is obtained, which is averaged to obtain the gaze point residence time; the number of turns per unit time and the walking route tortuosity of each pedestrian in each road area are obtained, added, and averaged to obtain the pedestrian movement trajectory complexity value of each road area; the walking route tortuosity is the ratio of the length of the walking path to the straight-line distance; the gaze point frequency, the gaze point density, the gaze point residence time, and the movement trajectory complexity value are weighted and calculated, and multiplied by the corresponding weight factor coefficient to obtain the pedestrian density adjustment coefficient; the turning speed and the turning angle of the vehicle in each road area are obtained, added, and averaged to obtain the vehicle angle value of each road area; the pedestrian density adjustment coefficient and the vehicle angle value are normalized and multiplied by the correction factor coefficient values h1 and h2 respectively, and summed to obtain the density adjustment factor coefficient; the density value of each road area is multiplied by the density adjustment factor coefficient to obtain the vehicle brightness demand value of each road area.

[0063] The efficiency module receives the street lamp information, analyzes the road brightness, obtains the brightness value of each road area, receives the environmental brightness value of each road area and the vehicle brightness demand value of each road area, and determines and analyzes the lighting efficiency of each road area, which is specifically analyzed as follows:

[0064] The power of each street lamp in each road area and the corresponding light emitting efficiency of each street lamp are obtained, the power of each street lamp and the light emitting efficiency are multiplied, and the sum is obtained to obtain the luminous flux Gt of each road area; the light emitting center of each street lamp is taken as the pole point, and the horizontal direction is taken as the pole axis to establish a light distribution curve diagram of the lamp, and each point on the curve represents the light intensity of the lamp in each angle direction; the range of the angle at which the light intensity in the horizontal direction decays to a certain degree in the curve diagram is obtained, and half of the angle range is marked as the horizontal light distribution angle pθ of each street lamp, and the certain degree refers to one third of the central light intensity; the height value lg of each street lamp is obtained, the lighting effective width yk is obtained according to the formula yk = 2 x lg x tan pθ, the distance value LJ between street lamps and the number value Lg of street lamps are obtained, and the formula

[0065] When yk < LJ, the lighting area Qm is obtained, and the lighting value Lb of each road area range is obtained according to the formula Lb = u × Gt / Qm, wherein u is a correction factor, and the specific value is 1.212;

[0066] The ambient light scattering value of each road area and the vehicle light demand value of each road area are marked as HLZ and CXL, respectively, and are normalized with the lighting value Lb of each road area range according to the set formula The comprehensive lighting efficiency coefficient ZXL of each road area is obtained, wherein xox1, xox2 and xox3 are respectively the set weight factors of the ambient light scattering value of each road area, the vehicle light demand value of each road area and the lighting value of each road area range, and the specific values are determined by personnel in the professional field;

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

[0068] When the comprehensive lighting efficiency coefficient of the road area is less than the lower limit value of the set lighting efficiency threshold, it is determined that the power of the road area is 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 lighting power adjustment value;

[0069] When the comprehensive lighting efficiency coefficient of the road area is greater than the upper limit value of the set lighting efficiency threshold, it is determined that the power of the road area is 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 decreases the street lamp lighting power according to the lighting power adjustment value;

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

[0071] A street lamp lighting intelligent control method based on artificial intelligence, comprising the following steps:

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

[0073] S2: The vegetation information and the road surface information are received by the environment module, and the scattering state of the vegetation, the reflection state of the road and the undulation state of the road are analyzed according to the vegetation information and the road surface information, and the ambient light scattering value of each road area is obtained.

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

[0075] S4: The efficiency module receives the street lamp information, analyzes the road brightness, obtains the lighting distribution value of each road region, receives the vehicle lighting demand value of each road region, and judges and analyzes the lighting efficiency of each road region;

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

[0077] The above is a description of the present application and should not be considered as a limitation. Although several exemplary embodiments of the present application are described, those skilled in the art will readily understand that many modifications can be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application. Therefore, all such modifications are intended to be included within the scope of the present application as defined in the claims. It should be understood that the above is a description of the present application and should not be considered as a limitation. It is intended that modifications of the disclosed embodiments and other embodiments are included within the scope of the appended claims. The present application is defined by the claims and their equivalents.

Claims

1. An artificial intelligence-based intelligent control system for street light illumination, characterized in that, The application relates to a road environment and efficiency analysis system and method. The data acquisition module is used for collecting vegetation information, road surface information, pedestrian information, vehicle information and street lamp information and sending the information to an environment module, a vehicle module and an efficiency module. The environment module analyzes the scattering state, the reflection state and the fluctuation state of the vegetation and the road surface information to obtain the environment brightness and scattering values of the road regions. The analysis of the environment brightness and scattering values of the road regions is as follows: A fixed laser light source is placed on one side of the leaf pile of each road region, and a light detector is placed on the other side; the light detector is rotated at an angle interval from the parallel angle of the incident light direction to obtain the received light intensity jq corresponding to each angle position, wherein the light intensity of the laser light source is fixed, 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 scattering light intensity sq corresponding to each angle position is obtained according to the formula sq= (jq-bq) / fq, a scattering light intensity-angle change curve is established with the scattering angle as the horizontal axis and the scattering light intensity as the vertical axis, the forward scattering region light intensity value is obtained by integrating the scattering light intensity curve at the angle from 0 to pi / 2, the backward scattering region light intensity value is obtained by integrating the scattering light intensity curve at the angle from pi / 2 to pi, and the leaf scattering deviation value is obtained by dividing the forward scattering region light intensity value by the backward scattering region light intensity value; a plane light detection array is placed above the leaf pile of each road region, a laser light source with fixed light intensity is turned on, the light intensity of each position of the plane is measured, and the light intensity of each position is compared and analyzed with the set reference light intensity threshold value; when the light intensity of the position is greater than or equal to the set reference light intensity threshold value, the position is classified into a scattering light distribution range, the boundary position of the scattering light distribution range is identified, the boundary is decomposed into a plurality of triangles, and the areas of the triangles are summed to obtain the leaf scattering light distribution area value. Step one: the spatial position and shape information of the tree crown branches of each road region are obtained through three-dimensional laser scanning, a plane parallel to the road cross section direction is selected as a projection plane, the projected image is binarized to obtain a black-and-white binary image, the tree branch part is white pixels, and the background is black pixel values; noise is removed through corrosion and collision to obtain a noise-removed binary image; each pixel in the binary image is traversed. Step two: count the number of white pixels in the eight neighborhood pixels of the white pixel, when the number of white pixels is greater than 1 and the white pixels belong to different branch contours, then the current pixel is determined as a cross point, from the cross point, the neighborhood pixels of the current pixel are continuously checked to determine the position of the next pixel along the selected branch contour to realize tracking, when a new cross point is encountered, the position relationship of branch one and branch two at the last cross point is recorded, and the position relationship of branch one and branch two at the new cross point is recorded, when the relative position relationship of the branches between the two cross points is upside down, it is determined that there is an up-down crossing situation, the path of the current pixel is tracked, if it returns to the starting cross point, it is determined that a winding is completed, and the winding number is increased by 1; Step three: repeat step two for all starting cross points and tracking paths in the image, and the total winding number of each road area branch is obtained after all cross points are traversed, and the total cross point number of each road area branch is counted to obtain the total cross point number of each road area branch; Step four: obtaining the above-identified intersection points, identifying the intersection line segments of each intersection point, obtaining the associated line segment list [L1, L2, L3,... LN] of each intersection point, N is the maximum value of the associated line segment number, combining the line segments of the associated line segment list two by two, identifying the two end point pixel coordinates of one of the line segments L1 and L2, respectively marked as (x1, y1) and (x2, y2), the two end point pixel coordinates of L2, respectively marked as (x3, y3) and (x4, y4), according to the formula and the vector dot product of line segments L1 and L2 , the modulus of vector L1 and the modulus of vector L2 , according to the formula , the angle θ12 between line segments L1 and L2 is obtained, and the above operation is repeated to obtain the angle formed by each intersection point corresponding to each intersecting line segment, and the maximum and minimum values of the angle are counted, and the maximum value of the angle is subtracted from the minimum value to obtain the angle distribution value of each road area branch. Step four: normalize the total winding number of each road area branch, the total cross point number of each road area branch, and the angle distribution value of each road area branch, respectively marked as Cr, Jj and Jd, and obtain the crown branch state value Gz of each road area according to the formula Gz=υ / (pop1×Cr+pop2×Jj+pop3×Jd), wherein pop1, pop2 and pop3 are weight factor coefficients, and υ is a correction factor coefficient; The initial light intensity Cq is emitted in the vegetation of each road area through indirect optical instrument, the emitted light is transmitted through the leaves of the vegetation, the light intensity transmitted through the leaves of the vegetation is received and marked as Tq, the vegetation categories of each road area are identified, which are broad-leaved forest, shrub forest, coniferous forest and herbaceous vegetation respectively, the extinction coefficient values of the vegetation categories are a1, a2, a3 and a4 respectively, the extinction coefficient value of the vegetation is obtained and marked as Xx, and the vegetation leaf area index value Yz of each road area is obtained according to the formula . The leaf scattering deviation value, the leaf scattering total light intensity value and the leaf scattering light distribution area value are respectively marked as Sp, Sq and Sf, and are normalized with the vegetation leaf area index value Yz and the crown branch state value Gz, and the plant shadow scattering value Zy of each road area is obtained according to the set formula , wherein te1, te2, te3, te4 and te5 are set reference weight factor coefficients, and e is a natural constant. The reflectivity of the building surface and the ground reflectivity of each road area are obtained by a spectral reflectance instrument, the building surface reflectivity and the ground reflectivity are summed to obtain the building-ground reflectivity of each road area; the measuring points are set along the road direction of each road area according to the interval, the elevation of each measuring point is obtained by a total station, the measuring points are sorted according to the measurement sequence, the elevation of each measuring point is input into a three-dimensional coordinate system, the adjacent measuring points are connected in sequence according to the measurement sequence by a line segment, the included angle formed by each measuring point and the previous adjacent sorting measuring point and the included angle formed by each measuring point and the next adjacent sorting measuring point are obtained to obtain the included angle value jz i of each measuring point, i represents the number of the measuring point, i=1, 2, 3,..., n1, the average value of the included angles of each measuring point is calculated to obtain the average value Jj of the included angle of the measuring point, the formula is set according to the formula , the terrain fluctuation rate Dq of each road area is obtained, λ is a correction factor coefficient; the building-ground reflectivity, the terrain fluctuation rate and the plant shadow value are normalized, the cuboid is constructed by taking the terrain fluctuation rate and the plant shadow value as the length and width of the cuboid base respectively and taking the sum of the plant shadow value and the terrain fluctuation rate as the height of the cuboid, the sphere is constructed inside the cuboid by taking the center of the cuboid as the center of the sphere, specifically taking the building-ground reflectivity as the radius of the sphere, the special-shaped body volume formed by the cuboid and the sphere is identified and marked as the environmental bright scattering value of each road area; The car module analyzes the walking state of pedestrians and the driving state of vehicles based on pedestrian information and vehicle information, and obtains the car light demand value of each road area; The efficiency module analyzes the road brightness based on the street lamp information, obtains the light distribution value of each road area, receives the environmental light distribution value of each road area and the car light demand value of each road area, and determines and analyzes 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 the set lighting efficiency threshold, and obtain the automatic adjustment of the street lamp lighting power.

2. The intelligent control system for street light illumination based on artificial intelligence as claimed in claim 1 wherein, The car light demand value analysis step of each road area is as follows: The number of pedestrians and the number of vehicles in each road area are obtained, and the number of pedestrians and the number of vehicles are divided by the area of each road area respectively to obtain the pedestrian density value and the vehicle density value, which are added to obtain the density value of each road area; the eye tracking device is used to obtain the duration that the eye displacement of pedestrians in each road area in the vertical and horizontal directions does not exceed the set pixel threshold, which is marked as the gaze duration of each pedestrian in each road area; when the gaze duration of each pedestrian is greater than or equal to the duration, the pedestrian is determined as a gaze point; 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; the number of gaze points in each road area is divided by the area of the road area to obtain the gaze point density; the residence time of each gaze point in each road area is obtained, and the average value is processed to obtain the gaze point residence duration; the number of turns per unit time and the walking route tortuosity of each pedestrian in each road area are obtained, added, and the average value is calculated 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, the gaze point density, the gaze point residence duration, and the movement trajectory complexity value are weighted and calculated, and multiplied by the corresponding weight factor coefficient to obtain the pedestrian density heterodyne coefficient; the turning speed and the turning angle of the vehicle in each road area are obtained, added, and the average value is calculated to obtain the vehicle angle value of each road area; the pedestrian density heterodyne coefficient and the vehicle angle value are normalized, and multiplied by the correction factor coefficient values h1 and h2 respectively to obtain the density value adjustment factor coefficient; the density value of each road area is multiplied by the density value adjustment factor coefficient to obtain the vehicle lighting density value of each road area.

3. The intelligent control system for street light illumination based on artificial intelligence as claimed in claim 1 wherein, The lighting efficiency analysis step of each road area is as follows: The light flux Gt of each road area is obtained by multiplying the power of each street lamp in each road area by the corresponding light emitting efficiency of the street lamp and summing the results. A light distribution curve graph is established with the light emitting center of each street lamp as the pole point and the horizontal direction as the pole axis. Each point on the curve represents the light intensity of the lamp in each angular direction. The range of the angle at which the light intensity in the horizontal direction decays to a certain degree in the graph is obtained. Half of the angle range is marked as the horizontal light distribution angle pθ of each street lamp. The certain degree refers to one-third of the central light intensity. The height value lg of each street lamp is obtained. The effective illumination width yk is obtained according to the formula yk=2×lg×tan pθ. The street lamp spacing value LJ and the number of street lamps Lg are obtained. The illumination area Qm is obtained according to the formula . The brightness value Lb of each road area range is obtained according to the formula Lb=u×Gt / Qm. u is a correction factor coefficient. The environment light spread value of each road area, the car light demand value of each road area, and the light distribution value of each road area range are marked as HLZ, CXL, and Lb respectively, and normalized processing is performed according to the set formula , to obtain the comprehensive lighting performance coefficient ZXL of each road area, wherein xox1, xox2, and xox3 are set weight factors.

4. The intelligent control system for street light illumination based on artificial intelligence as claimed in claim 1 wherein, The automatic adjustment processing analysis step of the street lamp lighting power is as follows: When the comprehensive lighting efficiency coefficient of the road area is less than the lower limit value of the set lighting efficiency threshold, it is determined that the power of the road area is abnormal; the difference between the comprehensive lighting efficiency coefficient of the road area and the lighting efficiency threshold is calculated to obtain the efficiency bias value; the efficiency bias value is multiplied by the lighting power conversion coefficient to obtain the lighting power adjustment value; the street lamp lighting control system automatically increases the street lamp lighting power according to the lighting power adjustment value; When the comprehensive lighting efficiency coefficient of the road area is greater than the upper limit value of the set lighting efficiency threshold, it is determined that the power of the road area is abnormal; the difference between the comprehensive lighting efficiency coefficient of the road area and the lighting efficiency threshold is calculated to obtain the efficiency bias value; the efficiency bias value is multiplied by the lighting power conversion coefficient to obtain the lighting power adjustment value; the street lamp lighting control system automatically decreases the street lamp lighting power according to the lighting power adjustment value; When the comprehensive lighting efficiency coefficient of the road area is greater than or equal to the lower limit value of the set lighting efficiency threshold and less than or equal to the upper limit value of the set lighting efficiency threshold, it is determined that the lighting of the road area is normal, and no corresponding operation is performed.

5. An artificial intelligence-based intelligent control method for street light illumination, characterized by A street lamp lighting intelligent control system based on artificial intelligence is applied to any one of claims 1-4, comprising the following steps: S1: The data acquisition module collects vegetation information, road surface information, pedestrian information, vehicle information and street lamp information, and sends them to the environment module, the vehicle module and the efficiency module; S2: The environment module receives the vegetation information and the road surface information, and analyzes the scattering state of the vegetation, the reflection state of the road and the undulation state of the road according to the information, to obtain the environment brightness scattering value of each road area; S3: The vehicle module receives the pedestrian information and the vehicle information, and analyzes the walking state of the pedestrian and the driving state of the vehicle, to obtain the vehicle brightness demand value of each road area; S4: The efficiency module receives the street lamp information, analyzes the road brightness, obtains the brightness distribution value of each road area, receives the environment brightness scattering value of each road area and the vehicle brightness demand value of each road area, and judges 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 the automatic adjustment processing of the street lamp lighting power.

Images