Environment sensing illumination adjusting system applied to intelligent lamp post

Abstract

The invention, which relates to the field of illumination adjustment, discloses an environment sensing illumination adjustment system applied to an intelligent lamp post, comprising a data acquisition module, an air data analysis module, an image data analysis module, a model training module, an instruction generation module and an adjustment module. The data acquisition module is used for acquiring related data; the air data analysis module obtains an air influence value by analyzing the air quality index and the visibility; the image data analysis module analyzes the image data to obtain a personnel influence value and a crowd illumination value; the model training module generates a use illumination adjustment model according to the historical illumination data set; the instruction generation module generates an illumination adjustment instruction according to a comparison result of the target illumination parameter and the actual illumination parameter; the adjusting module adjusts the intelligent lamp pole according to the illumination adjusting instruction; according to the invention, through comprehensive analysis of various factors, the adjustment accuracy of the intelligent lamp post can be improved.

Description

Technical Field

[0001] The present invention relates to the field of lighting adjustment, and specifically to an environmental perception lighting adjustment system applied to smart lamp posts. Background Art

[0002] At present, with the rapid development of urbanization, the urban lighting system, as a key component of urban infrastructure, has become increasingly prominent. The traditional street lamp lighting system generally adopts a fixed brightness lighting method, which is difficult to dynamically adjust according to the actual environmental conditions, resulting in a large amount of energy waste and light pollution problems.

[0003] With the rapid development of technologies such as the Internet of Things, sensors, and communication, smart lamp posts have emerged as an important carrier for urban intelligent construction. By integrating multiple functional modules such as lighting, environmental monitoring, video surveillance, and information publishing, smart lamp posts have realized the collection and interaction of multi-faceted data in the city, providing strong support for urban refined management.

[0004] However, most of the existing smart lamp posts are adjusted based on a single factor of light intensity, without considering air factors (air quality index, visibility) and the personnel distribution in the target area, resulting in poor accuracy of lighting adjustment.

[0005] Improving the accuracy of smart lamp post adjustment is a problem that needs to be solved. For this reason, an environmental perception lighting adjustment system applied to smart lamp posts is provided. Summary of the Invention

[0006] The purpose of the present invention is to provide an environmental perception lighting adjustment system applied to smart lamp posts.

[0007] The purpose of the present invention can be achieved through the following technical solutions: An environmental perception lighting adjustment system applied to smart lamp posts includes:

[0008] Data acquisition module: Preset acquisition nodes, collect light data, air data, and image data in the target area at the acquisition nodes, and at the same time obtain the historical lighting data set of the smart lamp post;

[0009] Air data analysis module: Analyze the air data to obtain an air influence value;

[0010] Image data analysis module: Analyze the image data to obtain a personnel influence value and a crowd lighting value;

[0011] Model training module: Train a preset lighting adjustment model according to the historical lighting data set to obtain a used lighting adjustment model;

[0012] Instruction generation module: Input the lighting set into the lighting adjustment model to obtain target lighting parameters, compare the target lighting parameters with the actual lighting parameters, and generate a lighting adjustment instruction based on the comparison result;

[0013] Adjustment module: Parse the lighting adjustment instruction and adjust the smart light pole according to the parsed result.

[0014] Preferably, the air data includes the air quality index and visibility;

[0015] The image data is pictures of the target area taken from different angles by a camera;

[0016] The light data is the light intensity and light direction of sunlight;

[0017] The historical lighting data set is the historical air influence value, historical personnel influence value, historical crowd lighting value, historical light data, and the corresponding target lighting parameters;

[0018] The target lighting parameters include the target light intensity, target light direction, and target color temperature.

[0019] Preferably, the process of analyzing the air data to obtain the air influence value is as follows:

[0020] Fuse the air quality index and visibility to obtain the air-visibility value of each collection node;

[0021] Obtain the air-visibility values of the previous n collection nodes of the current collection node as the air-visibility set of the current collection node;

[0022] Take the mean value of the elements in the air-visibility set as the air mean value of the current collection node, preset the air-visibility step size, and obtain each air-visibility interval according to the air-visibility step size;

[0023] Match the elements in the air-visibility set with each air-visibility interval to obtain the frequency value of each air-visibility interval;

[0024] Obtain the air influence index according to the frequency values of each air-visibility interval.

[0025] Preferably, the process of analyzing the image data to obtain the personnel influence value and the crowd lighting value is as follows:

[0026] Identify the personnel in the pictures through target detection technology, and combine different pictures to form a two-dimensional personnel distribution map of the target area;

[0027] Through the two-dimensional personnel distribution map, obtain the distance vector of each person in the target area, and cluster the personnel in the target area based on the K-means clustering algorithm and the distance vector to obtain the number of clusters, the cluster domain, and the cluster points;

[0028] Obtain the distances between each group of points and the smart light poles as the group light distances, obtain the group rate values according to the number of people in the group where the group of points is located, and obtain the personnel influence values according to the group light distances and the group rate values.

[0029] Preferably, the process of obtaining the crowd illumination value is as follows:

[0030] Sum up the areas of the group domains corresponding to each group as the group area, and divide the group area by the total area of the target area to obtain the group area ratio;

[0031] Obtain the personnel density of each group, obtain the brightness indication values corresponding to each group according to the group light distances and the personnel density, and take the average value of the brightness indication values corresponding to each group as the brightness average value;

[0032] Fuse the group area ratio and the brightness average value to obtain the crowd illumination value.

[0033] Preferably, the process of training the preset lighting adjustment model according to the historical lighting data set and obtaining the lighting adjustment model for use is as follows:

[0034] Divide the historical lighting data set into a training group and a validation group;

[0035] Initialize the preset lighting adjustment model using the Xavier method, input the training group into the preset lighting adjustment model, update the parameters of the model using the loss function and the backpropagation algorithm to obtain the validated lighting adjustment model;

[0036] Validate the validated lighting adjustment model using the validation group to obtain the lighting adjustment model for use.

[0037] Preferably, the process of comparing the target lighting parameters with the actual lighting parameters and generating a lighting adjustment instruction based on the comparison result is as follows:

[0038] The lighting set includes the air influence value, the personnel influence value, the crowd illumination value, and the lighting data;

[0039] The actual lighting parameters include: the actual light intensity, the actual light direction, and the actual color temperature;

[0040] If the absolute value of the difference between the target light intensity and the actual light intensity is greater than the light intensity threshold, generate a light intensity adjustment instruction; otherwise, do not generate any instruction;

[0041] If the absolute value of the difference between the target light direction and the actual light direction is greater than the light direction threshold, generate a light direction adjustment instruction; otherwise, do not generate any instruction;

[0042] If the absolute value of the difference between the target color temperature and the actual color temperature is greater than the color temperature threshold, a color temperature adjustment instruction is generated; otherwise, no instruction is generated.

[0043] Combine the light intensity adjustment instruction, the light direction adjustment instruction, and the color temperature adjustment instruction to generate an illumination adjustment instruction.

[0044] Preferably, the process of analyzing the illumination adjustment instruction and adjusting the smart light pole according to the analysis result is as follows:

[0045] If the illumination adjustment instruction includes a light intensity adjustment instruction, adjust the light intensity of the smart light pole to the target light intensity.

[0046] If the illumination adjustment instruction includes a light direction adjustment instruction, adjust the light direction of the smart light pole to the target light direction.

[0047] If the illumination adjustment instruction includes a color temperature adjustment instruction, adjust the color temperature of the smart light pole to the target color temperature.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] The present invention analyzes air data to obtain an air influence value, analyzes image data to obtain a personnel influence value and a crowd illumination value, trains a preset illumination adjustment model through a historical illumination data set to obtain a used illumination adjustment model, takes the air influence value, the personnel influence value, and the crowd illumination value as an illumination set, inputs the used illumination model to obtain target illumination parameters, and compares the target illumination parameters with the actual illumination parameters to generate corresponding illumination adjustment instructions, realizing the adjustment of the smart light pole; the present invention comprehensively considers the influence of illumination factors, air factors, and personnel factors in the area where the smart light pole is located on the light adjustment, thereby improving the accuracy of the smart light pole adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] As Figure 1 shown, an environmental perception illumination adjustment system applied to a smart light pole includes:

[0053] Data acquisition module: Preset acquisition nodes, collect illumination data, air data, and image data of the target area at the acquisition nodes, and simultaneously obtain the historical lighting data set of the smart lamp post;

[0054] The air data includes: air quality index and visibility;

[0055] The image data is pictures of the target area taken from different angles by a camera;

[0056] The illumination data is the illumination intensity and illumination direction of sunlight;

[0057] The historical lighting data set is the historical air influence value, historical personnel influence value, historical crowd illumination value, historical illumination data, and corresponding target lighting parameters;

[0058] Specifically, by collecting and processing the historical air data and historical image data of the smart lamp post, the corresponding historical air influence value, historical personnel influence value, and historical crowd illumination value are obtained;

[0059] Build a 3D model of the area where the smart lamp post is located in the lighting simulation software, input the historical air data, historical image data, and historical illumination data into the 3D model to obtain a simulation model, and continuously adjust the lighting parameters of the smart lamp post in the simulation model to obtain the target lighting parameters corresponding to the historical air data, historical illumination data, and historical image data;

[0060] Associate the target lighting parameters with the historical air influence value, historical personnel influence value, historical crowd illumination value, and historical illumination data to obtain the historical lighting data set;

[0061] The target lighting parameters include target light intensity, target light direction, and target color temperature.

[0062] Air data analysis module: Analyze the air data to obtain the air influence value;

[0063] Fuse and process the air quality index and visibility to obtain the air-visibility value of each acquisition node;

[0064] Specifically, substitute the air quality index KQZ and visibility KJD into the formula: Thus, the air-visibility value KJZ corresponding to each acquisition point is obtained, where q1 and q2 are the weight influence factors corresponding to the air quality index KQZ and visibility KJD respectively;

[0065] Specifically, the larger the air quality index, the more pollutants there are in the air. The pollutants in the air will scatter and absorb light, causing the light emitted by the smart light pole to be weakened when it reaches the target area. Therefore, the larger the air quality index, the stronger the light that the smart light pole needs to emit;

[0066] Obtain the air quality values of the previous n collection nodes of the current collection node as the air quality set of the current collection node;

[0067] Specifically, if there are not enough collection nodes before the current collection node, then use the air quality values of all the collection nodes before the current collection node as the air quality set corresponding to the current collection node;

[0068] Take the mean value of the elements in the air quality set as the air quality mean value of the current collection node, preset the air quality step size, and obtain each air quality interval according to the air quality step size;

[0069] For example, if the air quality mean value is 60 and the air quality step size is 2, then the air quality intervals are [60, 62), [62, 64), [64, 66), [58, 60), [56, 58), [54, 56), etc.;

[0070] Match the elements in the air quality set with each air quality interval to obtain the frequency value of each air quality interval;

[0071] Specifically, matching means comparing the elements in the air quality set with each air quality interval one by one. If a certain element in the air quality set belongs to a certain air quality interval, it means that the match is successful; count the number of successful matches in the air quality interval, and divide the number of successful matches in the air quality interval by the number of elements in the air quality set. The result obtained is used as the frequency value of this air quality interval;

[0072] Specifically, analyzing the previous n collection nodes of the current collection node is mainly to smooth the data and avoid adjusting the smart light pole due to sudden changes in the data, thereby extending the life of the smart light pole;

[0073] Obtain the air influence index according to the frequency values of each air quality interval;

[0074] Specifically, preset several intervals of frequency values, different frequency value intervals correspond to different weight influence factors, the higher the frequency value, the larger the corresponding weight influence factor. Match the frequency value of the air quality interval with the frequency value interval to obtain the weight influence factor corresponding to the air quality interval. Multiply the median value of each air quality interval by the corresponding weight influence factor and then sum up the results, which is used as the air influence index.

[0075] Image data analysis module: Analyze the image data to obtain the personnel influence value and the crowd illumination value;

[0076] Identify the people in the picture through object detection technology, combine different pictures to form a two-dimensional distribution map of people in the target area;

[0077] Specifically, extract SIFT feature points from each picture, use a feature point matching algorithm (for example, nearest neighbor matching based on Euclidean distance) to match the feature points in different pictures, and according to the successfully matched feature points, use an image stitching algorithm to calculate the transformation relationship between the pictures, and stitch all the images together to form a panoramic image covering the target area;

[0078] In the panoramic image of the target area, randomly select a point as the origin, establish a two-dimensional coordinate system, and determine the position of the corresponding person in the two-dimensional coordinate system according to the position of the person in the panoramic image, so as to obtain a two-dimensional distribution map of people;

[0079] Through the two-dimensional distribution map of people, obtain the distance vector of each person in the target area, and cluster the people in the target area based on the K-means clustering algorithm and the distance vector to obtain the number of clusters, the cluster domain, and the cluster center point;

[0080] Specifically, number each person, use i to represent the number, calculate the spatial distance between each person and all other people, and record the spatial distance between oneself and oneself as 0. Combine the spatial distances of a certain person and represent them in the form of a vector, so as to obtain the distance vector of this person;

[0081] Specifically, when combining the spatial distances of a certain person, it is necessary to follow a certain order. In this embodiment, the combination is carried out in the order of the person numbers; for example, the distance vector corresponding to a certain person is (2, 3, 4, 0, 5, 6), indicating that the spatial distance between this person and the person numbered 1 is 2, and the spatial distance between this person and the person numbered 2 is 3...;

[0082] Specifically, use the distance vectors of all the people in the target area as the input, and use the K-means clustering algorithm to cluster the distance vectors, so as to realize the clustering of the people in the target area; identify the boundary points of each cluster, connect the boundary points to form a closed area, so as to obtain the cluster domain corresponding to each cluster; the cluster center point refers to the center point of the cluster domain;

[0083] Specifically, the K-means clustering algorithm is an unsupervised learning algorithm based on distance measurement, mainly used to divide the samples in the data set into different clusters, so that the samples within the same cluster have high similarity, and the samples between different clusters have high differences;

[0084] Obtain the distance between each cluster center point and the intelligent street lamp as the cluster-lamp distance, obtain the cluster rate value according to the number of people in the cluster where the cluster center point is located, and obtain the personnel influence value according to the cluster-lamp distance and the cluster rate value;

[0085] Specifically, the group lamp distance refers to the distance between the group points and the lamp post on the two-dimensional personnel distribution map; the group rate value corresponding to the group points = the number of personnel in the group where the group points are located / the total number of personnel in the target area;

[0086] Multiply the group rate value corresponding to each group point by the group lamp distance and then sum them up, and use the obtained result as the personnel influence value;

[0087] Specifically, the personnel influence value is used to adjust the lighting direction of the smart lamp post. Different values of the group lamp distance indicate that the corresponding group requires different lighting directions; and the larger the group rate value, the larger the number of people in this group compared to other groups. When adjusting the lighting direction, it should be more biased towards this group;

[0088] Sum up the areas of the group domains corresponding to each group as the group area, and divide the group area by the total area of the target area to obtain the group area ratio;

[0089] Specifically, the larger the group area ratio, the more people there are in the target area, and stronger lighting is required to meet the needs;

[0090] Obtain the personnel density of each group, and based on the group lamp distance and the personnel density, obtain the brightness indication value LDZ corresponding to each group. Take the average value of the brightness indication values LDZ corresponding to each group as the average brightness value;

[0091] Specifically, normalize the group lamp distance QDJ and the personnel density RYM and then substitute them into the formula: LDZ = sinh(QDJ * e w1 + RYM * e w2 ) to obtain the brightness indication value LDZ;

[0092] Specifically, the greater the personnel density, the closer the distance between people, and the more serious the occlusion and reflection of the light, and stronger light is required to meet the needs;

[0093] Fuse the group area ratio and the average brightness value to obtain the crowd illumination value;

[0094] Specifically, preset the weight influence factors corresponding to the group area ratio and the average brightness value, and perform weighted processing on the group area ratio and the average brightness value based on the preset weight influence factors to obtain the crowd illumination value.

[0095] Model training module: Train the preset lighting adjustment model according to the historical lighting data set to obtain the used lighting adjustment model;

[0096] Divide the historical lighting data set into a training group and a validation group;

[0097] Initialize the preset lighting adjustment model using the Xavier method, input the training set into the preset lighting adjustment model, and update the parameters of the model using the loss function and backpropagation algorithm to obtain the verified lighting adjustment model;

[0098] Specifically, the expression of the loss function is:

[0099]

[0100] where SS represents the loss value, y represents the true value, represents the predicted value, and α, β, and δ all represent preset hyperparameters;

[0101] The backpropagation algorithm provides an efficient method to calculate the gradient of each weight in the lighting adjustment model, making large-scale model training possible; by continuously backpropagating the error and updating the weights, the lighting adjustment model can gradually adjust its own parameters to minimize the error, thereby achieving regression on the input data;

[0102] Verify the verified lighting adjustment model using the verification set to obtain the lighting adjustment model for use;

[0103] Specifically, input the verification set into the verified lighting adjustment model, calculate the performance indicators of the verification set. The performance indicators include accuracy, recall rate, F1 value, and mean square error, and preset the thresholds for each performance indicator. Compare the performance indicators with the corresponding thresholds. When the comparison is successful, obtain the lighting adjustment model for use; if the comparison fails, retrain the preset lighting adjustment model using the training set;

[0104] Specifically, a successful comparison means that the accuracy, recall rate, F1 value, and mean square error are all greater than the corresponding thresholds, and the mean square error is less than the preset threshold.

[0105] Instruction generation module: Input the lighting set into the lighting adjustment model for use to obtain the target lighting parameters, compare the target lighting parameters with the actual lighting parameters, and generate a lighting adjustment instruction based on the comparison result;

[0106] The lighting set is the air influence value, personnel influence value, crowd illumination value, and illumination data;

[0107] The actual lighting parameters include: actual light intensity, actual light direction, and actual color temperature;

[0108] Specifically, the actual lighting parameters are the actual parameters of the smart light pole during operation;

[0109] Preset the light intensity threshold, light direction threshold, and color temperature threshold;

[0110] If the absolute value of the difference between the target light intensity and the actual light intensity is greater than the light intensity threshold, a light intensity adjustment instruction is generated; otherwise, no instruction is generated.

[0111] If the absolute value of the difference between the target light direction and the actual light direction is greater than the light direction threshold, a light direction adjustment instruction is generated; otherwise, no instruction is generated.

[0112] If the absolute value of the difference between the target color temperature and the actual color temperature is greater than the color temperature threshold, a color temperature adjustment instruction is generated; otherwise, no instruction is generated.

[0113] The light intensity adjustment instruction, the light direction adjustment instruction, and the color temperature adjustment instruction are combined to generate an illumination adjustment instruction.

[0114] Adjustment module: Parse the illumination adjustment instruction and adjust the smart light pole according to the parsed result.

[0115] If the illumination adjustment instruction includes a light intensity adjustment instruction, adjust the light intensity of the smart light pole to the target light intensity.

[0116] If the illumination adjustment instruction includes a light direction adjustment instruction, adjust the light direction of the smart light pole to the target light direction.

[0117] If the illumination adjustment instruction includes a color temperature adjustment instruction, adjust the color temperature of the smart light pole to the target color temperature.

[0118] The above are only the preferred embodiments of the present invention and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the above-disclosed technical content to obtain equivalent embodiments with equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any modification or equivalent replacement made to the above embodiments based on the technical essence of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. An environmental perception lighting adjustment system applied to a smart light pole, characterized in that Including: Data acquisition module: preset acquisition nodes, collect illumination data, air data and image data of the target area on the acquisition nodes, and at the same time obtain the historical lighting data set of the smart light pole; Air data analysis module: analyze the air data to obtain the air influence value; Image data analysis module: analyze the image data to obtain the personnel influence value and the crowd illumination value; Model training module: train the preset lighting adjustment model according to the historical lighting data set to obtain the used lighting adjustment model; Instruction generation module: input the lighting set into the used lighting adjustment model to obtain the target lighting parameters, compare the target lighting parameters with the actual lighting parameters, and generate a lighting adjustment instruction based on the comparison result; Adjustment module: parse the lighting adjustment instruction and adjust the smart light pole according to the parsed result.

2. The environmental perception lighting adjustment system applied to the smart street lamp according to claim 1, characterized in that, The air data includes the air quality index and visibility; The image data is pictures of the target area taken from different angles by a camera; The illumination data is the illumination intensity and illumination direction of sunlight; The historical lighting data set is the historical air influence value, historical personnel influence value, historical crowd illumination value, historical illumination data and the corresponding target lighting parameters; The target lighting parameters include the target light intensity, target light direction and target color temperature.

3. The environmental perception lighting adjustment system applied to the intelligent street lamp according to claim 2, characterized in that The process of analyzing the air data to obtain the air influence value is as follows: Perform fusion processing on the air quality index and visibility to obtain the air-visibility value of each acquisition node; Obtain the air-visibility values of the previous n acquisition nodes of the current acquisition node as the air-visibility set of the current acquisition node; Take the mean value of the elements in the air-visibility set as the air mean value of the current acquisition node, preset the air-visibility step length, and obtain each air-visibility interval according to the air-visibility step length; Match the elements in the air-visibility set with each air-visibility interval to obtain the frequency value of each air-visibility interval; Obtain the air influence index according to the frequency value of each air-visibility interval.

4. The environmental perception lighting adjustment system applied to a smart light pole according to claim 3, wherein The process of analyzing the image data to obtain the personnel influence value and the crowd illumination value is as follows: Identify the personnel in the picture through the target detection technology, and combine different pictures to form a two-dimensional personnel distribution map of the target area; Through the two-dimensional personnel distribution map, obtain the distance vector of each person in the target area, and cluster the personnel in the target area based on the K-means clustering algorithm and the distance vector to obtain the number of clusters, cluster domains and cluster points; Obtain the distance between each cluster point and the smart light pole as the cluster-light pole distance, obtain the cluster rate value according to the number of personnel in the cluster where the cluster point is located, and obtain the personnel influence value according to the cluster-light pole distance and the cluster rate value.

5. The environmental perception lighting adjustment system applied to a smart light pole according to claim 4, wherein The process of obtaining the crowd illumination value is as follows: Add up the areas of the cluster domains corresponding to each cluster as the cluster area, and divide the cluster area by the total area of the target area to obtain the cluster area ratio; Obtain the personnel density of each cluster, obtain the brightness indication value corresponding to each cluster according to the cluster-light pole distance and the personnel density, and take the mean value of the brightness indication values corresponding to each cluster as the brightness mean value; Perform fusion processing on the cluster area ratio and the brightness mean value to obtain the crowd illumination value.

6. The environmental perception lighting adjustment system applied to the intelligent street lamp according to claim 5, characterized in that The process of training the preset lighting adjustment model according to the historical lighting data set to obtain the used lighting adjustment model is as follows: Divide the historical lighting data set into a training group and a validation group; Initialize the preset lighting adjustment model using the Xavier method, input the training set into the preset lighting adjustment model, and update the parameters of the model using the loss function and backpropagation algorithm to obtain the verified lighting adjustment model; Verify the verified lighting adjustment model using the verification set to obtain the lighting adjustment model for use.

7. The environmental perception lighting adjustment system applied to a smart lamp post according to claim 6, wherein The process of comparing the target lighting parameters with the actual lighting parameters and generating a lighting adjustment instruction based on the comparison results is as follows: The lighting set includes the air influence value, the personnel influence value, the crowd lighting value, and the lighting data; The actual lighting parameters include: the actual light intensity, the actual light direction, and the actual color temperature; If the absolute value of the difference between the target light intensity and the actual light intensity is greater than the light intensity threshold, generate a light intensity adjustment instruction; otherwise, do not generate any instruction; If the absolute value of the difference between the target light direction and the actual light direction is greater than the light direction threshold, generate a light direction adjustment instruction; otherwise, do not generate any instruction; If the absolute value of the difference between the target color temperature and the actual color temperature is greater than the color temperature threshold, generate a color temperature adjustment instruction; otherwise, do not generate any instruction; Combine the light intensity adjustment instruction, the light direction adjustment instruction, and the color temperature adjustment instruction to generate a lighting adjustment instruction.

8. The environmental perception lighting adjustment system applied to the intelligent street lamp according to claim 7, wherein The process of parsing the lighting adjustment instruction and adjusting the smart light pole according to the parsing result is as follows: If the lighting adjustment instruction includes a light intensity adjustment instruction, adjust the light intensity of the smart light pole to the target light intensity; If the lighting adjustment instruction includes a light direction adjustment instruction, adjust the light direction of the smart light pole to the target light direction; If the lighting adjustment instruction includes a color temperature adjustment instruction, adjust the color temperature of the smart light pole to the target color temperature.

Images