Smart city smart street light control method, device, smart terminal and storage medium
By collecting and analyzing real-time weather, lighting, sound and image data, the optimal lighting and warning solutions are generated, and the problems of energy waste and inaccurate light data in traditional street light control methods are solved, intelligent lighting and traffic safety reminders are realized, and the Street light power consumption and accident risk.
Patent Information
- Application Number
- CN202411171034.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-26
AI Technical Summary
Traditional street light control methods cannot flexibly adjust the lighting brightness according to actual needs, resulting in serious energy waste. Although existing smart street light systems can adjust the brightness according to environmental data, it is difficult to avoid light sensors being disturbed by vehicle lights and building lights, resulting in inaccurate light intensity data. .
The acquisition unit is used to obtain real-time weather data, lighting data, sound data and image data, and the central analysis unit generates the optimal lighting scheme and warning scheme, and generates control instructions based on these schemes to realize remote switching and brightness adjustment, and obtains lighting through image analysis. Distribute data, establish a regression equation for lighting intensity adjustment to avoid interference.
It improves the intelligence of street light lighting, reduces power consumption, realizes energy conservation and emission reduction, and reduces the probability of traffic accidents by reminding lights in advance.
Smart Images

Figure CN118695445B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of street lamp control, and specifically relates to a smart city smart street lamp control method, device, smart terminal and storage medium. Background Art
[0002] With the acceleration of urbanization, street lamps, as an important part of urban infrastructure, have become increasingly problematic with high energy consumption and extensive management. Traditional street lamps have a single control method and cannot flexibly adjust the lighting brightness according to actual needs, resulting in serious energy waste. Therefore, smart street lamps have emerged. Smart street lamps are equipped with light-sensing components that can automatically adjust the brightness of street lamps according to the brightness of the surrounding environment, thereby achieving the goal of energy saving and consumption reduction.
[0003] For example, a Chinese patent document with publication number CN116600446A discloses an intelligent street light system based on the Internet of Things technology. The system collects data on vehicle flow, pedestrian flow, and light factors, and simultaneously monitors and counts street light parameters in real time, thereby increasing the controllability of street light management. By collecting data on the surrounding environment of street lights, the system adjusts the lighting brightness according to different environmental data analysis to improve energy efficiency. At the same time, by real-time monitoring of the use status of street lights, it quickly warns of abnormal street lights, thereby improving the maintenance efficiency of street lights. For example, a Chinese patent document with publication number CN115297595A discloses an intelligent control method and system for smart city street lights based on the Internet of Things. The method receives road information through a management platform, and the road information includes ambient light intensity and road images. Based on the road images, the road environment information is determined; based on the ambient light intensity and road environment information, the illumination intensity of the street lights on the road is determined.
[0004] Based on the above-mentioned prior art, it can be known that smart street lights are generally also provided with image acquisition devices. Traffic condition information can be obtained by acquiring images based on the image acquisition device. If the street lights can transmit the traffic condition information of their own monitoring areas to drivers in the distance, the intelligence level of the street lights can be further improved. Summary of the invention
[0005] To solve the above problems, the present invention provides a smart city smart street lamp control method, device, smart terminal and storage medium to solve the problems in the prior art.
[0006] In order to achieve the above-mentioned invention object, the present invention proposes a smart city smart street light control method, comprising:
[0007] The collecting unit collects basic data, wherein the basic data includes real-time weather data, real-time lighting data, real-time sound data and real-time image data;
[0008] The central analysis unit analyzes the real-time weather data and the real-time image data to generate a first analysis result, and analyzes the real-time sound data and the real-time image data to generate a second analysis result;
[0009] The central analysis unit generates an optimal lighting solution according to the first analysis result, and generates a warning solution according to the second analysis result;
[0010] The central analysis unit generates a first control instruction and a second control instruction based on the optimal lighting solution and the warning solution respectively;
[0011] Define the smart street lamp that collects the basic data as the first object, and the smart street lamps located on both sides of the first object as the second object, and the control unit controls the first object to perform remote switching and brightness adjustment based on the first control instruction;
[0012] The control unit controls the second object to generate a warning light based on the second control instruction.
[0013] Further, analyzing the real-time weather data and the real-time image data comprises the following steps:
[0014] The real-time image data includes reference image data toward the non-illuminated area, the reference image data is analyzed, illumination distribution data is extracted therefrom, and the illumination distribution data is stored in a database in correspondence with the real-time weather data at the same time;
[0015] Selecting first weather data and second weather data from the database, wherein the first weather data and the second weather data are the real-time weather data belonging to a sunny day and a cloudy day, respectively, obtaining first illumination distribution data and second illumination distribution data stored corresponding to the first weather data and the second weather data, selecting historical illumination distribution data at a historical time point from the database, comparing the historical illumination distribution data with the first illumination distribution data and the second illumination distribution data, respectively, to obtain a first coefficient and a second coefficient, extracting the historical illumination distribution data at the historical time point again, and calculating the corresponding first coefficient and second coefficient, and repeating the extraction until each of the historical time points is traversed;
[0016] Acquire the historical light distribution data at each of the historical time points, set the number of clusters, cluster each of the historical light distribution data based on the number of clusters to obtain multiple clusters, extract characteristic values of multiple preset characteristics in each of the clusters, establish a first regression equation for calculating the first coefficient based on the first coefficient and the characteristic value at each of the historical time points, and calculate a second regression equation for the second coefficient based on the second coefficient and the characteristic value at each of the historical time points.
[0017] Furthermore, generating the optimal lighting solution includes the following steps:
[0018] If the smart street light is in an off state, when the real-time illumination data is less than a first threshold value, the smart street light is turned on and the illumination intensity is adjusted to a predetermined value. If the smart street light is in an on state, the current brightness distribution data toward the non-illuminated area is obtained, the current brightness distribution data is clustered, and the characteristic value of the preset feature of each cluster after clustering is extracted. The first coefficient is calculated using the first regression equation and the extracted characteristic value, and the second coefficient is calculated using the second regression equation and the extracted characteristic value. The brightness value L is calculated based on the first formula, and the first formula is, , wherein K is a reference value, S and C are respectively the preset first value and second value, E1 and E2 are respectively the first coefficient and the second coefficient, a corresponding relationship between the brightness value and the light intensity is established, the light intensity of the smart street lamp is determined based on the calculated brightness value, and the light intensity is set as the optimal lighting solution.
[0019] Further, analyzing the real-time sound data and the real-time image data comprises the following steps:
[0020] Inputting the real-time sound data into a recognition model, if the real-time sound data is determined to be the sound of a traffic accident based on the recognition model, obtaining the location of the traffic accident based on the real-time sound data, obtaining first image data including the location from the real-time image data, analyzing the first image data to classify the traffic accident into a minor type and a serious type, and generating a first emergency event based on the type of the traffic accident;
[0021] Second image data including a predetermined angle is obtained from the real-time image data, and the second image data is analyzed to obtain the walking direction of each pedestrian therein. If the walking direction intersects with the road, it is determined that a pedestrian is crossing the road, and a second emergency event is generated.
[0022] Furthermore, generating the warning scheme includes the following steps:
[0023] If the first emergency event is generated and corresponds to the minor type of the traffic accident, updating the road traffic situation according to the location of the traffic accident; if it is the serious type of the traffic accident, sending the location of the traffic accident to a predetermined terminal;
[0024] If the second emergency event is generated, the walking direction intersecting the road is defined as the crossing direction, the moving speed of the pedestrian in the crossing direction is obtained, and the number of lights P is calculated based on the second formula, and the second formula is: , where L is the road width, V1 is the moving speed, V2 is the average speed of vehicles on this road, α is a correction value set according to the real-time weather data, and the correction value for rainy and snowy weather is greater than that for sunny weather, D is the distance between adjacent smart street lights, N is a preset redundancy value, and the second object whose interval with the first object is less than the number of lights on is located, and its light color is adjusted to a reminder light.
[0025] Furthermore, extracting the light distribution data includes the following steps:
[0026] The reference image data includes first image data and second image data, the first image data and the second image data are taken at a first time point and a second time point respectively, the central analysis unit converts the first image data and the second image data into a first grayscale image and a second grayscale image, and subtracts pixel values of pixels at the same position in the first grayscale image and the second grayscale image to obtain a brightness difference value of each pixel;
[0027] If the brightness difference value meets the preset conditions, continue to obtain the third image data at the third time point, convert the third image data into a third grayscale image, compare the third grayscale image with the first grayscale image and the second grayscale image respectively, and obtain the corresponding brightness difference value; if there is a brightness difference value that does not meet the preset conditions, use the third grayscale image as illumination distribution data.
[0028] Furthermore, the preset condition is that more than a preset number of brightness difference values are greater than a second threshold.
[0029] The present invention also provides a smart city smart street light control device, which is used to implement the smart city smart street light control method described above, and the device includes:
[0030] A collection unit, used to collect basic data, wherein the basic data includes real-time weather data, real-time lighting data, real-time sound data and real-time image data;
[0031] A central analysis unit, for generating a first analysis result based on the real-time weather data and the real-time image data, analyzing the real-time sound data and the real-time image data to generate a second analysis result, and generating a first control instruction and a second control instruction based on the optimal lighting solution and the warning solution respectively;
[0032] A control unit defines a smart street lamp that collects the basic data as a first object, and smart street lamps located on both sides of the first object as a second object. The control unit controls the first object to perform remote switching and brightness adjustment based on the first control instruction, and controls the second object to generate a reminder light based on the second control instruction.
[0033] The present invention also provides an intelligent terminal, including a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to implement the above-mentioned smart city smart street light control method when executing the computer program stored in the memory.
[0034] The present invention also discloses a computer storage medium, which stores program instructions. When the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned smart city smart street lamp control method.
[0035] Compared with the prior art, the beneficial effects of the present invention are at least as follows:
[0036] The present invention not only collects the surrounding light intensity through the light sensor, but also obtains the surrounding light intensity according to weather data and image data. By obtaining the light intensity in these two ways, it is possible to avoid obtaining the wrong light intensity due to interference of vehicle lights, building lights and other factors with the light sensor; after obtaining the light intensity data, the light intensity of the street lamp is automatically adjusted by generating a control instruction, so that the light intensity of the street lamp is adapted to the environment. The present invention not only improves the intelligence of street lamp lighting, but also greatly reduces the power consumption of street lamps, thereby achieving the purpose of energy saving and emission reduction.
[0037] The smart street light of the present invention also captures and analyzes abnormal traffic conditions on the road. When pedestrians cross the road or a traffic accident occurs, control instructions are generated to control the street lights on both sides of the abnormal traffic situation, thereby reminding vehicle drivers on the road in advance to reduce the probability of minor accidents. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative work.
[0039] Figure 1 This is a flowchart of the steps of a smart city smart street lamp control method of the present invention;
[0040] Figure 2 This is a structural schematic diagram of a smart city smart street lamp control device of the present invention. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0042] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.
[0043] like Figure 1 As shown, a smart city smart street lamp control method includes:
[0044] S1: The collection unit collects basic data, which includes real-time weather data, real-time lighting data, real-time sound data and real-time image data.
[0045] Specifically, a collection unit is provided in the smart street light, which includes a temperature sensor, a humidity sensor, a light sensor, an image sensor, a sound sensor, etc. The above data collects the corresponding basic data such as temperature, humidity, light intensity of natural light in the current environment (i.e. real-time lighting data), images and sounds. In addition, the collection unit also collects weather data through the external system.
[0046] S2: The central analysis unit analyzes the real-time weather data and the real-time image data to generate a first analysis result, and analyzes the real-time sound data and the real-time image data to generate a second analysis result.
[0047] The central analysis unit is a server set as the control center. The collection unit sends data to the server through the 5G network, and the server performs data analysis. The central analysis unit preprocesses the data, including data cleaning, denoising, and missing value processing. Through data cleaning, errors in the data, such as format errors, can be identified and corrected, which can significantly improve the quality of the data. Through denoising, outliers of noise in the data can be removed, making the data smoother. Through missing value processing, missing values in the data can be processed to avoid using incomplete or uncertain information in subsequent analysis.
[0048] By combining the real-time weather data and the real-time image data, a first analysis result is obtained, which includes the current light intensity information. In particular, the light intensity information is obtained through image analysis, which is different from the light intensity information collected by the sensor. The light intensity collected by the sensor may be interfered by decorative lights such as buildings, so more accurate light intensity information is obtained through image analysis at night. By combining the real-time sound data and the real-time image data, a second analysis result is obtained, which includes whether there are pedestrians crossing the road or traffic accidents.
[0049] S3: The central analysis unit generates an optimal lighting plan according to the first analysis result, and generates a warning plan according to the second analysis result.
[0050] S4: The central analysis unit generates a first control instruction and a second control instruction based on the optimal lighting solution and the warning solution respectively.
[0051] After obtaining the first analysis result containing light intensity information, a lighting scheme can be generated according to the first analysis result, that is, the lighting intensity of the street lamp can be adjusted in real time according to the first analysis result, thereby achieving the purpose of energy saving and consumption reduction. The present invention generates a warning light through a warning scheme based on the warning result generated by the second analysis result, thereby reminding vehicles on the road to pay attention to pedestrians crossing the road ahead or traffic accidents, thereby improving the intelligence of the smart lamp pole.
[0052] S5: Define the smart street lamp that collects basic data as the first object, and the smart street lamps located on both sides of the first object as the second object. The control unit controls the first object to perform remote switching and brightness adjustment based on the first control instruction.
[0053] S6: The control unit controls the second object to generate a warning light based on the second control instruction.
[0054] After generating the first control instruction and the second control instruction, the control unit sends the first control instruction to the first object to adjust the light brightness of the first object, and sends the second control instruction to the second object to control the second object to generate a warning light, thereby reminding passing vehicles in advance.
[0055] The present invention not only collects the surrounding light intensity through the light sensor, but also obtains the surrounding light intensity according to weather data and image data. By obtaining the light intensity in these two ways, it is possible to avoid obtaining the wrong light intensity due to interference of vehicle lights, building lights and other factors with the light sensor; after obtaining the light intensity data, the light intensity of the street lamp is automatically adjusted by generating a control instruction, so that the light intensity of the street lamp is adapted to the environment. The present invention not only improves the intelligence of street lamp lighting, but also greatly reduces the power consumption of street lamps, thereby achieving the purpose of energy saving and emission reduction.
[0056] The smart street light of the present invention also captures and analyzes abnormal traffic conditions on the road. When pedestrians cross the road or a traffic accident occurs, control instructions are generated to control the street lights on both sides of the abnormal traffic situation, thereby reminding vehicle drivers on the road in advance to reduce the probability of minor accidents.
[0057] It is particularly noteworthy that the smart street lamp of the present invention can remind drivers in the distance according to the road traffic conditions, further improving the intelligence level of the street lamp.
[0058] This embodiment analyzes real-time weather data and real-time image data including the following steps:
[0059] The real-time image data includes reference image data toward the non-illuminated area. The reference image data is analyzed to extract illumination distribution data therefrom. The illumination distribution data and the real-time weather data of the same time are stored in a database in correspondence.
[0060] Select first weather data and second weather data from the database, where the first weather data and the second weather data are real-time weather data belonging to sunny days and cloudy days respectively, obtain first illumination distribution data and second illumination distribution data stored corresponding to the first weather data and the second weather data, select historical illumination distribution data at historical time points from the database, compare the historical illumination distribution data with the first illumination distribution data and the second illumination distribution data respectively, obtain first coefficients and second coefficients, extract the historical illumination distribution data at the historical time points again, calculate the corresponding first coefficients and second coefficients, and repeat the extraction until each historical time point is traversed.
[0061] For example, the non-illuminated area is the sky facing away from the ground. The illumination distribution data is extracted from the reference image data and stored together with the weather data at the same time as the image data at the historical time point. Afterwards, the illumination distribution data representing sunny and cloudy days are selected from the database as template data. For example, through manual selection, the two extracted template data are named first illumination distribution data and second illumination distribution data respectively. After that, the historical illumination distribution data at the historical time point is also extracted from the database, and the historical illumination distribution data is compared with the first illumination distribution data to obtain the ratio of the pixel values of the pixels at the same position. The ratio with the smallest value is used as the first coefficient. Similarly, the historical illumination distribution data is compared with the second illumination distribution data to obtain the second coefficient. Repeating this step can obtain the corresponding first coefficient and second coefficient for each historical time point.
[0062] Acquire historical light distribution data at each historical time point, set the number of clusters, cluster each historical light distribution data based on the number of clusters to obtain multiple clusters, extract characteristic values of multiple preset characteristics in each cluster, establish a first regression equation for calculating the first coefficient based on the first coefficient and characteristic value at each historical time point, and calculate a second regression equation for the second coefficient based on the second coefficient and characteristic value at each historical time point.
[0063] In this embodiment, the number of clusters is set to 3, and the K-means algorithm is used. In other embodiments, it can also be set to natural values such as 4, 5, 6, or an unsupervised clustering algorithm is used without specifying the number of clusters in advance. After extracting the historical illumination distribution data of the historical time point, each pixel point is clustered based on the pixel value, and then the characteristic value of the preset feature in the cluster is extracted. The preset feature includes the number of pixels in the cluster, the average value, standard deviation, maximum value, minimum value of the pixel value, and the maximum difference and minimum difference of the pixel values in the same cluster. Since each historical time point corresponds to the first coefficient and the second coefficient, as well as the corresponding characteristic value, a first regression equation of the characteristic value with respect to the first coefficient and a second regression equation with respect to the second coefficient are established. In this embodiment, The first regression equation is, for example, in the following form, where E1 is the first coefficient, E1=A+A1*W1+A2*W2+A3*W3+A4*W4+A5*W5+A6*W6+A7*W7+···+A15*W15+A16*W16+A17*W17+A18*W18+A19*W19+A20*W20+A21*W21, wherein A1-A7 are the 7 eigenvalues in the first cluster of the illumination distribution data to be analyzed, A15-A21 are the 7 eigenvalues in the third cluster of the illumination distribution data to be analyzed, W1-W21 are the coefficients calculated by regression analysis, A is a constant, and the second regression equation is similar. When there is sufficient data, establishing a regression equation is a prior art.
[0064] The generation of the optimal lighting solution in this embodiment includes the following steps:
[0065] If the smart street light is in the off state, when the real-time illumination data is less than the first threshold, turn on the smart street light and adjust the illumination intensity to a predetermined value. If the smart street light is in the on state, obtain the current brightness distribution data toward the non-illuminated area, cluster the current brightness distribution data, extract the characteristic value of the preset feature of each cluster after clustering, use the first regression equation and the extracted characteristic value to calculate the first coefficient, use the second regression equation and the extracted characteristic value to calculate the second coefficient, and calculate the brightness value L based on the first formula. The first formula is, , where K is the reference value, S and C are the preset first and second values respectively, E1 and E2 are the first coefficient and the second coefficient respectively, and a corresponding relationship between the brightness value and the light intensity is established. The light intensity of the smart street lamp is determined based on the calculated brightness value, and the light intensity is set as the optimal lighting solution.
[0066] If the smart street light is currently in the off state, when the real-time illumination data is less than the first threshold, it indicates that the current environment brightness is dark and the smart street light needs to be turned on. After the street light is turned on, it uses a preset and relatively weak light for illumination. Since the sky is just getting dark when the smart street light is just turned on, there is usually no interference from other lights around. At this time, the real-time illumination data obtained by the light sensor controls the opening of the smart street light. As time goes by, the surrounding environment gradually darkens and light interference begins to appear. At this time, the current brightness distribution data facing the non-illuminated area is obtained. The current brightness distribution data is clustered using the same method as the previous step, and the characteristic value of each cluster is calculated. The data is substituted into the first regression equation and the second regression equation to calculate the first coefficient and the second coefficient. Then, the brightness value of the current surrounding environment is calculated in combination with the first formula. In the first formula, the larger the first coefficient, the larger the calculated brightness value, and the larger the second coefficient, the smaller the calculated brightness value. When the brightness value is large, the smart street light uses a smaller light intensity, or even turns off the smart street light. Conversely, when the brightness value is large, a larger light intensity is used. Through two regression equations, the weather conditions from sunny to cloudy can be quantified, so as to control the smart street lights to adjust the brightness more accurately.
[0067] This embodiment analyzes real-time sound data and real-time image data including the following steps:
[0068] The real-time sound data is input into the recognition model. If the real-time sound data is judged to be the sound of a traffic accident based on the recognition model, the location of the traffic accident is obtained based on the real-time sound data, and first image data including the location is obtained from the real-time image data. The first image data is analyzed to classify the traffic accident into minor and serious types, and a first emergency event is generated based on the type of the traffic accident.
[0069] The second image data including a predetermined angle is obtained from the real-time image data, and the second image data is analyzed to obtain the walking direction of each pedestrian therein. If the walking direction intersects with the road, it is determined that a pedestrian is crossing the road, and a second emergency event is generated.
[0070] Specifically, the recognition model is established based on artificial intelligence algorithms, which can be hidden Markov models, deep learning networks, etc. The smart street lamp collects surrounding sounds through sound sensors, such as microphone arrays. After determining that there is a sound of a traffic accident, it infers the direction of the sound based on the time when the accident sound reaches the microphones in each direction of the microphone array, combined with the acoustic propagation model. After that, the camera is used to capture an image of the direction of the occurrence, that is, the first image data is analyzed, and the severity of the traffic accident is determined through the CNN convolutional neural network. Subsequently, according to the severity of the traffic accident, the street lamp is controlled to display the corresponding warning light.
[0071] The predetermined angle of this embodiment is the angle toward the road. The camera captures second image data containing the road, and by analyzing multiple consecutive second image data, the walking direction and speed of the pedestrian are determined by the position changes of the pedestrian in each frame image. If the walking direction of the pedestrian intersects with the road, it is considered that a pedestrian is crossing the road, and a second emergency event is generated at this time.
[0072] The generation of the warning scheme in this embodiment includes the following steps:
[0073] If the first emergency event is generated and it corresponds to a minor traffic accident, the road traffic situation will be updated according to the location of the traffic accident. If it is a serious traffic accident, the location of the traffic accident will be sent to the predetermined terminal and the brightness of the lights will be increased.
[0074] If it is a minor type of traffic accident, the smart street light will automatically upload the location of the traffic accident to the city map, so that the driver can understand the situation and take a detour in advance; if it is a serious accident, the accident location will be sent to the city map and also to the predetermined terminal, which includes the hospital and traffic law enforcement department closest to the accident site, thereby speeding up the traffic accident handling process and facilitating the handling of traffic accidents by increasing its own brightness.
[0075] If a second emergency event is generated, the walking direction that intersects the road is defined as the crossing direction, the moving speed of the pedestrian in the crossing direction is obtained, and the number of lights P is calculated based on the second formula, which is: , where L is the road width, V1 is the moving speed, V2 is the average speed of cars on this road, α is the correction value set according to real-time weather data, and the correction value for rainy and snowy weather is greater than that for sunny weather, D is the distance between adjacent smart street lights, and N is the preset redundancy value. The second object whose interval with the first object is less than the number of lights on is located, and its light color is adjusted to a reminder light.
[0076] In this embodiment, the smart street lamp has not only a first light-emitting element with a lighting function, but also a second light-emitting element with a reminder function. The second light-emitting element can emit light of a different color from the first light-emitting element, or the second light-emitting element can project a predetermined pattern of light onto the ground. After the first object detects that there is a pedestrian crossing the road, the number of lights is calculated by the second formula. In the second formula, the slower the pedestrian's moving speed, the more lights are calculated, and the faster the average speed of the car, the more lights are calculated. A correction value is added to the second formula, such as 1 when the weather is clear, 5 when it rains, and 10 when it snows. N is a redundant value, which is set to 2 in this embodiment. If the calculated number of lights is 5, the 5 consecutive smart street lamps on the left side of the first object and the 5 consecutive smart street lamps on the right side are adjusted to reminder lights, so that the driver can be reminded in advance, thereby reducing the probability of accidents.
[0077] The present embodiment of extracting light distribution data includes the following steps:
[0078] The reference image data includes first image data and second image data, the first image data and the second image data are respectively taken at a first time point and a second time point, the central analysis unit converts the first image data and the second image data into a first grayscale image and a second grayscale image, and subtracts pixel values of pixels at the same position in the first grayscale image and the second grayscale image to obtain a brightness difference value of each pixel;
[0079] If the brightness difference meets the preset conditions, continue to obtain the third image data at the third time point, convert the third image data into a third grayscale image, and compare the third grayscale image with the first grayscale image and the second grayscale image respectively to obtain the corresponding brightness difference. If there is a brightness difference that does not meet the preset conditions, the third grayscale image is used as the illumination distribution data.
[0080] The first image data and the second image data are two images taken by the camera at the same angle and at different time points, for example, the first image data is taken at 17:00:00, and the second image data is taken at 17:00:05. Then, the first image data and the second image data are converted into a grayscale image. In the grayscale image, the greater the brightness of the pixel point, the greater the corresponding pixel value. After conversion to grayscale, the brightness distribution in the first image data and the second image data can be obtained; the first grayscale image is subtracted from the second grayscale image to obtain the brightness difference.
[0081] The preset condition of this embodiment is that the brightness difference values exceeding the preset number are greater than the second threshold value, and the preset number can be determined according to the shooting resolution. For example, in the case of 1920*1080, the preset number is 200; when the number of brightness difference values in the comparison result meets the preset condition, the third image data captured at the next time point is obtained, and it is also processed into a third grayscale image, and the third grayscale image is compared with the first grayscale image to obtain the corresponding brightness difference value, and the third grayscale image is compared with the second grayscale image to obtain the corresponding brightness difference value. If there is a brightness difference value between the two brightness differences that does not meet the preset condition, the third grayscale image is used as the illumination distribution data.
[0082] The purpose of this step is to first find the points with large brightness changes in the two images. If the number of these points is large, it is considered that the light distribution of the two images is quite different. For example, the birds flying by just cover the interfering light in the second image data. At this time, the third image data is introduced. After comparison with the third image data, if it is found that the two images have similar brightness distributions, it is considered that the two images have normal light distributions. At this time, the third grayscale image is used as the light distribution data.
[0083] like Figure 2 As shown, the present invention also provides a smart city smart street light control device, which is used to implement the above-mentioned smart city smart street light control method, and the device includes:
[0084] A collection unit is used to collect basic data, including real-time weather data, real-time lighting data, real-time sound data and real-time image data;
[0085] A central analysis unit, configured to analyze the real-time weather data and the real-time image data to generate a first analysis result, analyze the real-time sound data and the real-time image data to generate a second analysis result, and generate a first control instruction and a second control instruction based on the optimal lighting solution and the warning solution, respectively;
[0086] The control unit defines the smart street lamp that collects basic data as the first object, and the smart street lamps located on both sides of the first object as the second object. The control unit controls the first object to perform remote switching and brightness adjustment based on the first control instruction, and controls the second object to generate a reminder light based on the second control instruction.
[0087] The present invention also provides an intelligent terminal, including a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to implement the above-mentioned smart city smart street light control method when executing the computer program stored in the memory.
[0088] The present invention also discloses a computer storage medium, which stores program instructions. When the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned smart city smart street lamp control method.
[0089] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.
[0090] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0091] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
[0092] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A smart city smart street light control method, characterized in that: include: The collecting unit collects basic data, wherein the basic data includes real-time weather data, real-time lighting data, real-time sound data and real-time image data; The central analysis unit analyzes the real-time weather data and the real-time image data to generate a first analysis result, and analyzes the real-time sound data and the real-time image data to generate a second analysis result; The central analysis unit generates an optimal lighting solution according to the first analysis result, and generates a warning solution according to the second analysis result; The central analysis unit generates a first control instruction and a second control instruction based on the optimal lighting solution and the warning solution respectively; Define the smart street lamp that collects the basic data as the first object, and the smart street lamps located on both sides of the first object as the second object, and the control unit controls the first object to perform remote switching and brightness adjustment based on the first control instruction; The control unit controls the second object to generate a reminder light based on the second control instruction; Analyzing the real-time weather data and the real-time image data comprises the following steps: The real-time image data includes reference image data toward the non-illuminated area, the reference image data is analyzed, illumination distribution data is extracted therefrom, and the illumination distribution data is stored in a database in correspondence with the real-time weather data at the same time; Selecting first weather data and second weather data from the database, wherein the first weather data and the second weather data are the real-time weather data belonging to a sunny day and a cloudy day, respectively, obtaining first illumination distribution data and second illumination distribution data stored corresponding to the first weather data and the second weather data, selecting historical illumination distribution data at a historical time point from the database, comparing the historical illumination distribution data with the first illumination distribution data and the second illumination distribution data, respectively, to obtain a first coefficient and a second coefficient, extracting the historical illumination distribution data at the historical time point again, and calculating the corresponding first coefficient and second coefficient, and repeating the extraction until each of the historical time points is traversed; Acquire the historical illumination distribution data at each of the historical time points, set the number of clusters, cluster each of the historical illumination distribution data based on the number of clusters to obtain a plurality of clusters, extract characteristic values of a plurality of preset characteristics in each of the clusters, establish a first regression equation for calculating the first coefficient based on the first coefficient and the characteristic value at each of the historical time points, and calculate a second regression equation for the second coefficient based on the second coefficient and the characteristic value at each of the historical time points; Generating the optimal lighting solution includes the following steps: If the smart street light is in an off state, when the real-time illumination data is less than a first threshold value, the smart street light is turned on and the illumination intensity is adjusted to a predetermined value. If the smart street light is in an on state, the current brightness distribution data toward the non-illuminated area is obtained, the current brightness distribution data is clustered, and the characteristic value of the preset feature of each cluster after clustering is extracted. The first coefficient is calculated using the first regression equation and the extracted characteristic value, and the second coefficient is calculated using the second regression equation and the extracted characteristic value. The brightness value L is calculated based on the first formula, and the first formula is, , wherein K is a reference value, S and C are respectively the preset first value and second value, E1 and E2 are respectively the first coefficient and the second coefficient, a corresponding relationship between the brightness value and the light intensity is established, the light intensity of the smart street lamp is determined based on the calculated brightness value, and the light intensity is set as the optimal lighting solution.
2. The method according to claim 1, characterized in that Analyzing the real-time sound data and the real-time image data comprises the following steps: Inputting the real-time sound data into a recognition model, if the real-time sound data is determined to be the sound of a traffic accident based on the recognition model, obtaining the location of the traffic accident based on the real-time sound data, obtaining first image data including the location from the real-time image data, analyzing the first image data to classify the traffic accident into a minor type and a serious type, and generating a first emergency event based on the type of the traffic accident; Second image data including a predetermined angle is obtained from the real-time image data, and the second image data is analyzed to obtain the walking direction of each pedestrian therein. If the walking direction intersects with the road, it is determined that a pedestrian is crossing the road, and a second emergency event is generated.
3. The method according to claim 2, characterized in that Generating the warning scheme includes the following steps: If the first emergency event is generated and corresponds to the minor type of the traffic accident, the road traffic situation is updated according to the location of the traffic accident; if it is the serious type of the traffic accident, the location of the traffic accident is sent to the predetermined terminal and the brightness of the lights is increased; If the second emergency event is generated, the walking direction intersecting the road is defined as the crossing direction, the moving speed of the pedestrian in the crossing direction is obtained, and the number of lights P is calculated based on the second formula, and the second formula is: , where L is the road width, V1 is the moving speed, V2 is the average speed of vehicles on this road, α is a correction value set according to the real-time weather data, and the correction value for rainy and snowy weather is greater than that for sunny weather, D is the distance between adjacent smart street lights, N is a preset redundancy value, and the second object whose interval with the first object is less than the number of lights on is located, and its light color is adjusted to a reminder light.
4. The method according to claim 1, characterized in that: Extracting light distribution data includes the following steps: The reference image data includes first image data and second image data, the first image data and the second image data are taken at a first time point and a second time point respectively, the central analysis unit converts the first image data and the second image data into a first grayscale image and a second grayscale image, and subtracts pixel values of pixels at the same position in the first grayscale image and the second grayscale image to obtain a brightness difference value of each pixel; If the brightness difference value meets the preset conditions, continue to obtain the third image data at the third time point, convert the third image data into a third grayscale image, compare the third grayscale image with the first grayscale image and the second grayscale image respectively, and obtain the corresponding brightness difference value; if there is a brightness difference value that does not meet the preset conditions, use the third grayscale image as illumination distribution data.
5. The method according to claim 4, characterized in that The preset condition is that more than a preset number of brightness difference values are greater than a second threshold.
6. A smart street light control device for a smart city, used to implement the method according to any one of claims 1 to 5, characterized in that: include: A collection unit, used to collect basic data, wherein the basic data includes real-time weather data, real-time lighting data, real-time sound data and real-time image data; A central analysis unit is used to analyze the real-time weather data and the real-time image data to generate a first analysis result, wherein the first analysis result includes a first regression equation and a second regression equation, wherein the real-time image data includes reference image data facing a non-illuminated area, wherein the central analysis unit analyzes the reference image data, extracts illumination distribution data therefrom, and stores the illumination distribution data in a database corresponding to the real-time weather data at the same time, wherein the central analysis unit selects first weather data and second weather data from the database, wherein the first weather data and the second weather data are the real-time weather data belonging to a sunny day and a cloudy day, respectively, and obtains first illumination distribution data and second illumination distribution data stored corresponding to the first weather data and the second weather data, selects historical illumination distribution data at a historical time point from the database, compares the historical illumination distribution data with the first illumination distribution data and the second illumination distribution data, respectively, and obtains a first coefficient and a second coefficient, extracts the historical illumination distribution data at the historical time point again, and calculates the corresponding first coefficient and second coefficient, and repeats the extraction until each historical time point is traversed, wherein the central analysis unit obtains the historical illumination distribution data at each historical time point , setting the number of clusters, clustering each of the historical illumination distribution data based on the number of clusters to obtain a plurality of clusters, extracting the characteristic values of a plurality of preset features in each of the clusters, establishing the first regression equation for calculating the first coefficient based on the first coefficient and the characteristic value of each of the historical time points, calculating the second regression equation for calculating the second coefficient based on the second coefficient and the characteristic value of each of the historical time points, analyzing the real-time sound data and the real-time image data to generate a second analysis result, the central analysis unit generating an optimal lighting scheme based on the first analysis result, generating a warning scheme based on the second analysis result, when generating, if the smart street lamp is in the off state, when the real-time illumination data is less than the first threshold, turning on the smart street lamp and adjusting the illumination intensity to a predetermined value, if the smart street lamp is in the on state, obtaining the current brightness distribution data toward the non-illuminated area, clustering the current brightness distribution data, extracting the characteristic value of the preset feature of each of the clusters after clustering, using the first regression equation and the extracted characteristic value to calculate the first coefficient, using the second regression equation and the extracted characteristic value to calculate the second coefficient, calculating the brightness value L based on the first formula, the first formula is, , wherein K is a reference value, S and C are respectively a preset first value and a second value, E1 and E2 are respectively the first coefficient and the second coefficient, a corresponding relationship between the brightness value and the light intensity is established, the light intensity of the smart street lamp is determined based on the calculated brightness value, the light intensity is set as the optimal lighting scheme, and a first control instruction and a second control instruction are generated based on the optimal lighting scheme and the warning scheme respectively; A control unit defines a smart street lamp that collects the basic data as a first object, and smart street lamps located on both sides of the first object as a second object. The control unit controls the first object to perform remote switching and brightness adjustment based on the first control instruction, and controls the second object to generate a reminder light based on the second control instruction.
7. An intelligent terminal, comprising a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to implement the method described in any one of claims 1 to 5 when executing the computer program stored in the memory.
8. A computer storage medium, characterized in that: The computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Smart city street lamp intelligent control method and system based on Internet of Things
CN115297595A
Intelligent street lamp system based on Internet of Things technology
CN116600446A
Road traffic intelligent guidance system
CN107146428A
Traffic accident warning method and device based on smart light poles
CN108492584A
An unmanned vehicle transverse motion control method based on GK clustering algorithm model prediction
CN109885883A
