Internet of Things data analysis system and method based on intelligent street lamp

Abstract

The invention discloses an Internet of Things data analysis system and method based on an intelligent street lamp, and belongs to the technical field of Internet of Things data analysis. Comprising the steps that a target road is obtained, the target road comprises a plurality of street lamps, each street lamp is provided with an intelligent monitor, vehicles on the target road are shot, and all feature vehicles are obtained; obtaining a characteristic quantity proportion corresponding to each street lamp and energy-saving irradiation power corresponding to the street lamps on the target road; obtaining a power characteristic coefficient corresponding to each street lamp, and obtaining a suggested irradiation power corresponding to each street lamp on the target road; and classifying the street lamps on the target road to obtain the final irradiation power corresponding to each street lamp on the target road. The method comprises the following steps: analyzing vehicle data on a target road to obtain final irradiation power of each street lamp on the target road; therefore, the illumination power of the street lamp on the road is intelligently controlled and adjusted, thereby adjusting the illumination brightness of the street lamp and saving electric energy.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things data analysis, and specifically to an Internet of Things data analysis system and method based on smart street lamps. Background Art

[0002] In recent years, with the improvement of road facilities, especially the widespread implementation of urban lighting projects such as road lighting and landscape lighting, the scale of urban lighting systems has become larger and larger, and more roads have been well covered by lighting, which not only improves the level of traffic safety, but also provides convenience for citizens' night travel, so the requirements for street lighting have become more and more important; smart street light remote monitoring can achieve comprehensive monitoring and remote management of street light equipment through advanced sensors, controllers and remote communication technologies. However, traditional street lights usually run all night, and due to the lack of intelligent control systems, the brightness of the lights cannot be adjusted according to actual needs, resulting in a large amount of energy waste. Therefore, according to the changes in the surrounding vehicles or people on the road, it is of great significance to adjust the irradiation power of the street lights on the road in real time, and then adjust the irradiation brightness of the street lights, which is of great significance to saving electric energy. Summary of the invention

[0003] The purpose of the present invention is to provide an Internet of Things data analysis system and method based on smart street lamps to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] A method for analyzing IoT data based on smart street lamps, comprising the following steps:

[0006] Step S100: Acquire a target road, which includes a number of street lamps, each of which is equipped with an intelligent monitoring system, photograph vehicles on the target road through the intelligent monitoring system, and obtain all characteristic vehicles on the target road based on the information of each photographed vehicle;

[0007] Step S200: according to all characteristic vehicles, obtain the characteristic quantity ratio corresponding to each street lamp, and then obtain the energy-saving irradiation power corresponding to the street lamp on the target road;

[0008] Step S300: According to the intelligent monitoring corresponding to each street lamp on the target road, the real-time vehicle data corresponding to each street lamp is obtained, and the power characteristic coefficient corresponding to each street lamp is obtained according to the real-time vehicle data; according to the energy-saving irradiation power and the power characteristic coefficient, the recommended irradiation power corresponding to each street lamp on the target road is obtained;

[0009] Step S400: Classify the street lamps on the target road, and set the final irradiation power corresponding to each street lamp on the target road according to the recommended irradiation power corresponding to each street lamp in each category.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S110: The road between two adjacent road intersections is taken as the target road. A certain target road TP includes several street lamps, wherein the intelligent monitoring corresponding to a certain street lamp SL is MT; a complete monitoring video shot by the intelligent monitoring MT in the past several days starting from the current time is obtained, and N monitoring videos are intercepted from the complete monitoring video according to each light on and off time corresponding to the certain street lamp SL;

[0012] There are many types of road intersections, including cross, T-shaped, Y-shaped intersections, etc., all of which are road intersections. The record between the on-time and off-time of a street lamp SL is a complete record corresponding to the surveillance video;

[0013] Step S120: Set the road length corresponding to a target road TP to L TP , the maximum speed limit is set to V TP , get the time interval Ti corresponding to a certain target road TP TP =min(L TP / V TP ,Ti0), where min() is the minimum value and Ti0 is the time interval threshold; then we get the nth surveillance video starting from the start time and the time interval is Ti TP Each frame of monitoring screen; pre-train the neural network model, and use the neural network model to mark all vehicles in each frame of monitoring screen;

[0014] Step S130: convert each frame of the monitoring screen obtained into a grayscale image, wherein the grayscale image corresponding to a certain frame of the monitoring screen RP is GP, and obtain the area in the grayscale image GP where the grayscale value is greater than the grayscale threshold as the illumination range Ran of the certain street lamp SL on the certain target road TP SL ; Convert a certain frame of monitoring screen RP into a two-dimensional coordinate system, obtain a certain vehicle car on a certain frame of monitoring screen RP, and obtain the rectangular bounding box Ran corresponding to the certain vehicle car on the certain frame of monitoring screen RP through the trained neural network model car , the rectangular bounding box Ran car With the irradiation range Ran SL The area of ​​the intersection is Area, and the rectangular bounding box is Ran. car There are four rectangular vertices corresponding to a certain frame of monitoring screen RP. According to the coordinate points corresponding to each rectangular vertex in the two-dimensional coordinate system, the distance between the two coordinate points with the largest horizontal coordinate and the second largest horizontal coordinate is used as the vehicle width Wid of a certain vehicle car. car ;

[0015] Step S140: If Area≥Area0 and Wid car ≥Wid0 are satisfied, where Area0 is the area threshold and Wid0 is the vehicle width threshold, then use the vehicle car as the feature vehicle; thus, all feature vehicles in each frame of the monitoring video corresponding to the street lamp SL are obtained.

[0016] Further, step S200 includes the following steps:

[0017] Step S210: Obtain the power irradiated by each street lamp in the A days before a target road TP starting from the current time, and obtain the historical irradiation power where A is the total number of days and M is the total number of street lamps corresponding to the target road TP, is the power irradiated by the b-th street lamp on the a-th day; according to the total number of feature vehicles at each moment in the n-th monitoring video corresponding to the street lamp SL, use the moment as the abscissa and the total number of feature vehicles as the ordinate to establish a moment-total number line graph;

[0018] Step S220: Obtain the first moment corresponding to the maximum value of the total number of feature vehicles in the moment-total number line graph, obtain 2X + 1 moments that are adjacent X moments to the left and right with the abscissa corresponding to the first moment as the midpoint, and add up the total number of feature vehicles corresponding to the 2X + 1 moments and find the average value to obtain the first quantity Y1; obtain the second moment corresponding to the minimum value of the total number of feature vehicles in the moment-total number line graph, obtain 2X + 1 moments that are adjacent X moments to the left and right with the abscissa corresponding to the second moment as the midpoint, and add up the total number of feature vehicles corresponding to the 2X + 1 moments and find the average value to obtain the second quantity Y2; according to the first quantity Y1 and the second quantity Y2, obtain the feature quantity ratio Rat n = Y1 / Y2;

[0019] Step S230: According to the historical irradiation power P^ and the feature quantity ratio Rat n , obtain the energy-saving irradiation power corresponding to the street lamp SL If P E < P1, let P E = P1, if P E > P2, let P E = P2, where N is the total number of monitoring videos corresponding to the street lamp SL, K0 is the energy-saving irradiation power coefficient, and P1 and P2 are the first power threshold and the second power threshold respectively.

[0020] Even if there are no vehicles on the target road, the street lamp should still illuminate. This illumination power is the energy-saving illumination power in this solution, that is, the energy-saving illumination power is the power of the street lamp when there are no large vehicles. Since the energy-saving illumination power is obtained based on the historical vehicle data of the target road; when there are more vehicles with large characteristic vehicles, it means that there are often vehicles passing by the road. Under normal circumstances, there should be more non-motor vehicles or pedestrians on the road. Therefore, when there are fewer vehicles on the road, there may also be more non-motor vehicles or pedestrians. Therefore, the energy-saving illumination power of the road should be set higher, that is, the energy-saving illumination power X should be larger; when there are fewer vehicles with large characteristic vehicles, it means that there are not often vehicles passing by the road. Under normal circumstances, there should be fewer non-motor vehicles or pedestrians on the road. Therefore, when there are fewer vehicles on the road, there are also fewer non-motor vehicles or pedestrians. Therefore, the energy-saving illumination power of the road should be set lower, that is, the energy-saving illumination power X should be smaller.

[0021] Further, step S300 includes the following steps:

[0022] Step S310: The monitoring image captured by the intelligent monitoring MT corresponding to a street lamp SL at the current moment is used as the RP MT , according to step S130, the monitoring screen RP is obtained MT Each characteristic vehicle on the image, and the illumination range Ran of the street lamp SL SL , and then get each characteristic vehicle in the monitoring screen RP MT The corresponding rectangular bounding box is obtained, and then each rectangular bounding box and the irradiation range Ran are obtained. SL The area of ​​the intersection, and add the areas to get the total area Area MT , and then according to the irradiation range Ran SL Corresponding area SL , we get the area ratio R = Area MT / Area SL , 0≤R≤1; and then obtain the power characteristic coefficient C=e corresponding to a street lamp SL at the current moment R , and normalized, e is the natural logarithm;

[0023] If the power characteristic coefficient is large, it means that the density of vehicles at this moment is high. The power characteristic coefficient is obtained based on the current number of vehicles on the street lamp and the size of each vehicle. The power characteristic coefficient reflects the number of vehicles and the size of the vehicles. In this scheme, as long as there are vehicles, even if there are few vehicles, the power characteristic coefficient should be large, because even if there is only one vehicle on the road, in order to ensure the safety of vehicle operation, the street lamp must light up the appropriate brightness for this vehicle;

[0024] Step S320: When the area ratio R=0, the recommended irradiation power P corresponding to a street lamp SLS = P E ; According to the energy-saving irradiation power P E and the power characteristic coefficient C, and the historical irradiation power P^, if the energy-saving irradiation power is P E = P1, the recommended irradiation power P S = P E * C; if the energy-saving irradiation power is P E = P2, then the recommended irradiation power P S = P^; if the energy-saving irradiation power is P1 < P E < P2, then the recommended irradiation power P S = min(P E * C, P^), and min() is to find the minimum value.

[0025] Furthermore, step S400 includes the following steps:

[0026] Step S410: According to the vehicle driving direction, sort each street lamp corresponding to a certain target road TP from small to large, and obtain the street lamp recommended power line graph corresponding to the target road TP according to the recommended irradiation power of each street lamp;

[0027] Step S420: Set the total number of street lamps corresponding to a certain target road TP as M, and the number of street lamp clusters as T. Take T adjacent street lamps in the street lamp recommended power line graph as one class, and a total of M - T + 1 classes are divided. If the recommended irradiation power of the street lamp with the smallest serial number in the v-th class is the largest in the v-th class, then set the final irradiation power of all street lamps in the v-th class to the recommended irradiation power of the street lamp with the smallest serial number; if the recommended irradiation power of the street lamp with the smallest serial number in the v-th class is not the largest in the v-th class, then set the final irradiation power of all street lamps in the v-th class to the recommended irradiation power corresponding to each street lamp;

[0028] In this solution, the maximum recommended power is used as the final irradiation power because when the irradiation power of a certain street lamp changes with the vehicle conditions corresponding to the street lamp, for other street lamps behind the street lamp, since the other street lamps behind also have a certain effect on the vehicle driving, the power of the other street lamps behind should be changed accordingly;

[0029] Step S430: If a certain street lamp has multiple final irradiation powers, then take the maximum value of the multiple final irradiation powers as the final irradiation power of the street lamp; thus, the final irradiation power of each street lamp is obtained.

[0030] An Internet of Things data analysis system based on smart street lamps includes a characteristic vehicle module, an energy-saving irradiation power module, a recommended irradiation power module, and a final irradiation power module;

[0031] Feature vehicle module: used to obtain the target road, which includes several street lights. Each street light is equipped with intelligent monitoring. The vehicles on the target road are photographed through intelligent monitoring, and all the feature vehicles are obtained based on the information of each photographed vehicle.

[0032] Energy-saving irradiation power module: used to obtain the characteristic quantity ratio corresponding to each street lamp according to all characteristic vehicles, and then obtain the energy-saving irradiation power corresponding to the street lamp on the target road;

[0033] Recommended irradiation power module: used to obtain the real-time vehicle data corresponding to each street lamp according to the intelligent monitoring corresponding to each street lamp on the target road, and obtain the power characteristic coefficient corresponding to each street lamp according to the real-time vehicle data; according to the energy-saving irradiation power and the power characteristic coefficient, obtain the recommended irradiation power corresponding to each street lamp on the target road;

[0034] Final irradiation power module: used to classify the street lamps on the target road, and set the final irradiation power corresponding to each street lamp on the target road according to the recommended irradiation power corresponding to each street lamp in each category.

[0035] Further, it is suggested that the irradiation power module includes a line graph unit, a characteristic quantity ratio unit and an energy-saving irradiation power unit;

[0036] Line chart unit: used to create a time-total number line chart based on the total number of characteristic vehicles at each moment in the surveillance video corresponding to a street lamp;

[0037] Feature quantity ratio unit: used to obtain the first quantity and the second quantity corresponding to the time-total quantity line graph, and then obtain the feature quantity ratio of the monitoring video corresponding to a street lamp;

[0038] Energy-saving irradiation power unit: used to obtain the energy-saving irradiation power corresponding to a street lamp according to the ratio of the number of features.

[0039] Further, the final irradiation power module includes a street lamp recommended power line graph unit, a street lamp classification unit and a final irradiation power unit;

[0040] Street lamp recommended power line graph unit: used to sort each street lamp corresponding to a target road from small to large according to the direction of vehicle travel, and obtain a street lamp recommended power line graph corresponding to a target road according to the recommended irradiation power of each street lamp;

[0041] Street light classification unit: used to classify street lights on a target road into several categories;

[0042] Final irradiation power unit: used to obtain the final irradiation power of each street lamp.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention provides an IoT data analysis system and method based on smart street lamps, including: obtaining a target road, the target road includes a number of street lamps, each street lamp is equipped with intelligent monitoring, photographing vehicles on the target road, and obtaining all characteristic vehicles; obtaining the characteristic quantity ratio corresponding to each street lamp, and the energy-saving irradiation power corresponding to the street lamps on the target road; obtaining the power characteristic coefficient corresponding to each street lamp, and obtaining the recommended irradiation power corresponding to each street lamp on the target road; classifying the street lamps on the target road, and obtaining the final irradiation power corresponding to each street lamp on the target road. The present invention obtains the final irradiation power of each street lamp on the target road by analyzing the vehicle data on the target road; realizes intelligent control and adjustment of the irradiation power of the street lamps on the road, and then adjusts the irradiation brightness of the street lamps to save electric energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a flow chart of an Internet of Things data analysis method based on smart street lamps of the present invention;

[0046] Figure 2 It is a structural diagram of an Internet of Things data analysis system based on smart street lamps of the present invention;

[0047] Figure 3 It is a structural schematic diagram of a vehicle car on a certain frame monitoring screen RP of an Internet of Things data analysis system and method based on smart street lamps of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1-Figure 2 The present invention provides an Internet of Things data analysis system and method based on smart street lamps, and a corresponding flowchart of an Internet of Things data analysis method based on smart street lamps is shown as follows: Figure 1 As shown. The following steps are included:

[0050] Step S100: Acquire a target road, which includes a number of street lamps. Each street lamp is equipped with an intelligent monitor. Vehicles on the target road are photographed through the intelligent monitor, and all characteristic vehicles therein are obtained based on the information of each photographed vehicle.

[0051] Step S110: The road between two adjacent road intersections is taken as the target road. A certain target road TP includes several street lamps, among which the intelligent monitoring corresponding to a certain street lamp SL is MT; the complete monitoring video shot by the intelligent monitoring MT in the past several days starting from the current time is obtained, and N monitoring videos are intercepted from the complete monitoring video according to each light on and off time corresponding to a certain street lamp SL.

[0052] There are many types of road intersections, including cross, T-shaped, Y-shaped intersections, etc., all of which are road intersections. The record between the on-time and off-time of a street lamp SL is a complete record corresponding to the surveillance video.

[0053] Step S120: Set the road length corresponding to a target road TP to L TP , the maximum speed limit is set to V TP , get the time interval Ti corresponding to a certain target road TP TP =min(L TP / V TP ,Ti0), where min() is the minimum value and Ti0 is the time interval threshold; then we get the nth surveillance video starting from the start time and the time interval is Ti TP Each frame of monitoring screen; pre-train the neural network model, and use the neural network model to mark all vehicles in each frame of monitoring screen;

[0054] Step S130: convert each frame of the monitoring screen obtained into a grayscale image, wherein the grayscale image corresponding to a certain frame of the monitoring screen RP is GP, and obtain the area in the grayscale image GP where the grayscale value is greater than the grayscale threshold as the illumination range Ran of the certain street lamp SL on the certain target road TP SL ; Convert a certain frame of monitoring screen RP into a two-dimensional coordinate system, obtain a certain vehicle car on a certain frame of monitoring screen RP, and obtain the rectangular bounding box Ran corresponding to the certain vehicle car on the certain frame of monitoring screen RP through the trained neural network model car , the rectangular bounding box Ran car With the irradiation range Ran SL The area of ​​the intersection is Area, and the rectangular bounding box is Ran. car There are four rectangular vertices corresponding to a certain frame of monitoring screen RP. According to the coordinate points corresponding to each rectangular vertex in the two-dimensional coordinate system, the distance between the two coordinate points with the largest horizontal coordinate and the second largest horizontal coordinate is used as the vehicle width Wid of a certain vehicle car.car . For details, please refer to the attached Figure 3 The structural schematic diagram of a vehicle car on a certain frame of monitoring screen RP is shown below.

[0055] Step S140: If Area≥Area0 and Wid car ≥Wid0, where Area0 is the area threshold and Wid0 is the vehicle width threshold, the vehicle car is taken as the feature vehicle; and then all the feature vehicles in each frame of monitoring screen in each monitoring video corresponding to the street lamp SL are obtained.

[0056] Feature vehicles are vehicles that can be displayed in most of the road image and whose width meets certain requirements. By analyzing these vehicles, the impact caused by non-motor vehicles and pedestrians can be excluded. SL Wid0 is 1 / 10 of the corresponding area, and Wid0 is 1 / 5 of the maximum value of the vertical coordinate corresponding to RP of a certain frame of monitoring screen.

[0057] Step S200: According to all characteristic vehicles, the characteristic quantity ratio corresponding to each street lamp is obtained, and then the energy-saving illumination power corresponding to the street lamp on the target road is obtained.

[0058] Step S210: Obtain the irradiation power of each street lamp on a target road TP A days ago, starting from the current time, and obtain the historical irradiation power Among them, A is the total number of days, M is the total number of street lights corresponding to a certain target road TP, is the power irradiated by the bth street lamp on the ath day; according to the total number of characteristic vehicles at each moment in the nth monitoring video corresponding to the street lamp SL, a time-total number line graph is established with the time as the horizontal axis and the total number of characteristic vehicles as the vertical axis;

[0059] Step S220: Obtain the first moment corresponding to the maximum total number of characteristic vehicles in the moment-total number line graph, obtain the X moments adjacent to the left and right with the horizontal coordinate corresponding to the first moment as the midpoint, a total of 2X+1 moments, and add the total number of characteristic vehicles corresponding to the 2X+1 moments to obtain the average value, and obtain the first number Y1; obtain the second moment corresponding to the minimum total number of characteristic vehicles in the moment-total number line graph, obtain the X moments adjacent to the left and right with the horizontal coordinate corresponding to the second moment as the midpoint, a total of 2X+1 moments, and add the total number of characteristic vehicles corresponding to the 2X+1 moments to obtain the average value, and obtain the second number Y2; according to the first number Y1 and the second number Y2, obtain the characteristic quantity ratio Rat of the nth monitoring video corresponding to a certain street lamp SL n =Y1 / Y2;

[0060] Step S230: Based on the historical irradiation power P^ and the characteristic quantity ratio Rat n , obtain the energy-saving irradiation power corresponding to a certain street lamp SL If P E < P1, let P E = P1. If P E > P2, let P E = P2, where N is the total number of monitoring videos corresponding to a certain street lamp SL, K0 is the energy-saving irradiation power coefficient, and P1 and P2 are the first power threshold and the second power threshold respectively.

[0061] Even if there are no vehicles on the target road, the street lamps should still irradiate. The power of this irradiation is the energy-saving irradiation power in this solution, that is, the energy-saving irradiation power is the power when the street lamp irradiates without large-sized vehicles. Since the energy-saving irradiation power is obtained based on the historical vehicle data of the target road; when there are more large-sized characteristic vehicles, it indicates that there are often vehicles passing through this road. Normally, there should also be more non-motor vehicles or pedestrians on this road. Therefore, when there are fewer vehicles on this road, there may still be more non-motor vehicles or pedestrians. So the energy-saving irradiation power of this road should be set relatively high, that is, the energy-saving irradiation power X should be larger; when there are fewer large-sized characteristic vehicles, it indicates that there are not often vehicles passing through this road. Normally, there should also be fewer non-motor vehicles or pedestrians on this road. Therefore, when there are fewer vehicles on this road, there are also fewer non-motor vehicles or pedestrians. So the energy-saving irradiation power of this road should be set relatively low, that is, the energy-saving irradiation power X should be smaller; and the energy-saving irradiation power is most suitable at about 30% - 70% of the historical irradiation power. Therefore, in this embodiment, P1 = 30% and P2 = 70%.

[0062] Step S300: Based on the intelligent monitoring corresponding to each street lamp on the target road, obtain the real-time vehicle data corresponding to each street lamp currently, and based on the real-time vehicle data, obtain the power characteristic coefficient corresponding to each street lamp; based on the energy-saving irradiation power and the power characteristic coefficient, obtain the recommended irradiation power corresponding to each street lamp on the target road.

[0063] Step S310: Take the monitoring image captured by the intelligent monitoring MT corresponding to a certain street lamp SL at the current moment as RP MT , and according to Step S130, obtain each characteristic vehicle on the monitoring image RP MT , and the irradiation range Ran SL of the certain street lamp SL, and then obtain the rectangular bounding box corresponding to each characteristic vehicle on the monitoring image RP MT , and then obtain the area of intersection between each rectangular bounding box and the irradiation range Ran SL , and add up the areas to obtain the total area Area MT , and then according to the irradiation range Ran SLCorresponding area Area SL , the area ratio R = Area MT / Area SL , 0 ≤ R ≤ 1; furthermore, the power characteristic coefficient C corresponding to a certain street lamp SL at the current moment is obtained as C = e R , and normalization is performed, where e is the natural logarithm. C ∈ [0, 1].

[0064] If the power characteristic coefficient is large, it indicates a high density of vehicles at this moment. The power characteristic coefficient is obtained based on the current number of vehicles on the street lamp and the volume of each vehicle. The power characteristic coefficient reflects the number of vehicles and the volume of the vehicles. In this solution, as long as there are vehicles, even if the number of vehicles is small, the power characteristic coefficient should be large. Because even if there is only one vehicle on the road, in order to ensure the safety of vehicle operation, the street lamp should illuminate an appropriate brightness for this one vehicle. Therefore, in this embodiment, the exponential formula C = e R is used. Of course, the more vehicles or the larger the volume of the vehicles, the larger the power characteristic coefficient should be.

[0065] Step S320: When the area ratio R = 0, the recommended irradiation power P S corresponding to a certain street lamp SL is P E ; according to the energy-saving irradiation power P E and the power characteristic coefficient C, as well as the historical irradiation power P^, if the energy-saving irradiation power is P E = P1, the recommended irradiation power P S corresponding to a certain street lamp SL is P E * C; if the energy-saving irradiation power is P E = P2, then the recommended irradiation power P S corresponding to a certain street lamp SL is P^; if the energy-saving irradiation power is P1 < P E < P2, then the recommended irradiation power P S corresponding to a certain street lamp SL is min(P E * C, P^), and min() is used to find the minimum value.

[0066] Step S400: Classify the street lamps on the target road, and set the final irradiation power corresponding to each street lamp on the target road according to the recommended irradiation power corresponding to each street lamp in each category.

[0067] Step S410: Sort each street lamp corresponding to a certain target road TP in ascending order according to the vehicle driving direction, and obtain the street lamp recommended power line graph corresponding to the certain target road TP according to the recommended irradiation power of each street lamp.

[0068] Step S420: Set the total number of street lamps corresponding to a target road TP to M, the number of street lamp clusters to T, and take the T adjacent street lamps in the street lamp recommended power line graph as one class, which is divided into M-T+1 classes in total. If the recommended illumination power corresponding to the street lamp with the smallest serial number in the vth class is the largest in the vth class, then the final illumination powers corresponding to all street lamps in the vth class are set to the recommended illumination power corresponding to the street lamp with the smallest serial number; if the recommended illumination power corresponding to the street lamp with the smallest serial number in the vth class is not the largest in the vth class, then the final illumination powers corresponding to all street lamps in the vth class are set to the recommended illumination powers corresponding to each street lamp.

[0069] The maximum recommended power is used as the final illumination power in this scheme because when the illumination power of a street lamp changes with the vehicle situation corresponding to the street lamp, the power of other street lamps behind the street lamp should be changed accordingly because the other street lamps behind the street lamp also have a certain effect on the driving of the vehicle. In this scheme, T street lamps are regarded as a category, so the number of other street lamps behind is T-1.

[0070] Step S430: If a street lamp has multiple final irradiation powers, the maximum value of the multiple final irradiation powers is used as the final irradiation power of the street lamp; and then the final irradiation power of each street lamp is obtained.

[0071] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0072] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing Internet of Things data based on smart street lamps, characterized in that: The following steps are involved: Step S100: Acquire a target road, where the target road includes a plurality of street lamps, each of which is equipped with an intelligent monitoring system, and photograph vehicles on the target road through the intelligent monitoring system, and obtain all characteristic vehicles therein based on information of each photographed vehicle; Step S200: according to all the characteristic vehicles, obtaining the characteristic quantity ratio corresponding to each street lamp, and then obtaining the energy-saving irradiation power corresponding to the street lamp on the target road; Step S300: According to the intelligent monitoring corresponding to each street lamp on the target road, the real-time vehicle data corresponding to each street lamp is obtained, and the power characteristic coefficient corresponding to each street lamp is obtained according to the real-time vehicle data; According to the energy-saving irradiation power and the power characteristic coefficient, a recommended irradiation power corresponding to each street lamp on the target road is obtained; Step S400: Classify the street lamps on the target road, and set the final irradiation power corresponding to each street lamp on the target road according to the recommended irradiation power corresponding to each street lamp in each category.

2. The method for analyzing IoT data based on smart street lamps according to claim 1 is characterized in that: Step S100 includes the following steps: Step S110: The road between two adjacent road intersections is taken as the target road. A certain target road TP includes several street lamps, wherein the intelligent monitoring corresponding to a certain street lamp SL is MT; a complete monitoring video shot by the intelligent monitoring MT in the past several days starting from the current time is obtained, and N monitoring videos are intercepted from the complete monitoring video according to each light on and off time corresponding to the certain street lamp SL; Step S120: Set the road length corresponding to the target road TP to L TP , the maximum speed limit is set to V TP , get the time interval Ti corresponding to a certain target road TP TP =min(L TP / V TP ,Ti0), where min() is the minimum value and Ti0 is the time interval threshold; then we get the nth surveillance video starting from the start time and the time interval is Ti TP Each frame of monitoring screen; pre-train the neural network model, and use the neural network model to mark all vehicles in each frame of monitoring screen; Step S130: convert each frame of the monitoring screen obtained into a grayscale image, wherein the grayscale image corresponding to a certain frame of the monitoring screen RP is GP, and obtain the area in the grayscale image GP where the grayscale value is greater than the grayscale threshold as the illumination range Ran of the certain street lamp SL on the certain target road TP SL ; Convert a certain frame of monitoring screen RP into a two-dimensional coordinate system, obtain a certain vehicle car on a certain frame of monitoring screen RP, and obtain the rectangular bounding box Ran corresponding to the certain vehicle car on the certain frame of monitoring screen RP through the trained neural network model car , the rectangular bounding box Ran car With the irradiation range Ran SL The area of ​​the intersection is Area, and the rectangular bounding box is Ran. car There are four rectangular vertices corresponding to a certain frame of monitoring screen RP. According to the coordinate points corresponding to each rectangular vertex in the two-dimensional coordinate system, the distance between the two coordinate points with the largest horizontal coordinate and the second largest horizontal coordinate is used as the vehicle width Wid of a certain vehicle car. car ; Step S140: If Area≥Area0 and Wid car ≥Wid0, where Area0 is the area threshold and Wid0 is the vehicle width threshold, the vehicle car is taken as the feature vehicle; and then all the feature vehicles in each frame of monitoring screen in each monitoring video corresponding to the street lamp SL are obtained.

3. The method for analyzing IoT data based on smart street lamps according to claim 2 is characterized in that: Step S200 includes the following steps: Step S210: Obtain the irradiation power of each street lamp on a target road TP A days ago, starting from the current time, and obtain the historical irradiation power Among them, A is the total number of days, M is the total number of street lights corresponding to a certain target road TP, is the power irradiated by the bth street lamp on the ath day; according to the total number of characteristic vehicles at each moment in the nth monitoring video corresponding to the street lamp SL, a time-total number line graph is established with the time as the horizontal axis and the total number of characteristic vehicles as the vertical axis; Step S220: Obtain the first moment corresponding to the maximum total number of characteristic vehicles in the moment-total number line graph, obtain the X moments adjacent to the left and right with the horizontal coordinate corresponding to the first moment as the midpoint, a total of 2X+1 moments, and add the total number of characteristic vehicles corresponding to the 2X+1 moments to obtain the average value, and obtain the first number Y1; obtain the second moment corresponding to the minimum total number of characteristic vehicles in the moment-total number line graph, obtain the X moments adjacent to the left and right with the horizontal coordinate corresponding to the second moment as the midpoint, a total of 2X+1 moments, and add the total number of characteristic vehicles corresponding to the 2X+1 moments to obtain the average value, and obtain the second number Y2; according to the first number Y1 and the second number Y2, obtain the characteristic quantity ratio Rat of the nth monitoring video corresponding to a certain street lamp SL n =Y1 / Y2; Step S230: Obtain the energy-saving irradiation power corresponding to a certain street lamp SL according to the historical irradiation power P^ and the feature quantity ratio Rat n , and obtain the energy-saving irradiation power corresponding to a certain street lamp SL If P E < P1, let P E = P1; if P E > P2, let P E = P2, where N is the total number of monitoring videos corresponding to a certain street lamp SL, K0 is the energy-saving irradiation power coefficient, and P1 and P2 are the first power threshold and the second power threshold respectively.

4. The method for analyzing IoT data based on smart street lamps according to claim 3 is characterized in that: Step S300 includes the following steps: Step S310: The monitoring image captured by the intelligent monitoring MT corresponding to a street lamp SL at the current moment is used as the RP MT , according to step S130, the monitoring screen RP is obtained MT Each characteristic vehicle on the map, and the illumination range Ran of the street lamp SL SL , and then get each characteristic vehicle in the monitoring screen RP MT The corresponding rectangular bounding box is obtained, and then each rectangular bounding box and the irradiation range Ran are obtained. SL The area of ​​the intersection, and add the areas to get the total area Area MT , and then according to the irradiation range Ran SL Corresponding area SL , we get the area ratio R = Area MT / Area SL , 0≤R≤1; and then obtain the power characteristic coefficient C=e corresponding to a street lamp SL at the current moment R , and normalized, e is the natural logarithm; Step S320: When the area ratio R = 0, the recommended irradiation power P of a certain street lamp SL S = P E ; According to the energy-saving irradiation power P E and the power characteristic coefficient C, as well as the historical irradiation power P^, if the energy-saving irradiation power is P E = P1, the recommended irradiation power P of a certain street lamp SL S = P E * C; if the energy-saving irradiation power is P E = P2, then the recommended irradiation power P of a certain street lamp SL S = P^; if the energy-saving irradiation power is P1 < P E < P2, then the recommended irradiation power P of a certain street lamp SL S = min(P E * C, P^), and min() is to find the minimum value.

5. The method for analyzing IoT data based on smart street lamps according to claim 1 is characterized in that: Step S400 includes the following steps: Step S410: sorting each street lamp corresponding to a target road TP from small to large according to the vehicle's driving direction, and obtaining a street lamp recommended power line graph corresponding to the target road TP according to the recommended irradiation power of each street lamp; Step S420: Set the total number of street lamps corresponding to a certain target road TP to M, the number of street lamp clusters to T, and take the T adjacent street lamps in the street lamp recommended power line graph as one class, which is divided into M-T+1 classes in total. If the recommended irradiation power corresponding to the street lamp with the smallest serial number in the vth class is the largest in the vth class, then the final irradiation powers corresponding to all street lamps in the vth class are set to the recommended irradiation power corresponding to the street lamp with the smallest serial number; if the recommended irradiation power corresponding to the street lamp with the smallest serial number in the vth class is not the largest in the vth class, then the final irradiation powers corresponding to all street lamps in the vth class are set to the recommended irradiation powers corresponding to each street lamp; Step S430: If a street lamp has multiple final irradiation powers, the maximum value of the multiple final irradiation powers is used as the final irradiation power of the street lamp; and then the final irradiation power of each street lamp is obtained.

6. An Internet of Things data analysis system, used to execute an Internet of Things data analysis method based on smart street lamps as described in any one of claims 1 to 5, characterized in that: The system includes a characteristic vehicle module, an energy-saving irradiation power module, a recommended irradiation power module and a final irradiation power module; Feature vehicle module: used to obtain a target road, which includes several street lights, each of which is equipped with intelligent monitoring. Vehicles on the target road are photographed through intelligent monitoring, and all feature vehicles are obtained based on the information of each photographed vehicle; Energy-saving irradiation power module: used to obtain the characteristic quantity ratio corresponding to each street lamp according to all the characteristic vehicles, and then obtain the energy-saving irradiation power corresponding to the street lamp on the target road; Recommended irradiation power module: used to obtain the real-time vehicle data corresponding to each street lamp according to the intelligent monitoring corresponding to each street lamp on the target road, and obtain the power characteristic coefficient corresponding to each street lamp according to the real-time vehicle data; according to the energy-saving irradiation power and the power characteristic coefficient, obtain the recommended irradiation power corresponding to each street lamp on the target road; Final irradiation power module: used to classify the street lamps on the target road, and set the final irradiation power corresponding to each street lamp on the target road according to the recommended irradiation power corresponding to each street lamp in each category.

7. The Internet of Things data analysis system according to claim 6, characterized in that: The suggested irradiation power module includes a line graph unit, a characteristic quantity ratio unit and an energy-saving irradiation power unit; Line chart unit: used to create a time-total number line chart based on the total number of characteristic vehicles at each moment in the surveillance video corresponding to a street lamp; Feature quantity ratio unit: used to obtain the first quantity and the second quantity corresponding to the time-total quantity line graph, and then obtain the feature quantity ratio of the monitoring video corresponding to a street lamp; Energy-saving irradiation power unit: used to obtain the energy-saving irradiation power corresponding to a street lamp according to the ratio of the number of features.

8. The Internet of Things data analysis system according to claim 7, characterized in that: The final irradiation power module includes a street lamp recommended power line graph unit, a street lamp classification unit and a final irradiation power unit; Street lamp recommended power line graph unit: used to sort each street lamp corresponding to a target road from small to large according to the direction of vehicle travel, and obtain a street lamp recommended power line graph corresponding to a target road according to the recommended irradiation power of each street lamp; Street light classification unit: used to classify street lights on a target road into several categories; Final irradiation power unit: used to obtain the final irradiation power of each street lamp.

Images