Smart city lighting management system based on traffic flow

Abstract

The present invention relates to a smart city lighting management system based on traffic flow applied in the field of electric lighting. By collecting road traffic images, the vehicle flow on each lane of the road is analyzed. According to the lane traffic direction, the next road that the vehicle is about to enter is predicted, and then the traffic flow that is about to be generated on the next road is obtained, so that the lighting intensity of the next road can be adjusted accordingly in advance before the traffic arrives. Compared with the means of adjusting the lighting of roads with existing traffic flow in the prior art, the present application better guarantees traffic safety through the objective adjustment process of predicting the traffic flow and adjusting it in advance. In addition, the present application also regularly conducts lighting opinion surveys on drivers who have just passed the road. According to the feedback data from the personnel, based on the above objective adjustment results, the road lighting intensity is subjectively adjusted, such as enhanced, weakened or unchanged, so that the lighting intensity is more adapted to the actual traffic needs, thereby further improving traffic safety.

Description

Technical Field

[0001] The present invention relates to a city lighting management system, and in particular to a smart city lighting management system based on traffic flow applied in the field of electric lighting. Background Art

[0002] In the construction of smart cities, street lighting systems are important and basic equipment and facilities in cities. Appropriate lighting intensity can not only significantly improve the level of urban traffic management, but also play an important role in energy conservation, emission reduction, environmental protection, etc. Existing intelligent detection methods for road accidents are mostly concentrated on video algorithm detection through road cameras, high-density laser beam sensing, audio multi-feature collision sound detection or other gantry coil sensing.

[0003] The specification of Chinese patent CN202311108250.2 discloses an intelligent street lighting system based on dynamic traffic flow. The system takes into account the changes in traffic flow at night, collects road information and environmental information under the street lights through laser radar, ultrasonic radar, camera, light intensity sensor, PM2.5 sensor, temperature and humidity sensor, flame sensor, and collision detection sensor, and uses cloud servers to control the street lights in the area to perform adaptive brightness control of a single street light and coordinated brightness control of multiple street lights based on the traffic flow per unit time and real-time traffic flow. The present invention can perform real-time street light control according to the actual scene without adding any hardware or software to the passing vehicles, while taking into account the function of adjusting the brightness of the street lights according to the ambient light intensity, thereby achieving the purpose of effectively saving power resources and ensuring traffic safety.

[0004] The existing lighting management method generally adjusts the lighting system uniformly according to factors such as night time, weather conditions, and peak traffic flow time. This method has low adjustment flexibility. Even if there is adjustment based on night traffic flow, the current road lighting is adjusted based on the existing current road traffic, which makes it difficult to achieve the effect of pre-response. Summary of the invention

[0005] In view of the above-mentioned prior art, the technical problem to be solved by the present invention is how to achieve the effect of predicting the road traffic flow and pre-adjusting the lighting.

[0006] To solve the above problems, the present invention provides a smart city lighting management system based on traffic flow, including an objective management system and a subjective management system. The objective management system includes a video monitoring module, a lane flow analysis module, a prejudgment comparison module, a pre-adjustment module, an instant adjustment module, a historical flow library, a flow grade library and a lighting grade library. The video monitoring module is used to control the video monitoring equipment above the road to collect images of the required area. The historical flow library stores the average vehicle flow data passing through a certain road in multiple historical time periods. The flow grade library stores multiple flow grade data from small to large, and different flow grades correspond to different vehicle flow ranges. The lighting grade library stores multiple lighting grade data corresponding to different flow grades.

[0007] The subjective management system includes a vehicle identification module, a lighting feedback module and a subjective adjustment module. The vehicle identification module is used to identify license plate information. The lighting feedback module is used to send feedback information about road lighting conditions to mobile terminals and receive feedback data from mobile terminals. The pre-adjustment module, the real-time adjustment module and the subjective adjustment module are all connected to the urban lighting system.

[0008] The method for using the smart city lighting management system based on traffic flow includes the following steps:

[0009] S1, traffic prediction: collect traffic image information on road D1 through video monitoring equipment, analyze the traffic flow on different lanes on road D1, and predict the next road D2 that the vehicle is about to enter based on the traffic direction of the lane;

[0010] By integrating the vehicle analysis data on multiple roads D1 related to road D2, it is predicted that the traffic volume to be generated on road D2 is the predicted value h;

[0011] S2. Predictive adjustment:

[0012] S2-1, retrieve the average traffic flow data of road D2 in the same historical time period, compare it with the predicted value h, and obtain the difference Z;

[0013] S2-2, when the difference Z is within the preset range A, the lighting intensity on the road D2 is adjusted to a corresponding level in advance according to the flow level of the predicted value h; conversely, when the difference Z exceeds the preset range A, the lighting intensity on the road D2 is adjusted to a corresponding level in advance according to the flow level of the historical average flow data;

[0014] S3, Subjective Adjustment:

[0015] S3-1, according to the vehicle image information obtained in step S1, identify part of the license plate information therein, then send feedback survey information on the lighting conditions of road D2 to the mobile terminal of the corresponding driver, and analyze the driver feedback data collected within time T to obtain feedback results;

[0016] S3-2. When the predicted value h' of the traffic flow on the road D2 is at the same traffic flow level as the predicted value h, the lighting intensity on the road D2 is first adjusted in a predictive manner according to the operation method of step S2, and then the lighting intensity is subjectively adjusted based on the adjustment result and the feedback from the driver.

[0017] As a further supplement to the present application, the specific methods of subjective adjustment in step S3-2 include the following:

[0018] When the driver's feedback result is that the road lighting is appropriate, the result of the predictive adjustment remains unchanged;

[0019] When the driver's feedback result is to suggest increasing the lighting, an additional lighting level is added based on the predictive adjustment result;

[0020] When the driver's feedback result is a suggestion to lower the lighting, the lighting level is reduced by one level based on the predictive adjustment result.

[0021] As a further supplement to this application, while performing step S2, the following operations are also performed:

[0022] On-site adjustment: According to the traffic flow on different lanes on the road D1 obtained by the analysis in step S1, the total vehicle flow data on the road D1 is obtained, and the lighting intensity on the road D1 is adjusted to a corresponding level according to the flow level of the total vehicle flow.

[0023] As a further supplement to the present application, when the difference between the predicted value of the traffic flow on road D2 and the corresponding historical average traffic flow data exceeds a preset range A for a continuous period of time, an abnormal traffic flow warning is remotely issued to the traffic management system.

[0024] As another improvement of the present application, the present application also includes a multi-factor adjustment system, which includes an environmental analysis module, an accident analysis module and a multi-factor adjustment module. The environmental analysis module is connected to the video surveillance equipment, and the multi-factor adjustment module is also connected to the urban lighting system.

[0025] The smart city lighting management system based on traffic flow, and the method of using the same further includes the following steps:

[0026] Step S4, regularly collect images of other environmental areas from a non-road perspective, and compare them with historical images collected at the same time, the same perspective and under normal weather conditions to determine environmental visibility;

[0027] When the environmental visibility is within the safe range, no other operation is performed. When the environmental visibility is lower than the safe range, after completing step S3-2, an illumination level is increased based on the subjective adjustment result.

[0028] As another improvement supplement of the present application, in step S1, when analyzing the traffic image information, when it is analyzed that there is a possibility of an accident on road D1, the traffic flow analysis of road D1 is stopped, and the lighting intensity on road D1 and other nearby roads is directly adjusted to the highest level.

[0029] To summarize, the present application collects road traffic image information and analyzes the traffic flow of each lane of the road. According to the lane traffic direction, the application predicts the next road that the vehicle is about to enter, and then obtains the traffic flow that is about to be generated on the next road, so as to achieve corresponding adjustment of the lighting intensity of the next road in advance before the traffic arrives. Compared with the prior art method of adjusting the lighting of roads with existing traffic flow, the present application better ensures traffic safety through the objective adjustment process of traffic flow prediction and advance adjustment. In addition, the present application also regularly conducts lighting opinion surveys on drivers who have just passed the road. According to the feedback data from the personnel, based on the above objective adjustment results, the road lighting intensity is subjectively adjusted, such as enhanced, weakened or unchanged, so that the lighting intensity is more adapted to actual traffic needs, thereby further improving traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a system diagram of the first implementation mode of the present application;

[0031] Figure 2 The process of adjusting road lighting in the first embodiment of this application Figure 1 ;

[0032] Figure 3 The process of adjusting road lighting in the first embodiment of this application Figure 1 ;

[0033] Figure 4 This is a system diagram of the second implementation mode of the present application;

[0034] Figure 5 The process of adjusting road lighting in the second embodiment of this application Figure 1 ;

[0035] Figure 6The process of adjusting road lighting in the second embodiment of this application Figure 2 . DETAILED DESCRIPTION

[0036] The following describes two implementation modes of the present application in detail with reference to the accompanying drawings.

[0037] The first implementation method:

[0038] The present invention provides a smart city lighting management system based on traffic flow, please refer to Figure 1 , including objective management system and subjective management system.

[0039] The objective management system includes a video surveillance module, a lane flow analysis module, a prediction comparison module, a pre-adjustment module, an instant adjustment module, a historical flow library, a flow grade library and a lighting grade library. The video surveillance module is used to control the video surveillance equipment above the road to collect images of the required area. The historical flow library stores the average vehicle flow data passing through a certain road in multiple historical time periods. The flow grade library stores multiple flow grade data from small to large, and different flow grades correspond to different vehicle flow ranges. The lighting grade library stores multiple lighting grade data corresponding to different flow grades.

[0040] Specific instructions on the flow level library and the lighting level library: Assume that the flow level library stores flow level data from small to large, which are L1, L2, L3...Lm, the vehicle flow range corresponding to L1 is La-Lb (La<Lb, and this range does not include Lb), the vehicle flow range corresponding to L2 is Lb-Lc (Lb<Lc, and this range does not include Lc), and the vehicle flow range corresponding to L3 is Ld-Le (Ld<Le, and this range does not include Le). By analogy, the larger the range area to which the vehicle flow belongs, the larger the corresponding flow level. The lighting level data stored in the lighting level library are G1, G2, G3...Gm from small to large, G1 corresponds to L1, G2 corresponds to L2, G3 corresponds to L3, and so on, Gm corresponds to Lm. For example, when it is confirmed that the flow level corresponding to a certain vehicle flow is L3, without considering other factors, the lighting level of the lighting system can be adjusted to G3 to make the lighting intensity adapt to the vehicle flow situation, which can effectively ensure the lighting needs and reduce energy waste.

[0041] The subjective management system includes a vehicle identification module, a lighting feedback module and a subjective adjustment module. The vehicle identification module is used to identify license plate information. The lighting feedback module is used to send feedback information about road lighting conditions to the mobile terminal and receive feedback data from the mobile terminal. The pre-adjustment module, the real-time adjustment module and the subjective adjustment module are all connected to the urban lighting system, that is, all three can adjust the urban lighting system.

[0042] Combination Figure 2 and Figure 3 As shown, the smart city lighting management system based on traffic flow, and its use method includes the following steps:

[0043] S1, traffic prediction: collect traffic image information on road D1 through video monitoring equipment, use lane traffic analysis module to analyze the traffic flow on different lanes on road D1, and predict the next road D2 that the vehicle is about to enter based on the traffic direction of the lane;

[0044] The prediction comparison module integrates the vehicle analysis data on multiple roads D1 related to the road D2, and predicts that the traffic volume that will be generated on the road D2 is the prediction value h.

[0045] S2. Predictive adjustment:

[0046] S2-1, the prediction comparison module retrieves the average traffic flow data of the road D2 in the same historical time period, compares it with the predicted value h, and obtains the difference Z;

[0047] S2-2, when the difference Z is within the preset range A, the pre-adjustment module adjusts the lighting intensity on the road D2 to a corresponding level in advance according to the flow level where the predicted value h is located; conversely, when the difference Z exceeds the preset range A, the lighting intensity on the road D2 is adjusted to a corresponding level in advance according to the flow level where the historical average flow data is located;

[0048] Supplementary explanation: When the difference Z exceeds the preset range A, it indicates that the predicted value h is significantly different from the average traffic flow data of road D2 in the same historical time period. The predicted value h may be accurate, but there is also the possibility that the predicted value h is inaccurate due to equipment failure. The historical average traffic flow data is obtained through sufficient data collection and analysis. Compared with the predicted value h obtained by this real-time measurement, it is more accurate. Therefore, in order to effectively avoid improper lighting intensity adjustment due to inaccurate predictions, which affects traffic safety, the pre-adjustment module ignores the predicted value h and adjusts the lighting intensity on road D2 to the corresponding level in advance according to the traffic level of the historical average traffic data.

[0049] S3, Subjective Adjustment:

[0050] S3-1, according to the vehicle image information obtained in step S1, use the vehicle recognition module to recognize part of the license plate information therein, and then send feedback survey information on the lighting conditions of road D2 to the mobile terminal of the corresponding driver through the lighting feedback module, asking whether the lighting brightness needs to be increased or decreased, and analyzing the driver feedback data collected within time T to obtain feedback results;

[0051] S3-2. When the predicted value h' of the traffic flow on the road D2 is at the same traffic flow level as the predicted value h, the lighting intensity on the road D2 is first adjusted in a predictive manner according to the operation method of step S2, and then based on this adjustment result, the subjective adjustment module subjectively adjusts the lighting intensity according to the feedback from the driver.

[0052] Among them, combined Figure 2 As shown, the specific methods of subjective adjustment in step S3-2 include the following:

[0053] When the driver's feedback result is that the road lighting is appropriate, the result of the predictive adjustment remains unchanged;

[0054] When the driver's feedback result is to suggest increasing the lighting, an additional lighting level is added based on the predictive adjustment result;

[0055] When the driver's feedback result is a suggestion to lower the lighting, the lighting level is reduced by one level based on the predictive adjustment result.

[0056] See also Figure 2 , while performing step S2, also perform the following operations:

[0057] On-site adjustment: Based on the traffic flow on different lanes on road D1 obtained by analyzing step S1, the total vehicle flow data on road D1 is obtained, and the real-time adjustment module adjusts the lighting intensity on road D1 to a corresponding level according to the flow level of the total vehicle flow.

[0058] In addition, when the difference between the predicted value of the traffic flow of road D2 and the corresponding historical average traffic flow data exceeds the preset range A for a continuous period of time, that is, the difference between the two continues to be large and there is a continuous large difference from the previous traffic flow conditions, then a traffic abnormality alert is remotely sent to the traffic management system, so that personnel can conduct further investigations on the traffic conditions of this road and its surrounding roads to check whether the continuous abnormal traffic flow is caused by traffic accidents or other factors, thereby further improving traffic safety and traffic efficiency.

[0059] Second implementation method:

[0060] This implementation mode adds the following contents based on implementation mode 1: Figure 4 The present application also includes a multi-factor adjustment system, which includes an environmental analysis module, an accident analysis module and a multi-factor adjustment module. The environmental analysis module is connected to the video surveillance equipment, and the multi-factor adjustment module is also connected to the urban lighting system.

[0061] See also Figure 5 , the smart city lighting management system based on traffic flow, and its use method also includes the following steps:

[0062] Step S4, using video surveillance equipment to regularly collect images of other environmental areas from non-road perspectives, and using an environmental analysis module to compare the used images with historical images collected at the same time, the same perspective and under normal weather conditions to determine environmental visibility;

[0063] When the environmental visibility is within the safe range, no other operations are performed. When the environmental visibility is lower than the safe range, after completing step S3-2, based on the subjective adjustment results, the lighting system is adjusted for safety through the multi-factor adjustment module to increase a lighting level.

[0064] See also Figure 6 In step S1, when analyzing the traffic image information, if it is found that there is a possibility of an accident on road D1, the traffic flow analysis on road D1 is stopped, and the lighting intensity on road D1 and other roads nearby is directly adjusted to the highest level. In this way, when the driver is driving towards the accident section, he can clearly observe the people and vehicles gathered in the accident area from a distance, slow down in advance, and effectively reduce the occurrence of secondary accidents.

[0065] In view of current practical needs, the above-mentioned implementation mode adopted in this application is not limited to the scope of protection. Various changes made within the knowledge scope of technical personnel in this field without departing from the concept of this application still fall within the scope of protection of the present invention.

Claims

1. Smart city lighting management system based on traffic flow, characterized by: It includes an objective management system and a subjective management system. The objective management system includes a video monitoring module, a lane flow analysis module, a prejudgment comparison module, a pre-adjustment module, an instant adjustment module, a historical flow library, a flow level library and a lighting level library. The video monitoring module is used to control the video monitoring equipment above the road to collect images of the required area. The historical flow library stores the average vehicle flow data passing through a certain road in multiple historical time periods. The flow level library stores multiple flow level data from small to large, and different flow levels correspond to different vehicle flow ranges. The lighting level library stores multiple lighting level data corresponding to different flow levels. The subjective management system includes a vehicle identification module, a lighting feedback module and a subjective adjustment module. The vehicle identification module is used to identify license plate information. The lighting feedback module is used to send feedback information about road lighting conditions to a mobile terminal and receive feedback data from the mobile terminal. The pre-adjustment module, the real-time adjustment module and the subjective adjustment module are all connected to the city lighting system. The method for using the above-mentioned smart city lighting management system based on traffic flow includes the following steps: S1, traffic prediction: collect traffic image information on road D1 through video monitoring equipment, analyze the traffic flow on different lanes on road D1, and predict the next road D2 that the vehicle is about to enter based on the traffic direction of the lane; By integrating the vehicle analysis data on multiple roads D1 related to road D2, it is predicted that the traffic volume to be generated on road D2 is the predicted value h; S2. Predictive adjustment: S2-1, retrieve the average traffic flow data of road D2 in the same historical time period, compare it with the predicted value h, and obtain the difference Z; S2-2, when the difference Z is within the preset range A, the lighting intensity on the road D2 is adjusted to a corresponding level in advance according to the flow level of the predicted value h; conversely, when the difference Z exceeds the preset range A, the lighting intensity on the road D2 is adjusted to a corresponding level in advance according to the flow level of the historical average flow data; S3, Subjective Adjustment: S3-1, according to the vehicle image information obtained in step S1, identify part of the license plate information therein, then send feedback survey information on the lighting conditions of road D2 to the mobile terminal of the corresponding driver, and analyze the driver feedback data collected within time T to obtain feedback results; S3-2. When the predicted value h' of the traffic flow on the road D2 is at the same traffic flow level as the predicted value h, the lighting intensity on the road D2 is first adjusted in a predictive manner according to the operation method of step S2, and then the lighting intensity is subjectively adjusted based on the adjustment result and the feedback from the driver.

2. The traffic flow-based smart city lighting management system according to claim 1 is characterized in that: The specific methods of subjective adjustment in step S3-2 include the following: When the driver's feedback result is that the road lighting is appropriate, the result of the predictive adjustment remains unchanged; When the driver's feedback result is to suggest increasing the lighting, an additional lighting level is added based on the predictive adjustment result; When the driver's feedback result is a suggestion to lower the lighting, the lighting level is reduced by one level based on the predictive adjustment result.

3. The traffic flow-based smart city lighting management system according to claim 1 is characterized in that: While performing step S2, the following operations are also performed: On-site adjustment: According to the traffic flow on different lanes on the road D1 obtained by the analysis in step S1, the total vehicle flow data on the road D1 is obtained, and the lighting intensity on the road D1 is adjusted to a corresponding level according to the flow level of the total vehicle flow.

4. The traffic flow-based smart city lighting management system according to claim 1 is characterized in that: When the difference between the predicted value of the traffic flow on road D2 and the corresponding historical average traffic flow data exceeds the preset range A for a continuous period of time, a traffic abnormality alert is remotely sent to the traffic management system.

5. The traffic flow-based smart city lighting management system according to claim 1 is characterized in that: It also includes a multi-factor adjustment system, which includes an environmental analysis module, an accident analysis module and a multi-factor adjustment module. The environmental analysis module is connected to the video monitoring equipment, and the multi-factor adjustment module is also connected to the city lighting system.

6. The traffic flow-based smart city lighting management system according to claim 5 is characterized in that: The method of using the same also includes the following steps: Step S4, regularly collect images of other environmental areas from a non-road perspective, and compare them with historical images collected at the same time, the same perspective and under normal weather conditions to determine environmental visibility; When the environmental visibility is within the safe range, no other operation is performed. When the environmental visibility is lower than the safe range, after completing step S3-2, an illumination level is increased based on the subjective adjustment result.

7. The traffic flow-based smart city lighting management system according to claim 5 is characterized in that: In step S1, when analyzing the traffic image information, if it is found that there is a possibility of an accident on the road D1, the traffic flow analysis on the road D1 is stopped, and the lighting intensity on the road D1 and other roads nearby is directly adjusted to the highest level.

Images