A method and system for intelligent management and maintenance of transportation infrastructure based on the Internet of Things

Abstract

The present invention relates to the field of data processing technology, and specifically to an intelligent management and maintenance method and system for traffic infrastructure based on the Internet of Things, including: collecting the distance from the monitoring camera to each special terrain, the monitoring records of the road section where it is located, and the street lamp power data; obtaining the daily weather influencing factors according to the daily weather influencing factors; obtaining the geographical location importance of the monitoring camera according to the distance between the monitoring camera and the special terrain and the traffic conditions of the road section, thereby obtaining the necessity of daily management and maintenance of the monitoring camera in combination with the weather influencing factors; obtaining the nighttime fuzziness of the monitoring camera through the difference between the monitoring camera traffic flow data and the induction traffic flow data, as well as the influence of the street lamp power data, and calculating the real-time management and maintenance of the monitoring camera in combination with the necessity of management and maintenance. The present invention manages and maintains the traffic infrastructure intelligently by analyzing the environment and usage status of the traffic infrastructure.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent management and maintenance method and system for transportation infrastructure based on the Internet of Things. Background Art

[0002] With the acceleration of urbanization, the management and maintenance of transportation infrastructure has become an important part of urban management. At the same time, with the rapid development of Internet of Things technology, transportation infrastructure transmits collected data to the Internet through Internet of Things technology for analysis and scheduling, realizing comprehensive detection and intelligent management and maintenance analysis of urban transportation infrastructure.

[0003] Among them, road surveillance cameras are an important source of data for providing information to the traffic management system. However, the maintenance method for road surveillance cameras mainly relies on regular manual inspections and irregular special inspections. Due to the limitations of road environment and human resources, real-time monitoring and rapid response cannot be achieved, resulting in blind spots in the collected monitoring data and information loss caused by environmental interference. In the maintenance of surveillance cameras, the power of the surveillance camera's fill light equipment is mainly adjusted according to different environmental factors. However, due to the influence of weather, seasons and road vehicles, even if the power is adjusted manually frequently, it cannot cope with the complex environmental changes on the road, resulting in poor quality of the information collected by the surveillance camera. Summary of the invention

[0004] The present invention provides an intelligent management and maintenance method and system for traffic infrastructure based on the Internet of Things to solve the existing problems.

[0005] The present invention provides an intelligent management and maintenance method and system for transportation infrastructure based on the Internet of Things, which adopts the following technical solutions:

[0006] An embodiment of the present invention provides an intelligent management and maintenance method for transportation infrastructure based on the Internet of Things, the method comprising the following steps:

[0007] Collect the distance from the surveillance camera to each special terrain, the daily surveillance records and street lamp power data of the road section where the surveillance camera is located, and obtain the traffic flow data, sensor traffic flow data and congestion times of the road section where the surveillance camera is located at every moment of the day according to the surveillance records; obtain the daily weather influencing factors according to the daily weather influencing factors;

[0008] According to the distance between the surveillance camera and the special terrain, as well as the traffic flow data and road traffic conditions at each time of the day, the importance of the surveillance camera's geographical location is obtained; according to the daily weather influencing factors and the importance of the surveillance camera's geographical location, the necessity of daily maintenance of the surveillance camera is obtained; through the difference between the surveillance camera's traffic flow data and the sensor traffic flow data, as well as the impact of street lamp power data on the surveillance image, the night fuzziness of the surveillance camera is obtained;

[0009] According to the necessity of daily maintenance of surveillance cameras and the blurriness at night, the real-time performance of daily maintenance of surveillance cameras is obtained; and the surveillance cameras are maintained according to the real-time performance of daily maintenance of surveillance cameras.

[0010] Furthermore, the importance of the geographical location of the surveillance camera is obtained according to the distance between the surveillance camera and the special terrain, as well as the traffic flow data and road traffic conditions at each time of the day, including the following specific steps:

[0011]

[0012] In the formula, JB r represents the geographical location importance of the rth surveillance camera; D[r,q] represents the location feature value of the rth surveillance camera; n represents all days; g r,i represents the traffic flow data of the rth surveillance camera on the i-th day; G r Represents the sum of the number of congestion times at each time of day on the road section where the rth surveillance camera is located.

[0013] Furthermore, the specific steps of obtaining the position feature value are as follows:

[0014] The Euclidean distance between the r-th surveillance camera and the q-th special terrain is recorded as the position feature value of the r-th surveillance camera.

[0015] Furthermore, the specific method of obtaining the traffic flow data of the i-th day is as follows:

[0016] The sum of the traffic flow data of the r-th surveillance camera at each moment on the i-th day is recorded as the traffic flow data of the r-th surveillance camera on the i-th day.

[0017] Furthermore, the necessity of daily maintenance of the surveillance camera is obtained according to the daily weather influencing factors and the importance of the geographical location of the surveillance camera, and the specific steps include the following:

[0018] The product of the geographical location importance of the r-th surveillance camera and the weather impact factor of the j-th day is recorded as the maintenance necessity of the r-th surveillance camera on the j-th day.

[0019] Furthermore, the nighttime blurriness of the surveillance camera is obtained by using the difference between the surveillance camera traffic flow data and the induction traffic flow data, and the influence of the street lamp power data on the surveillance image, and the specific steps include the following:

[0020]

[0021] In the formula, JL r represents the nighttime blur of the rth surveillance camera, E r represents the mean square error of the vehicle flow of the rth surveillance camera; P m,k It represents the street lamp power data of the kth street lamp at the mth time; N represents the number of street lamps, and M represents all the moments of the monitoring screen.

[0022] Furthermore, the specific method for obtaining the mean square error of the vehicle flow is as follows:

[0023] The mean square error between the traffic flow data of each surveillance camera at all times in the monitoring record and the sensed traffic flow data is recorded as the mean square error of the traffic flow of each surveillance camera.

[0024] Furthermore, the real-time performance of daily maintenance of the surveillance camera is obtained according to the necessity of daily maintenance of the surveillance camera and the blurriness at night, and the specific steps include the following:

[0025] JM r =norm(JH r,j ×JL r )

[0026] In the formula, JM r represents the real-time maintenance of the rth surveillance camera on the jth day, JH r,j represents the necessity of maintenance of the rth surveillance camera on the jth day, JL r represents the night ambiguity of the rth surveillance camera; norm( ) represents the linear normalization function.

[0027] Furthermore, the real-time maintenance of the surveillance camera according to the daily maintenance of the surveillance camera includes the following specific steps:

[0028] A maintenance judgment threshold is preset. When the real-time maintenance of the r-th surveillance camera on the j-th day is greater than or equal to the maintenance judgment threshold, the power of the lighting compensation device of the r-th surveillance camera is reduced to achieve maintenance.

[0029] The present invention also proposes an intelligent management and maintenance system for transportation infrastructure based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned intelligent management and maintenance method for transportation infrastructure based on the Internet of Things.

[0030] The beneficial effects of the technical solution of the present invention are: collecting the distance from the surveillance camera to each special terrain, the monitoring records of the road section and the street lamp power data, and obtaining the daily weather influencing factors based on the daily weather influencing factors, taking into account the impact of environmental factors on the surveillance camera; obtaining the importance of the geographical location of the surveillance camera based on the distance between the surveillance camera and the special terrain and the traffic conditions of the road section, and then obtaining the necessity of daily maintenance of the surveillance camera in combination with the weather influencing factors, showing the importance of the location of the surveillance camera; obtaining the night fuzziness of the surveillance camera through the difference between the surveillance camera traffic data and the sensor traffic data, as well as the influence of the street lamp power data, and calculating the real-time maintenance of the surveillance camera every day in combination with the necessity of maintenance, so as to perform intelligent maintenance on the surveillance camera, thereby improving the timeliness of maintenance of the surveillance camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 The present invention is a flowchart of the steps of an intelligent management and maintenance method for transportation infrastructure based on the Internet of Things. DETAILED DESCRIPTION

[0033] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of an intelligent management and maintenance method and system for transportation infrastructure based on the Internet of Things proposed by the present invention, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0034] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0035] The specific scheme of the intelligent management and maintenance method and system of transportation infrastructure based on the Internet of Things provided by the present invention is described in detail below with reference to the accompanying drawings.

[0036] See also Figure 1 , which shows a flowchart of a method for intelligent management and maintenance of transportation infrastructure based on the Internet of Things provided by an embodiment of the present invention, the method comprising the following steps:

[0037] Step S001, collect monitoring records of the road section where the monitoring camera is located, the distance to each special terrain and the street lamp power data, obtain the traffic flow data, induced traffic flow data and congestion times of the road section where the monitoring camera is located at each time of the day according to the monitoring records, and obtain the daily weather influencing factors according to the daily weather influencing factors.

[0038] The purpose of this embodiment is to analyze the environment and usage status of traffic infrastructure, so as to perform intelligent management and maintenance of traffic infrastructure. In this embodiment, the monitoring cameras on the highway are used as the maintenance objects to analyze the traffic infrastructure. The monitoring cameras in the traffic infrastructure generally have their own light compensation measures, such as infrared light compensation or night vision function. When the maintenance demand is high, the contrast of the monitoring picture can be increased by adjusting the power of the camera's fill light device, that is, reducing the power of the light compensation device, so as to ensure that the vehicle condition of the road section is clearly identified and monitored without changing the power of the road street lamp; therefore, the longitude and latitude coordinates of each monitoring camera and the longitude and latitude coordinates of the special terrain marked by the map software are obtained through the map software, and the Euclidean distance from each monitoring camera to each special terrain is obtained through the longitude and latitude coordinates of the monitoring camera and the special terrain and the scale. The special terrain in this embodiment is such as sharp turns, continuous turns, continuous downhill, etc.; the monitoring records of each moment of each day are collected through the Internet of Things technology. In this embodiment, the data collected between each moment and the next moment are used as real-time data at each moment. In this embodiment, every three minutes is described as a moment, and other embodiments can set other values, which are not specifically limited in this embodiment.

[0039] Since surveillance cameras are usually installed in areas with poor road conditions and prone to emergencies, which usually lead to traffic congestion, the historical records of each surveillance camera are queried to obtain the number of congestion times at each time of each day on the road section where each surveillance camera is located, and the number of vehicles passing at each time of each day is counted through the surveillance images taken by the surveillance cameras to obtain the traffic flow data at each time of each day on the road section where each surveillance camera is located; since the vehicles photographed by the surveillance cameras may be affected by weather, obstructions, etc., resulting in inaccurate traffic flow data obtained by the surveillance cameras, induction sensors are installed on the road surface where each surveillance camera is located, and a record is recorded every time a vehicle passes by to obtain the induction traffic flow data at each time of each day on the road section where each surveillance camera is located; at the same time, the power consumption of the street lights on the road section where each surveillance camera is located is monitored to obtain the street light power data at each time of each day on the road section where each surveillance camera is located.

[0040] Since the weather is different every day, it has a certain impact on the use of surveillance cameras. Therefore, the key features of various weather influencing factors are integrated through the neural network method to obtain the weather influencing factor; specifically, the key features of the weather influencing factors within a day are input into the trained neural network to obtain the weather influencing factor δ of the day; the neural network used in this embodiment is YOLOv3, and the method for obtaining the data set for training the neural network is: collecting the key features of weather influencing factors such as temperature, humidity, rainfall, wind speed, etc. of each day, and scoring the key features of weather influencing factors by manual scoring. The higher the score, the greater the degree of weather influence and the poor weather quality; the key features of weather influencing factors and their corresponding scoring values ​​constitute a data set; the neural network is trained using the data set, and the loss function used in the training process is the cross entropy function; the specific training process is a well-known content of the neural network, and the specific training process is not repeated in this embodiment.

[0041] Step S002: Obtain the geographical location importance of each surveillance camera based on the terrain conditions and road traffic conditions at the location of the surveillance camera.

[0042] It should be noted that the situation of the road section where the surveillance camera is located affects the importance of monitoring this section. Different sections may have different terrain conditions. The more special the terrain conditions, the more important the existence of the surveillance camera. When the surveillance camera is closer to the special terrain, the more important the surveillance camera is and the more important it is to maintain. At the same time, the more traffic on the road section, the more likely it is to have traffic congestion, and the more important this section is. The occurrence of traffic accidents also has a certain impact on the importance of the road section, and thus the more important it is to maintain the surveillance cameras on these sections.

[0043] Specifically, the calculation method of the geographical location importance of the rth surveillance camera is:

[0044]

[0045] In the formula, JB r represents the geographical location importance of the r-th surveillance camera; D[r,q] represents the Euclidean distance between the r-th surveillance camera and the q-th special terrain; n represents the number of days; g r,i represents the traffic flow data of the r-th surveillance camera on the i-th day, and the traffic flow data of the i-th day is obtained by recording the sum of the traffic flow data of the r-th surveillance camera at each moment on the i-th day as the traffic flow data of the r-th surveillance camera on the i-th day; G r It represents the sum of the number of congestion times at each time of each day on the road section where the rth surveillance camera is located; α is a hyperparameter. This embodiment is described as α=0.1 to avoid the surveillance camera being located in the city, which causes the calculation result to be close to 0 and affects the calculation result. Other embodiments may set other values.

[0046] D[r,q] represents the similarity between the r-th surveillance camera and the q-th special terrain. The smaller the value, the more important the r-th surveillance camera is in monitoring the traffic location. It represents the product of the number of traffic accidents and congestion on the road section where the rth surveillance camera is located and the average daily traffic volume of the road section. The larger the product is, the more important the road condition and vehicle condition of the road section are, that is, the more important the surveillance camera is, and the more it needs maintenance.

[0047] Step S003: According to the influence of daily weather factors and the importance of the geographical location of each surveillance camera, the necessity of daily maintenance of each surveillance camera is obtained.

[0048] It should be noted that the necessity of maintenance of traffic infrastructure is not only reflected in the importance of traffic, but also in the weather factor that cannot be ignored. On traffic sections, most of the surveillance cameras are located without shelter and protection. The different weather every day affects the use of surveillance cameras, and also has a certain degree of impact on the maintenance of surveillance cameras. The key features of various weather influencing factors are integrated through the neural network method to obtain the weather influencing factor, and the necessity of surveillance camera maintenance is obtained according to the importance of weather influencing factors and geographical location.

[0049] The calculation method for the maintenance necessity of the rth surveillance camera on the jth day is:

[0050] JH r,j =JB r ×δ j

[0051] In the formula, JH r,j represents the necessity of maintenance of the rth surveillance camera on the jth day; JB r represents the geographical location importance of the rth surveillance camera; δ j Represents the weather impact factor of the jth day.

[0052] JB r ×δ j It represents the product of the geographical location importance of the r-th surveillance camera and the weather impact factor of the j-th day. The larger the product is, the more important the geographical location of the r-th transportation infrastructure is on the j-th day. Combined with the influence of the weather factors of the day, the larger the weather impact factor is, the greater the impact of the weather on the surveillance camera on the j-th day, and the stronger the necessity of maintaining the transportation infrastructure.

[0053] Step S004: Obtain the nighttime fuzziness of each surveillance camera according to the difference between the traffic flow in the surveillance picture of each surveillance camera and the traffic flow monitored by the vehicle detection sensor, as well as the influence of the light on the surveillance picture.

[0054] It should be noted that in the daytime and under good light conditions, the monitoring screen of the road monitoring is clear, the real-time monitoring of the road conditions on the road section is better than at night, and the recognition of road vehicles in the monitoring screen is high; however, at night or in low light conditions, due to the influence of light factors, the monitoring camera may find it difficult to accurately identify and track the target, and the clarity of the road monitoring screen is low. The illumination of light can improve the recognizability and detection accuracy of the vehicle. Therefore, the street light illumination in the night monitoring screen and the lights of the car driving on the road at night will affect the monitoring camera, resulting in overexposure of the monitoring camera, reducing the contrast of the monitoring screen, and making the outline in the monitoring screen unclear. The monitoring camera needs to be adjusted and maintained according to the actual road section conditions. By installing a vehicle detection sensor, the traffic flow of the road section can be accurately monitored, which is more accurate than the traffic flow recognized by the monitoring screen of the monitoring camera. Therefore, the quality of the monitoring screen of the monitoring camera is obtained by comparing the traffic flow of the vehicle detection sensor with the traffic flow in the monitoring screen of the monitoring camera, and the night fuzziness of the monitoring camera is obtained in combination with the street light power.

[0055] Specifically, the mean square error between the traffic flow data of the rth surveillance camera at all times during the monitoring time and the sensed traffic flow data is recorded as the mean square error of the traffic flow of the rth surveillance camera; then the calculation method of the night fuzziness of the rth surveillance camera is:

[0056]

[0057] In the formula, JL r represents the nighttime blur of the rth surveillance camera, Er represents the mean square error of the vehicle flow of the rth surveillance camera; P m,k Represents the street lamp power data of the kth street lamp at the mth time; N represents the number of street lamps, and M represents all times.

[0058] Indicates the average power of each street lamp. The greater the power, the higher the light intensity of the street lamp. This means that when the mean value of the street light illumination of the road section where the rth surveillance camera is located is larger, the illumination intensity of the road section is higher, the possibility of overexposure of the surveillance camera is higher, the contrast of the image in the surveillance video is lower, and the blur at night is higher; when E r The larger the value is, the greater the difference between the traffic flow in the monitoring picture and the traffic flow monitored by the traffic flow sensor is, which means that the monitoring camera is overexposed, resulting in reduced contrast of the monitoring picture and greater blur at night.

[0059] Step S005: According to the necessity of daily maintenance of each surveillance camera and the nighttime fuzziness of each surveillance camera, the real-time maintenance of each surveillance camera is obtained; and the surveillance camera is maintained.

[0060] It should be noted that when weather and geographical location factors have a great impact, the necessity of maintenance is high. At this time, the maintenance and adjustment of the surveillance camera need to be strong. However, in actual situations, the surveillance camera has a higher contrast at night, the surveillance picture quality is high, and the blurriness at night is low. The vehicle condition and road condition can be clearly identified on the road sections at night, which means that the surveillance camera is in good condition and does not need to be maintained in time for the time being. Therefore, the individual surveillance cameras are analyzed through the necessity of maintenance and the blurriness at night to calculate the degree to which the surveillance cameras need timely maintenance.

[0061] Specifically, the calculation method for the real-time maintenance of the rth surveillance camera on the jth day is:

[0062] JM r =norm(JH r,j ×JL r )

[0063] In the formula, JM r represents the real-time maintenance of the rth surveillance camera on the jth day, JH r,j represents the necessity of maintenance of the rth surveillance camera on the jth day, JL r represents the night ambiguity of the rth surveillance camera; norm( ) represents the linear normalization function.

[0064] When JH r,jWhen the value is larger, it means that the weather factors and the geographical location of the r-th surveillance camera on the j-th day have a greater impact, the necessity of the r-th surveillance camera on the j-th day is greater, the degree of timely maintenance is greater, and the real-time nature of maintenance is greater; when JL r The larger the value, the greater the night blur of the e-th surveillance camera, the worse the quality of the surveillance image, the greater the degree of maintenance required, and the more timely the maintenance.

[0065] A maintenance judgment threshold is preset. When the real-time maintenance of the r-th surveillance camera on the j-th day is greater than or equal to the maintenance judgment threshold, it indicates that the r-th surveillance camera needs timely maintenance. By reducing the power of the surveillance camera light compensation device, the contrast of the monitoring image is increased to ensure that the vehicle condition on the road section can be more clearly identified and monitored without changing the power of the road street lights. When the real-time maintenance of the r-th surveillance camera on the j-th day is less than or equal to the maintenance judgment threshold, the r-th surveillance camera does not need to be maintained temporarily. The maintenance judgment threshold preset in this embodiment is 0.8. Other embodiments may set other values, which are not specifically limited in this embodiment.

[0066] So far, the present invention is completed.

[0067] The present invention also provides an intelligent management and maintenance system for transportation infrastructure based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned intelligent management and maintenance method for transportation infrastructure based on the Internet of Things.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent management and maintenance method for transportation infrastructure based on the Internet of Things, characterized in that: The method comprises the following steps: Collect the distance from the surveillance camera to each special terrain, the daily surveillance records and street lamp power data of the road section where the surveillance camera is located, and obtain the traffic flow data, sensor traffic flow data and congestion times of the road section where the surveillance camera is located at every moment of the day according to the surveillance records; obtain the daily weather influencing factors according to the daily weather influencing factors; According to the distance between the surveillance camera and the special terrain, as well as the traffic flow data and road traffic conditions at each time of the day, the importance of the surveillance camera's geographical location is obtained; according to the daily weather influencing factors and the importance of the surveillance camera's geographical location, the necessity of daily maintenance of the surveillance camera is obtained; through the difference between the surveillance camera's traffic flow data and the sensor traffic flow data, as well as the impact of street lamp power data on the surveillance image, the night fuzziness of the surveillance camera is obtained; According to the necessity of daily maintenance of surveillance cameras and the blurriness at night, the real-time maintenance of surveillance cameras is obtained; the surveillance cameras are maintained according to the real-time maintenance of surveillance cameras; The specific steps of obtaining the geographical location importance of the surveillance camera according to the distance between the surveillance camera and the special terrain, as well as the traffic flow data and road traffic conditions at each time of the day, include the following: In the formula, JB r represents the geographical location importance of the rth surveillance camera; D[r,q] represents the location feature value of the rth surveillance camera; n represents all days; g r,i represents the traffic flow data of the rth surveillance camera on the i-th day; G r represents the sum of the number of congestion times at each time of the day on the road section where the rth surveillance camera is located; The necessity of daily maintenance of surveillance cameras is obtained according to the daily weather influencing factors and the importance of the geographical location of the surveillance cameras, and the specific steps include the following: The product of the geographical location importance of the r-th surveillance camera and the weather impact factor of the j-th day is recorded as the maintenance necessity of the r-th surveillance camera on the j-th day; The nighttime blurriness of the surveillance camera is obtained by using the difference between the surveillance camera traffic flow data and the induction traffic flow data, as well as the influence of the street lamp power data on the surveillance image, and the specific steps include the following: In the formula, JL r represents the nighttime blur of the rth surveillance camera, E r represents the mean square error of the vehicle flow of the rth surveillance camera; P m,k represents the street lamp power data of the kth street lamp at the mth time; N represents the number of street lamps, and M represents all the moments of the monitoring screen; The real-time performance of daily maintenance of surveillance cameras is obtained according to the necessity of daily maintenance of surveillance cameras and the blurriness at night, and the specific steps include the following: JM r =norm(JH r,j ×JL r ) In the formula, JM r represents the real-time maintenance of the rth surveillance camera on the jth day, JH r,j represents the necessity of maintenance of the rth surveillance camera on the jth day, JL r represents the night fuzziness of the rth surveillance camera; norm() represents the linear normalization function.

2. According to claim 1, a method for intelligent management and maintenance of transportation infrastructure based on the Internet of Things is characterized in that: The specific steps for obtaining the position feature value are as follows: The Euclidean distance between the r-th surveillance camera and the q-th special terrain is recorded as the position feature value of the r-th surveillance camera.

3. According to the method of intelligent management and maintenance of transportation infrastructure based on the Internet of Things in claim 1, it is characterized in that: The specific method of obtaining the traffic flow data of the i-th day is as follows: The sum of the traffic flow data of the r-th surveillance camera at each moment on the i-th day is recorded as the traffic flow data of the r-th surveillance camera on the i-th day.

4. According to the method of intelligent management and maintenance of transportation infrastructure based on the Internet of Things in claim 1, it is characterized in that: The specific method for obtaining the mean square error of the vehicle flow is as follows: The mean square error between the traffic flow data of each surveillance camera at all times in the monitoring record and the sensed traffic flow data is recorded as the mean square error of the traffic flow of each surveillance camera.

5. According to the method of intelligent management and maintenance of transportation infrastructure based on the Internet of Things in claim 1, it is characterized in that: The specific steps of maintaining the surveillance camera according to the real-time daily maintenance of the surveillance camera are as follows: A maintenance judgment threshold is preset. When the real-time maintenance of the r-th surveillance camera on the j-th day is greater than or equal to the maintenance judgment threshold, the power of the lighting compensation device of the r-th surveillance camera is reduced to achieve maintenance.

6. An intelligent management and maintenance system for transportation infrastructure based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by the processor, the steps of the intelligent management and maintenance method of transportation infrastructure based on the Internet of Things as described in any one of claims 1 to 5 are implemented.

Images