A method for monitoring traffic flow on municipal roads based on the Internet of Things

By setting up detection nodes in municipal roads, extracting vehicle characteristics and judging traffic flow, the problem of incomplete monitoring process in the existing technology is solved, and more accurate traffic information acquisition and road regulation is achieved, which alleviates the problem of inaccurate traffic flow. Road pressure.

CN118587912BActive Publication Date: 2024-11-05SHENZHEN RUNHYUAN CONSTR ENG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410710970.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-04
Publication Date
2024-11-05
Estimated Expiration
2044-06-04

Smart Images

  • Figure CN118587912B_ABST
    Figure CN118587912B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of municipal road traffic flow monitoring, and in particular to a municipal road traffic flow monitoring method based on the Internet of Things, comprising setting detection nodes in a municipal road to be monitored according to design requirements, collecting image information, extracting vehicle features from pre-processed image information to determine the number of vehicles; judging whether the traffic flow of each detection node meets the standard based on the number of vehicles, and making a secondary judgment based on the traffic flow corresponding to the upstream and downstream detection nodes, or determining the reason why the traffic flow does not meet the standard based on the average interval between the characteristics of each vehicle; adjusting the corresponding parameters based on the determined reasons or diverting vehicles to the road section where congestion has occurred to relieve road pressure.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of municipal road vehicle flow monitoring, and in particular to a municipal road vehicle flow monitoring method based on the Internet of Things. Background Art

[0002] By deploying sensors on roads, traffic lights, and vehicles, the Internet of Things technology has achieved real-time monitoring and data collection of urban traffic, and has gathered traffic information through high-tech to optimize the management of traffic flow. Through big data analysis, it can predict traffic flow, create accurate data about real-time traffic congestion, and direct vehicles using navigation to less crowded routes. This comprehensive application enables the Internet of Things technology to play an important role in smart city traffic management.

[0003] Chinese patent publication number: CN117275234A discloses an urban road IoT data management platform, which collects the traffic flow values ​​at multiple predetermined time points within a predetermined time period by smart street lamps deployed on predetermined roads; arranges the traffic flow values ​​at the multiple predetermined time points according to the time dimension as a traffic flow time series input vector; extracts the time series features of the traffic flow time series input vector to obtain the traffic flow time series features; and determines the congestion level label of the predetermined road based on the traffic flow time series features. In this way, the congestion level of the predetermined road can be intelligently judged, providing valuable information for urban management and services, and helping to realize the monitoring, prediction and optimization of traffic congestion levels.

[0004] It can be seen that the urban road Internet of Things data management platform has the following problems: although the data management platform can determine the congestion level label of the predetermined road based on the time series characteristics of the vehicle flow, intelligently judge the congestion level of the predetermined road, and realize the monitoring, prediction and optimization of the traffic congestion level, the platform cannot adjust the road sections that have already been congested, and the monitoring process of the urban road traffic conditions is not monitored, so it is impossible to determine the accuracy of the obtained traffic information, and thus it is impossible to determine whether the results output based on the obtained traffic information are accurate. Summary of the invention

[0005] To this end, the present invention provides a municipal road traffic flow monitoring method based on the Internet of Things, which is used to overcome the problems in the prior art that congested road sections cannot be adjusted, and the monitoring process of urban road traffic conditions is not monitored, and the accuracy of the obtained traffic information cannot be determined, and thus it is impossible to determine whether the results output based on the obtained traffic information are accurate.

[0006] To achieve the above object, the present invention provides a method for monitoring the traffic flow of municipal roads based on the Internet of Things, which is characterized by comprising:

[0007] Step S1, setting detection nodes in the municipal roads to be monitored according to design requirements, collecting image information at each detection node, preprocessing the image information and extracting vehicle features from the preprocessed image information, and determining the number of vehicles passing through each detection node within a preset time period based on the extracted vehicle features;

[0008] Step S2, during the monitoring of the traffic volume on the municipal roads, whether the traffic volume of each detection node meets the standard is determined based on the number of vehicles passing through each detection node, and when it is determined that the traffic volume of a single detection node does not meet the standard, whether the traffic volume of the detection node meets the standard is determined again based on the traffic volumes corresponding to the upstream detection nodes and the downstream detection nodes, or, the reason why the traffic volume of the detection node does not meet the standard is determined based on the average interval between the characteristics of each vehicle, wherein the upstream detection node is a detection node that is opposite to the direction of vehicle travel and adjacent to the detection node, and the downstream detection node is a detection node that is in the same direction as the direction of vehicle travel and adjacent to the detection node;

[0009] Step S3, adjusting the corresponding parameters based on the determined reasons and re-determining whether the traffic flow of the detection node meets the standards based on the updated parameters, and when it is re-determined that the traffic flow of the detection node still does not meet the standards, diverting the vehicles on the road section where the detection node is located until the traffic flow of the detection node meets the standards, and determining the number of diverted vehicles for the detection node based on the actual number of vehicles on the road section where the adjacent detection nodes whose traffic flow meets the standards are located, wherein the adjacent detection node is a detection node whose distance from the detection node is less than a preset value;

[0010] Step S4: When it is determined that the vehicle flow rate of the detection node meets the standard, the vehicle flow rate of the detection node is continuously monitored.

[0011] Furthermore, the process of extracting the vehicle features according to the image information after a single preprocessing includes:

[0012] According to the image information obtained after preprocessing, contour features are obtained based on the image information, and a preset number of evenly distributed feature points are set in the contour features, and the relative position relationship of each feature point is obtained respectively;

[0013] Selecting the feature point located at the top of the image information among the feature points as a reference feature point;

[0014] The reference feature point is set as the coordinate origin, a rectangular coordinate system is established, and a feature point set for the contour feature is established based on the coordinate information of each feature point in the coordinate system;

[0015] Acquire a preset feature point set from a database, substitute the preset feature point set into the coordinate system and make a preset reference feature point in the preset feature point set coincide with the reference feature point;

[0016] When the ratio of the number of feature points whose coordinates overlap to the total number of feature points in the contour feature is greater than a preset ratio, the contour feature is recorded as a vehicle feature and the extraction of the contour feature is completed;

[0017] After the determination of each of the contour features is completed, the vehicle features in the image information are extracted.

[0018] Furthermore, in the process of monitoring the traffic flow of municipal roads, the traffic flow of each detection node is determined based on the number of vehicles to determine whether it meets the standard. For a single detection node,

[0019] If the number of vehicles passing through the detection node within the preset time period is less than or equal to the first preset number of vehicles, it is determined that the traffic flow of the detection node meets the standard, and the traffic flow of the detection node is continuously monitored;

[0020] If the number of vehicles passing through the detection node within the preset time period is greater than the first preset number of vehicles and less than or equal to the second preset number of vehicles, it is determined that the traffic flow of the detection node does not meet the standard, and a second determination is made based on the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node whether the traffic flow of the detection node meets the standard;

[0021] If the number of vehicles passing through the detection node within the preset time period is greater than the second preset number of vehicles, it is determined that the traffic flow of the detection node does not meet the standard, and the reason why the traffic flow of the detection node does not meet the standard is determined based on the average interval between each of the vehicle characteristics.

[0022] Furthermore, the process of secondarily determining whether the vehicle flow rate of the detection node meets the standard includes:

[0023] Respectively detecting and recording the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node;

[0024] If the number of vehicles at the upstream detection node is greater than or equal to the first preset number of vehicles and the number of vehicles at the downstream detection node is less than or equal to the first preset number of vehicles, or the number of vehicles at the upstream detection node is less than or equal to the first preset number of vehicles and the number of vehicles at the downstream detection node is greater than or equal to the first preset number of vehicles, a secondary determination is made that the traffic flow of the detection node meets the standard, and the first preset number of vehicles is determined based on the absolute value of the difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node;

[0025] If the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node are both greater than the first preset number of vehicles, or the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node are both less than or equal to the first preset number of vehicles, it is determined for the second time that the traffic flow of the detection node does not meet the standard, and the reason why the traffic flow of the detection node does not meet the standard is determined based on the average interval between each of the vehicle characteristics.

[0026] Further, the process of determining the first preset number of vehicles based on the absolute value of the difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node includes:

[0027] Calculating an absolute value of a difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node;

[0028] If the absolute value is less than or equal to the preset absolute value, the first preset number of vehicles is corrected using a first vehicle correction coefficient;

[0029] If the absolute value is greater than the preset absolute value, the first preset number of vehicles is corrected using a second vehicle correction coefficient.

[0030] Further, the process of determining the reason why the traffic flow of the detection node does not meet the standard based on the average interval between the vehicle features includes:

[0031] Establishing an image coordinate system in the image information with the lower left corner of the image information as the origin;

[0032] For two adjacent vehicle features in the image coordinate system, the straight-line distance between the feature points with the largest ordinates in the two vehicle features is selected and recorded as the distance between the two vehicle features;

[0033] respectively detecting the distances between two adjacent vehicle features and recording the average of the measured distance values ​​as the average interval;

[0034] If the average interval is smaller than the preset average interval, it is determined that the reason why the traffic flow of the detection node does not meet the standard is that the number of feature points does not meet the standard, resulting in a deviation in the vehicle feature extraction, and the vehicle feature extraction process is adjusted based on the number of feature points;

[0035] If the average interval is greater than or equal to the preset average interval, it is determined that the reason why the traffic flow of the detection node does not meet the standard is congestion, and the number of diverted vehicles for the detection node is determined based on the actual number of vehicles on the road section where the adjacent detection node whose traffic flow meets the standard is located.

[0036] Further, the method for adjusting the vehicle feature extraction process based on the number of feature points includes:

[0037] Calculating the absolute value of the difference between the average interval and the preset average interval;

[0038] The ratio of the absolute value of the difference to the preset average interval is recorded as the difference percentage;

[0039] If the difference percentage is less than or equal to a preset difference percentage, a preset number of vehicle feature points is corrected using a first feature coefficient;

[0040] If the difference percentage is greater than a preset difference percentage, a second characteristic coefficient is used to correct a preset number of the vehicle characteristic points.

[0041] Further, after completing the correction of the preset number, reacquire the vehicle features based on the corrected preset number and calculate the ratio of the reacquired vehicle feature number to the vehicle feature number acquired before the correction and record it as the feature number ratio;

[0042] If the feature quantity ratio is greater than or equal to a preset feature quantity ratio, it is determined that the vehicle feature extraction process meets the standard;

[0043] If the feature quantity ratio is less than the preset feature quantity ratio, it is determined that the image information preprocessing process does not meet the standard and the image grayscale is adjusted based on the difference between the feature quantity ratio and the preset feature quantity ratio.

[0044] Furthermore, the process of adjusting the image grayscale based on the difference between the feature quantity ratio and the preset feature quantity ratio includes:

[0045] Recording the difference between the feature quantity ratio and the preset feature quantity ratio as the feature quantity difference;

[0046] If the feature quantity difference is less than or equal to a preset feature quantity difference, adjusting the image grayscale by using a first grayscale adjustment coefficient;

[0047] If the feature quantity difference is greater than a preset feature quantity difference, a second grayscale adjustment coefficient is used to adjust the image grayscale.

[0048] Furthermore, the process of determining the number of diverted vehicles for the detection node based on the actual number of vehicles on the road section where the adjacent detection node with a traffic flow rate meeting the standard is located includes:

[0049] Acquire each detection node whose distance from the detection node is less than a preset distance and whose traffic volume meets the standard, and record each detection node as a first detection node, a second detection node, ... an nth detection node in ascending order of distance from the detection node, where n is the total number of the acquired detection nodes meeting the corresponding condition;

[0050] Detecting the actual number of vehicles in the road section where the first detection node is located and calculating the difference between the actual number of vehicles and the first preset number of vehicles;

[0051] Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the first detection node is located;

[0052] re-determining whether the traffic flow of the detection node meets the standard based on the number of vehicles at the detection node after diversion, and if the traffic flow of the detection node still does not meet the standard, detecting the actual number of vehicles at the second detection node and calculating the difference between the actual number of vehicles and the first preset number of vehicles;

[0053] Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the second detection node is located;

[0054] Repeat the above steps to distribute the vehicles in the detection node to the road section where the corresponding detection node is located in sequence until it is determined that the vehicle flow in the detection node after diversion meets the standard.

[0055] Compared with the prior art, the beneficial effect of the present invention lies in that it determines whether the traffic flow of the detection node meets the standard based on the comparison result of the actual number of vehicles at the detection node and the preset number of vehicles. For the detection node that does not meet the standard, it is re-determined whether the traffic flow of the detection node meets the standard based on the traffic flow of the upstream and downstream detection nodes adjacent to it, thereby determining whether the monitoring process of the detection node meets the standard, and determining the reason why the traffic flow of the detection node does not meet the standard based on the average interval between the characteristics of each vehicle, adjusting the corresponding parameters based on the determined reason, and re-determining whether the traffic flow of the detection node meets the standard based on the adjusted parameters, thereby further improving the accuracy of the traffic flow monitoring results, being able to determine and obtain accurate traffic information, and performing diversion and adjustment on congested sections of the road, optimizing the distribution of vehicles on the road, and being able to effectively alleviate the pressure on congested municipal roads.

[0056] Furthermore, the present invention obtains contour features based on image information and sets a preset number of evenly distributed feature points in the contour features, establishes a rectangular coordinate system based on the reference feature points and obtains a feature point set based on the coordinate information of each feature point, overlaps the feature point set of vehicles running on municipal roads with a pre-stored preset feature point set, compares the number of feature points with the total number of feature points in the contour features and extracts vehicle features based on the comparison result, detects the number of vehicles passing through the detection node based on the vehicle features, thereby improving the accuracy of vehicle recognition, and can effectively improve the accuracy of traffic flow monitoring results, thereby obtaining accurate road conditions.

[0057] Furthermore, the present invention determines whether the traffic flow of each detection node meets the standards based on the number of vehicles. If the traffic flow of a detection node does not meet the standards, it is secondary determined whether the traffic flow of the detection node meets the standards based on the traffic flow of upstream and downstream detection nodes adjacent to the detection node, and the cause of the non-compliance is analyzed, thereby further improving the accuracy of the traffic flow monitoring results, thereby obtaining accurate road conditions.

[0058] Furthermore, the present invention detects the traffic flow of upstream and downstream detection nodes adjacent to the detection node whose traffic flow does not meet the standards, and determines whether the reason why the traffic flow of the detection node does not meet the standards is due to the impact of upstream and downstream conditions or a problem with the detection node. The affected situation is deemed to meet the standards, and the detection parameters are adjusted based on this. The cause of the problem at the detection node is determined and adjusted based on the determined cause, thereby further improving the accuracy of the traffic flow monitoring results and obtaining accurate road conditions.

[0059] Furthermore, the present invention uses a corresponding correction coefficient to correct the first preset vehicle based on the comparison result of the traffic flow of the upstream and downstream detection nodes, and re-detects the traffic flow of the detection node based on this, and determines the cause for the detection node whose traffic flow still does not meet the standard, thereby further improving the accuracy of the traffic flow monitoring results and obtaining accurate road conditions.

[0060] Furthermore, the present invention determines whether the traffic flow monitoring process meets the standards by detecting the average interval between each vehicle feature. If the average interval is less than the preset average interval, it is determined that the vehicle feature extraction process is not rigorous enough and the accurate number of vehicles cannot be obtained. If the average interval is greater than or equal to the preset average interval, it is determined that the detection node is congested and needs to be adjusted, thereby further improving the accuracy of the traffic flow monitoring results and obtaining accurate road conditions.

[0061] Furthermore, the present invention adjusts the feature extraction process of vehicles that do not meet the standards based on the number of vehicle feature points, and selects a corresponding correction coefficient to increase the number of vehicle feature points by comparing the average interval with a preset average interval, thereby further limiting the vehicle characteristics, thereby improving the accuracy of the traffic flow monitoring results, and obtaining accurate road conditions.

[0062] Furthermore, the present invention re-determines whether the traffic flow of the detection node meets the standards based on the number of vehicle feature points after correction. For the monitoring nodes where the traffic flow still does not meet the standards, it determines whether the vehicle feature extraction process meets the standards by comparing the ratio of the number of vehicle feature points re-acquired to the number of vehicle feature points acquired before correction with the ratio of the preset feature number. When it is determined that the vehicle feature extraction process still does not meet the standards, the image information preprocessing process is adjusted to further improve the accuracy of the vehicle flow monitoring results, thereby obtaining accurate road conditions.

[0063] Furthermore, the present invention determines the corresponding correction coefficient to adjust the image grayscale by calculating the difference between the feature quantity ratio and the preset feature quantity ratio, thereby improving the clarity of the image information and further improving the accuracy of the vehicle flow monitoring results, thereby obtaining accurate road conditions.

[0064] Furthermore, the present invention detects the traffic flow conditions of adjacent detection nodes on congested municipal roads and diverts the vehicles on the congested sections to adjacent sections with traffic flow rates that meet standards, thereby optimizing the distribution of road vehicles and effectively alleviating the pressure on congested municipal roads. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a structural block diagram of a method for monitoring municipal road traffic flow based on the Internet of Things according to the present invention;

[0066] Figure 2 This is a flow chart of a method for monitoring municipal road traffic flow based on the Internet of Things according to the present invention;

[0067] Figure 3 A flow chart of determining whether the traffic flow of each detection node meets the standard based on the number of vehicles according to the present invention;

[0068] Figure 4 This is a flow chart of the present invention for secondary determination of whether the traffic flow of a detection node meets the standard based on the number of vehicles at the upstream and downstream detection nodes. DETAILED DESCRIPTION

[0069] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0070] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0071] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0072] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0073] See also Figure 1 As shown, it is a structural block diagram of a method for monitoring municipal road traffic flow based on the Internet of Things according to the present invention, comprising:

[0074] An information collection module is used to collect image information of detection nodes;

[0075] An image processing module, connected to the information acquisition module, for preprocessing the image information;

[0076] The central control module is connected to the image processing module to extract vehicle features based on the pre-processed image information and count the number of vehicles based on the vehicle features. Based on the counted number of vehicles, it determines whether the traffic flow of each detection node meets the standards and analyzes and adjusts the detection nodes whose traffic flow does not meet the standards.

[0077] See also Figure 2 As shown, it is a flow chart of a method for monitoring the traffic flow of municipal roads based on the Internet of Things according to the present invention, comprising:

[0078] Step S1, according to the design requirements, detection nodes are set in the municipal roads to be monitored, the information acquisition module collects image information at each detection node, the image processing module pre-processes the image information, and the central control module extracts vehicle features from the pre-processed image information and determines the number of vehicles passing through each detection node within a preset time period based on the extracted vehicle features;

[0079] Step S2, during the monitoring of the traffic volume on municipal roads, the central control module determines whether the traffic volume of each detection node meets the standard based on the number of vehicles passing through each detection node, and when it is determined that the traffic volume of a single detection node does not meet the standard, it determines whether the traffic volume of the detection node meets the standard based on the traffic volumes corresponding to the upstream detection nodes and the downstream detection nodes, or determines the reason why the traffic volume of the detection node does not meet the standard based on the average interval between the characteristics of each vehicle, wherein the upstream detection node is a detection node that is opposite to the direction of vehicle travel and adjacent to the detection node, and the downstream detection node is a detection node that is in the same direction as the direction of vehicle travel and adjacent to the detection node;

[0080] Step S3, the central control module adjusts the corresponding parameters based on the determined reasons and re-determines whether the traffic flow of the detection node meets the standards based on the updated parameters. When it is re-determined that the traffic flow of the detection node still does not meet the standards, the vehicles on the road section where the detection node is located are diverted until the traffic flow of the detection node meets the standards, and the number of diverted vehicles for the detection node is determined based on the actual number of vehicles on the road section where the adjacent detection nodes whose traffic flow meets the standards are located, wherein the adjacent detection node is a detection node whose distance from the detection node is less than a preset value;

[0081] Step S4: When the central control module determines that the vehicle flow rate of the detection node meets the standard, the central control module continuously monitors the vehicle flow rate of the detection node.

[0082] Specifically, in the embodiment of the present invention, the process of extracting the vehicle features by the central control module according to the image information completed by a single preprocessing includes:

[0083] The central control module obtains contour features based on the image information obtained after preprocessing, sets a preset number of evenly distributed feature points in the contour features, and obtains the relative position relationship of each feature point respectively;

[0084] The central control module selects the feature point located at the top of the image information among the feature points as the reference feature point;

[0085] The central control module sets the reference feature point as the coordinate origin, establishes a rectangular coordinate system, and establishes a feature point set for the contour feature based on the coordinate information of each feature point in the coordinate system;

[0086] The central control module obtains a preset feature point set from the database, substitutes the preset feature point set into the coordinate system and makes a preset reference feature point in the preset feature point set coincide with the reference feature point;

[0087] When the ratio of the number of feature points whose coordinates overlap to the total number of feature points in the contour feature is greater than a preset ratio, the central control module records the contour feature as a vehicle feature and completes the extraction of the contour feature;

[0088] After the determination of each of the contour features is completed, the vehicle features in the image information are extracted.

[0089] Those skilled in the art can understand that the selection of vehicle feature points only needs to be able to clearly define the vehicle features, and the positions of the feature points are not set.

[0090] Specifically, the preset number of feature points is 12.

[0091] See also Figure 3As shown, it is a flow chart of determining whether the traffic flow of each detection node meets the standard based on the number of vehicles according to the present invention.

[0092] Specifically, during the traffic flow monitoring process on municipal roads, the central control module determines whether the traffic flow of each detection node meets the standard based on the number of vehicles. For a single detection node,

[0093] If the number of vehicles passing through the detection node within the preset time period is less than or equal to the first preset number of vehicles, the central control module determines that the traffic flow of the detection node meets the standard and continuously monitors the traffic flow of the detection node;

[0094] If the number of vehicles passing through the detection node within the preset time period is greater than the first preset number of vehicles and less than or equal to the second preset number of vehicles, the central control module determines that the traffic flow of the detection node does not meet the standard, and re-determines whether the traffic flow of the detection node meets the standard based on the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node;

[0095] If the number of vehicles passing through the detection node within the preset time period is greater than the second preset number of vehicles, the central control module determines that the traffic flow of the detection node does not meet the standard, and determines the reason why the traffic flow of the detection node does not meet the standard based on the average interval between each of the vehicle characteristics.

[0096] Specifically, the preset duration is 30 minutes;

[0097] Specifically, the first preset number of vehicles is 400 vehicles, and the second preset number of vehicles is 600 vehicles.

[0098] See also Figure 4 As shown, it is a flow chart of the present invention for secondary determining whether the traffic flow of the detection node meets the standard based on the number of vehicles at the upstream and downstream detection nodes.

[0099] Specifically, the process of the control module in the embodiment of the present invention secondarily determining whether the vehicle flow of the detection node meets the standard includes:

[0100] The central control module detects and records the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node respectively;

[0101] If the number of vehicles at the upstream detection node is greater than or equal to the first preset number of vehicles and the number of vehicles at the downstream detection node is less than or equal to the first preset number of vehicles, or the number of vehicles at the upstream detection node is less than or equal to the first preset number of vehicles and the number of vehicles at the downstream detection node is greater than or equal to the first preset number of vehicles, the central control module determines for the second time that the vehicle flow of the detection node meets the standard, and determines the first preset number of vehicles based on the absolute value of the difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node;

[0102] If the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node are both greater than the first preset number of vehicles, or the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node are both less than or equal to the first preset number of vehicles, the central control module determines for the second time that the traffic flow of the detection node does not meet the standard, and determines the reason why the traffic flow of the detection node does not meet the standard based on the average interval between each of the vehicle characteristics.

[0103] Specifically, the process of determining the first preset number of vehicles by the control module in the embodiment of the present invention based on the absolute value of the difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node includes:

[0104] Calculating an absolute value of a difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node;

[0105] If the absolute value is less than or equal to the preset absolute value, the first preset number of vehicles is corrected using a first vehicle correction coefficient;

[0106] If the absolute value is greater than the preset absolute value, the first preset number of vehicles is corrected using a second vehicle correction coefficient.

[0107] Specifically, the central control module re-compares the number of vehicles at the detection node with the corrected first preset number of vehicles and determines whether the traffic flow at the detection node meets the standards based on the comparison result. If the traffic flow at the detection node still does not meet the standards, the reason why the traffic flow at the detection node does not meet the standards is determined based on the average interval between the vehicle characteristics.

[0108] Specifically, the preset absolute value is 100.

[0109] Specifically, the first vehicle correction factor is 1.2, and the second vehicle correction factor is 1.5.

[0110] Specifically, the process of the control module in the embodiment of the present invention determining the reason why the vehicle flow of the detection node does not meet the standard based on the average interval between the vehicle features includes:

[0111] The central control module establishes an image coordinate system in the image information with the lower left corner of the image information as the origin;

[0112] For two adjacent vehicle features in the image coordinate system, the central control module selects the straight-line distance between the feature points with the largest ordinates in the two vehicle features as the distance between the two vehicle features;

[0113] The central control module detects the distance between two adjacent vehicle features respectively and records the average of the measured distance values ​​as the average interval;

[0114] If the average interval is less than the preset average interval, the central control module determines that the reason why the vehicle flow at the detection node does not meet the standard is that the number of feature points does not meet the standard, resulting in a deviation in the vehicle feature extraction, and adjusts the vehicle feature extraction process based on the number of feature points;

[0115] If the average interval is greater than or equal to the preset average interval, the central control module determines that the reason why the traffic flow of the detection node does not meet the standard is congestion, and determines the number of diverted vehicles for the detection node based on the actual number of vehicles on the road section where the adjacent detection node whose traffic flow meets the standard is located.

[0116] Specifically, the preset average interval is 3m.

[0117] Specifically, the method in which the control module in an embodiment of the present invention adjusts the vehicle feature extraction process based on the number of feature points includes:

[0118] The central control module calculates the absolute value of the difference between the average interval and the preset average interval;

[0119] The central control module records the ratio of the absolute value of the difference to the preset average interval as the difference percentage;

[0120] If the difference percentage is less than or equal to the preset difference percentage, the central control module uses the first characteristic coefficient to correct the preset number of vehicle characteristic points;

[0121] If the difference percentage is greater than the preset difference percentage, the central control module uses the second characteristic coefficient to correct the preset number of the vehicle characteristic points.

[0122] Specifically, the preset difference percentage is 30%.

[0123] Specifically, the first characteristic coefficient is 1.3, and the second characteristic coefficient is 1.6.

[0124] Specifically, after completing the correction of the preset number, the control module in the embodiment of the present invention reacquires the vehicle features based on the corrected preset number and calculates the ratio of the reacquired vehicle feature number to the vehicle feature number acquired before the correction and records it as the feature number ratio;

[0125] If the feature quantity ratio is greater than or equal to a preset feature quantity ratio, the central control module determines that the extraction process of the vehicle feature meets the standard;

[0126] If the feature quantity ratio is less than the preset feature quantity ratio, the central control module determines that the image information preprocessing process does not meet the standard and adjusts the image grayscale based on the difference between the feature quantity ratio and the preset feature quantity ratio.

[0127] Specifically, the preset feature quantity ratio is 1.5.

[0128] Specifically, the process of adjusting the image grayscale by the control module in the embodiment of the present invention based on the difference between the feature quantity ratio and the preset feature quantity ratio includes:

[0129] Recording the difference between the feature quantity ratio and the preset feature quantity ratio as the feature quantity difference;

[0130] If the feature quantity difference is less than or equal to a preset feature quantity difference, adjusting the image grayscale by using a first grayscale adjustment coefficient;

[0131] If the feature quantity difference is greater than a preset feature quantity difference, a second grayscale adjustment coefficient is used to adjust the image grayscale.

[0132] Specifically, the preset feature quantity difference is 0.2.

[0133] Specifically, the first grayscale adjustment coefficient is 1.4, and the second grayscale adjustment coefficient is 1.2.

[0134] Specifically, the process of determining the number of diverted vehicles for the detection node by the control module in the embodiment of the present invention based on the actual number of vehicles on the road section where the adjacent detection node where the traffic flow meets the standard is located includes:

[0135] Acquire each detection node whose distance from the detection node is less than a preset distance and whose traffic volume meets the standard, and record each detection node as a first detection node, a second detection node, ... an nth detection node in ascending order of distance from the detection node, where n is the total number of the acquired detection nodes meeting the corresponding condition;

[0136] Detecting the actual number of vehicles in the road section where the first detection node is located and calculating the difference between the actual number of vehicles and the first preset number of vehicles;

[0137] Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the first detection node is located;

[0138] re-determining whether the traffic flow of the detection node meets the standard based on the number of vehicles at the detection node after diversion, and if the traffic flow of the detection node still does not meet the standard, detecting the actual number of vehicles at the second detection node and calculating the difference between the actual number of vehicles and the first preset number of vehicles;

[0139] Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the second detection node is located;

[0140] Re-determining whether the traffic flow of the detection node meets the standard based on the number of vehicles at the detection node after the second diversion, and if the traffic flow of the detection node still does not meet the standard, detecting the actual number of vehicles at the third detection node and calculating the difference between the actual number of vehicles and the first preset number of vehicles;

[0141] Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the third detection node is located;

[0142] re-determining whether the traffic flow of the detection node meets the standard based on the number of vehicles at the detection node after the third diversion, and if the traffic flow of the detection node still does not meet the standard, detecting the actual number of vehicles at the fourth detection node and calculating the difference between the actual number of vehicles and the first preset number of vehicles;

[0143] Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the fourth detection node is located;

[0144] Repeat the above steps to distribute the vehicles in the detection node to the road section where the corresponding detection node is located in sequence until it is determined that the vehicle flow in the detection node after diversion meets the standard.

[0145] Specifically, the preset distance is 10km.

[0146] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for monitoring traffic flow on municipal roads based on the Internet of Things, characterized in that: include: Step S1, setting detection nodes in the municipal roads to be monitored according to design requirements, collecting image information at each detection node, preprocessing the image information and extracting vehicle features from the preprocessed image information, and determining the number of vehicles passing through each detection node within a preset time period based on the extracted vehicle features; Step S2, during the monitoring of the traffic volume on the municipal roads, whether the traffic volume of each detection node meets the standard is determined based on the number of vehicles passing through each detection node, and when it is determined that the traffic volume of a single detection node does not meet the standard, whether the traffic volume of the detection node meets the standard is determined again based on the traffic volumes corresponding to the upstream detection nodes and the downstream detection nodes, or, the reason why the traffic volume of the detection node does not meet the standard is determined based on the average interval between the characteristics of each vehicle, wherein the upstream detection node is a detection node that is opposite to the direction of vehicle travel and adjacent to the detection node, and the downstream detection node is a detection node that is in the same direction as the direction of vehicle travel and adjacent to the detection node; Step S3, adjusting the corresponding parameters based on the determined reasons and re-determining whether the traffic flow of the detection node meets the standards based on the updated parameters, and when it is re-determined that the traffic flow of the detection node still does not meet the standards, diverting the vehicles on the road section where the detection node is located until the traffic flow of the detection node meets the standards, and determining the number of diverted vehicles for the detection node based on the actual number of vehicles on the road section where the adjacent detection nodes whose traffic flow meets the standards are located, wherein the adjacent detection node is a detection node whose distance from the detection node is less than a preset value; Step S4: When it is determined that the vehicle flow rate of the detection node meets the standard, the vehicle flow rate of the detection node is continuously monitored.

2. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 1 is characterized in that: The process of extracting the vehicle features according to the image information completed by a single preprocessing comprises: According to the image information obtained after preprocessing, contour features are obtained based on the image information, and a preset number of evenly distributed feature points are set in the contour features, and the relative position relationship of each feature point is obtained respectively; Selecting the feature point located at the top of the image information among the feature points as a reference feature point; The reference feature point is set as the coordinate origin, a rectangular coordinate system is established, and a feature point set for the contour feature is established based on the coordinate information of each feature point in the coordinate system; Acquire a preset feature point set from a database, substitute the preset feature point set into the coordinate system and make a preset reference feature point in the preset feature point set coincide with the reference feature point; When the ratio of the number of feature points whose coordinates overlap to the total number of feature points in the contour feature is greater than a preset ratio, the contour feature is recorded as a vehicle feature and the extraction of the contour feature is completed; After the determination of each of the contour features is completed, the vehicle features in the image information are extracted.

3. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 2 is characterized in that: In the process of monitoring the traffic flow of municipal roads, the traffic flow of each detection node is determined based on the number of vehicles to determine whether it meets the standard. For a single detection node, If the number of vehicles passing through the detection node within the preset time period is less than or equal to the first preset number of vehicles, it is determined that the traffic flow of the detection node meets the standard, and the traffic flow of the detection node is continuously monitored; If the number of vehicles passing through the detection node within the preset time period is greater than the first preset number of vehicles and less than or equal to the second preset number of vehicles, it is determined that the traffic flow of the detection node does not meet the standard, and a second determination is made based on the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node whether the traffic flow of the detection node meets the standard; If the number of vehicles passing through the detection node within the preset time period is greater than the second preset number of vehicles, it is determined that the traffic flow of the detection node does not meet the standard, and the reason why the traffic flow of the detection node does not meet the standard is determined based on the average interval between each of the vehicle characteristics.

4. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 3 is characterized in that: The process of secondarily determining whether the vehicle flow rate of the detection node meets the standard includes: Respectively detecting and recording the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node; If the number of vehicles at the upstream detection node is greater than or equal to the first preset number of vehicles and the number of vehicles at the downstream detection node is less than or equal to the first preset number of vehicles, or the number of vehicles at the upstream detection node is less than or equal to the first preset number of vehicles and the number of vehicles at the downstream detection node is greater than or equal to the first preset number of vehicles, a secondary determination is made that the traffic flow of the detection node meets the standard, and the first preset number of vehicles is determined based on the absolute value of the difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node; If the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node are both greater than the first preset number of vehicles, or the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node are both less than or equal to the first preset number of vehicles, it is determined for the second time that the traffic flow of the detection node does not meet the standard, and the reason why the traffic flow of the detection node does not meet the standard is determined based on the average interval between each of the vehicle characteristics.

5. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 4 is characterized in that: The process of determining the first preset number of vehicles based on the absolute value of the difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node includes: Calculating an absolute value of a difference between the number of vehicles at the upstream detection node and the number of vehicles at the downstream detection node; If the absolute value is less than or equal to the preset absolute value, the first preset number of vehicles is corrected using a first vehicle correction coefficient; If the absolute value is greater than the preset absolute value, the first preset number of vehicles is corrected using a second vehicle correction coefficient.

6. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 5 is characterized in that: The process of determining the reason why the traffic flow of the detection node does not meet the standard based on the average interval between the vehicle features includes: Establishing an image coordinate system in the image information with the lower left corner of the image information as the origin; For two adjacent vehicle features in the image coordinate system, the straight-line distance between the feature points with the largest ordinates in the two vehicle features is selected and recorded as the distance between the two vehicle features; respectively detecting the distances between two adjacent vehicle features and recording the average of the measured distance values ​​as the average interval; If the average interval is smaller than the preset average interval, it is determined that the reason why the traffic flow of the detection node does not meet the standard is that the number of feature points does not meet the standard, resulting in a deviation in the vehicle feature extraction, and the vehicle feature extraction process is adjusted based on the number of feature points; If the average interval is greater than or equal to the preset average interval, it is determined that the reason why the traffic flow of the detection node does not meet the standard is congestion, and the number of diverted vehicles for the detection node is determined based on the actual number of vehicles on the road section where the adjacent detection node whose traffic flow meets the standard is located.

7. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 6 is characterized in that: The method for adjusting the vehicle feature extraction process based on the number of feature points includes: Calculating the absolute value of the difference between the average interval and the preset average interval; The ratio of the absolute value of the difference to the preset average interval is recorded as the difference percentage; If the difference percentage is less than or equal to a preset difference percentage, a preset number of vehicle feature points is corrected using a first feature coefficient; If the difference percentage is greater than a preset difference percentage, a second characteristic coefficient is used to correct a preset number of the vehicle characteristic points.

8. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 7 is characterized in that: After completing the correction of the preset number, reacquiring vehicle features based on the corrected preset number and calculating a ratio of the reacquired vehicle feature number to the vehicle feature number acquired before the correction and recording it as a feature number ratio; If the feature quantity ratio is greater than or equal to a preset feature quantity ratio, it is determined that the vehicle feature extraction process meets the standard; If the feature quantity ratio is less than the preset feature quantity ratio, it is determined that the image information preprocessing process does not meet the standard and the image grayscale is adjusted based on the difference between the feature quantity ratio and the preset feature quantity ratio.

9. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 8, characterized in that: The process of adjusting the image grayscale based on the difference between the feature quantity ratio and the preset feature quantity ratio includes: Recording the difference between the feature quantity ratio and the preset feature quantity ratio as the feature quantity difference; If the feature quantity difference is less than or equal to a preset feature quantity difference, adjusting the image grayscale by using a first grayscale adjustment coefficient; If the feature quantity difference is greater than a preset feature quantity difference, a second grayscale adjustment coefficient is used to adjust the image grayscale.

10. The method for monitoring the traffic flow of municipal roads based on the Internet of Things according to claim 6, characterized in that: The process of determining the number of diverted vehicles for the detection node based on the actual number of vehicles on the road section where the adjacent detection node that meets the traffic flow standard is located includes: Acquire each detection node whose distance from the detection node is less than a preset distance and whose traffic volume meets the standard, and record each detection node as a first detection node, a second detection node, ... an nth detection node in ascending order of distance from the detection node, where n is the total number of the acquired detection nodes meeting the corresponding condition; Detecting the actual number of vehicles in the road section where the first detection node is located and calculating the difference between the actual number of vehicles and the first preset number of vehicles; Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the first detection node is located; re-determining whether the traffic flow of the detection node meets the standard based on the number of vehicles at the detection node after diversion, and if the traffic flow of the detection node still does not meet the standard, detecting the actual number of vehicles at the second detection node and calculating the difference between the actual number of vehicles and the first preset number of vehicles; Diverting the number of vehicles corresponding to the difference from the road section where the detection node is located to the road section where the second detection node is located; Repeat the above steps to distribute the vehicles in the detection node to the road section where the corresponding detection node is located in sequence until it is determined that the vehicle flow in the detection node after diversion meets the standard.