A road cleaning and maintenance environment assessment method

Abstract

The present invention relates to the field of data processing technology, and in particular to a method for evaluating a road cleaning and maintenance environment, comprising: obtaining a road image of a road and vehicle information of vehicles passing on the road; determining the actual degree of damage to the road according to the road image; determining the degree of wear caused by vehicles on the road according to the vehicle information; determining the degree of traffic density on the road according to the vehicle information; and determining a result of evaluating a road cleaning and maintenance environment according to the degree of wear, the actual degree of damage, and the degree of traffic density. The method can improve the accuracy of evaluating a road cleaning and maintenance environment.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a method for evaluating the environment for road cleaning and maintenance. Background Art

[0002] Road cleaning and maintenance refers to the regular cleaning, repair and maintenance of roads to ensure the safety and comfort of roads. In order to formulate appropriate road cleaning and maintenance plans and strategies to ensure the efficiency and quality of road cleaning and maintenance work, it is necessary to accurately evaluate the road cleaning and maintenance environment in advance.

[0003] In traditional methods, the road cleaning and maintenance environment is generally evaluated directly based on the road damage condition. However, the specific usage of the road during actual use will also affect the road cleaning and maintenance environment. For example, the actual vehicles traveling on the road will also affect the road cleaning and maintenance environment. Therefore, directly evaluating the road cleaning and maintenance environment based on the road damage condition is not accurate enough. Summary of the invention

[0004] In order to solve the technical problem of inaccurate road cleaning and maintenance environment assessment, the purpose of the present invention is to provide a road cleaning and maintenance environment assessment method, and the technical scheme adopted is as follows:

[0005] Acquire a road image of a road and vehicle information of vehicles traveling on the road;

[0006] determining an actual degree of damage to the road according to the road image;

[0007] determining, based on the vehicle information, a degree of wear and tear caused by the vehicle on the road;

[0008] Determining the density of traffic on the road according to the vehicle information;

[0009] An environmental assessment result of cleaning and maintenance of the road is determined based on the degree of wear, the actual degree of damage and the traffic density.

[0010] In one embodiment, the vehicle information includes basic vehicle information, vehicle speed information, and time information; and determining the degree of wear caused by the vehicle on the road according to the vehicle information includes:

[0011] Clustering the vehicles on the road according to the time information to obtain a plurality of clusters;

[0012] For each cluster, determine the traffic congestion coefficient of the cluster according to the basic vehicle information and the vehicle speed information of the vehicles in the cluster;

[0013] Determining a load factor of the cluster according to the basic vehicle information and the time information of the vehicles in the cluster;

[0014] The degree of wear caused by vehicles on the road is determined according to the traffic congestion coefficient and the load coefficient of each of the clusters.

[0015] In one embodiment, determining the traffic congestion coefficient of the cluster according to the basic vehicle information and the vehicle speed information of the vehicles in the cluster includes:

[0016] Determine the total number of vehicles, the number of large vehicles and the number of small vehicles in the cluster according to the basic vehicle information of the vehicles in the cluster, and determine the average speed of the vehicles, the average speed of large vehicles and the average speed of small vehicles in the cluster in combination with the vehicle speed information;

[0017] Determine the difference between the number of large vehicles and the number of small vehicles in the cluster according to the number of large vehicles and the number of small vehicles;

[0018] Determine the speed difference between the large vehicles and the small vehicles in the cluster according to the average speed of the large vehicles and the average speed of the small vehicles;

[0019] The traffic congestion coefficient of the cluster is determined according to the quantity difference, the vehicle speed difference, the total number of vehicles and the average vehicle speed.

[0020] In one embodiment, determining the load factor of the cluster according to the basic vehicle information and the time information of the vehicles in the cluster includes:

[0021] Determine the total number of vehicles and the number of large vehicles in the cluster according to the basic vehicle information of the vehicles in the cluster, and determine the time point of the cluster according to the time information of the vehicles in the cluster;

[0022] Determining the load factor of the cluster according to the proportion of the number of large vehicles to the total number of vehicles;

[0023] Determining a load factor difference based on the load factor of the cluster and the load factors of adjacent clusters;

[0024] Determining the proximity of the clusters to night based on the time points of the clusters;

[0025] The load factor of the cluster is determined based on the load factor difference, the proximity of night, the number of large vehicles, and the total number of vehicles.

[0026] In one embodiment, the vehicle information includes basic vehicle information and time information; and determining the density of traffic on the road according to the vehicle information includes:

[0027] Clustering the vehicles on the road according to the time information to obtain a plurality of clusters;

[0028] Determine the total number of vehicles in each of the clusters according to the basic information of the vehicles;

[0029] Determine a maximum cluster from a plurality of clusters according to the total number of vehicles in each of the clusters;

[0030] For each of the maximum clusters, respectively, determine the change in the total number of vehicles between the maximum cluster and an adjacent maximum cluster of the maximum cluster according to the total number of vehicles, and determine the time difference between the maximum cluster and an adjacent maximum cluster of the maximum cluster according to the time information;

[0031] The density of traffic on the road is determined according to the change in the total number of vehicles corresponding to each of the maximum clusters, the time difference and the total number of vehicles in the maximum clusters.

[0032] In one embodiment, determining the change in the total number of vehicles between the maximum cluster and the adjacent maximum clusters of the maximum cluster according to the total number of vehicles includes:

[0033] Determine a mean of the total number of vehicles in the clusters between the maximum cluster and the adjacent maximum clusters of the maximum cluster as a first mean;

[0034] Determine a mean of the total number of vehicles in the maximum cluster and the maximum clusters adjacent to the maximum cluster as a second mean;

[0035] According to the ratio between the first mean and the second mean, the change in the total number of vehicles between the maximum cluster and the adjacent maximum clusters of the maximum cluster is determined.

[0036] In one embodiment, determining the cleaning and maintenance environment assessment result of the road according to the wear degree, the actual damage degree and the traffic density includes:

[0037] Determining a cleaning and maintenance environment assessment value of the road according to a difference between the wear degree and the actual damage degree, and the traffic density;

[0038] The cleaning and maintenance environment evaluation value is compared with a preset threshold value, and the cleaning and maintenance environment evaluation result of the road is determined according to the comparison result.

[0039] In one embodiment, the cleaning and maintenance environment evaluation result includes a first result and a second result; the cleaning and maintenance environment represented by the first result is better than the cleaning and maintenance environment represented by the second result;

[0040] The method further comprises:

[0041] A cleaning and maintenance strategy for the road is generated according to the cleaning and maintenance environment assessment result; the cleaning and maintenance strategy includes a cleaning and maintenance frequency and an input amount of cleaning and maintenance resources; the cleaning and maintenance frequency corresponding to the first result is greater than the cleaning and maintenance frequency corresponding to the second result; the cleaning and maintenance resource input amount corresponding to the first result is less than the cleaning and maintenance resource input amount corresponding to the second result.

[0042] In one embodiment, determining the actual damage degree of the road according to the road image includes:

[0043] Converting the road image into a grayscale image;

[0044] Performing edge detection on the grayscale image to obtain road marking edges, road damage edges, and road material particle edges;

[0045] The road marking edges, the damaged edges of the road and the edges of the road material particles are analyzed, and the actual damage degree of the road is determined according to the analysis results.

[0046] In one embodiment, the analyzing the edges of the road markings, the damaged edges of the road, and the edges of the road material particles, and determining the actual degree of damage to the road according to the analysis results, includes:

[0047] Determining the integrity of the road markings based on the road marking edges;

[0048] Determining the size and degree of damage on the road according to the damaged edge of the road;

[0049] Determining edge length and gradient of the road material particles according to the edge of the road material particles;

[0050] The actual degree of damage to the road is determined based on the integrity of the markings, the size and degree of damage to the road, and the edge length and gradient of the road material particles.

[0051] The present invention has the following beneficial effects:

[0052] By determining the actual degree of damage to the road based on the road image, and determining the degree of wear and tear caused by vehicles on the road and the traffic density based on the vehicle information, and finally determining the road cleaning and maintenance environment assessment results based on the degree of wear, the actual degree of damage and the traffic density, not only the actual degree of damage to the road itself can be taken into account, but also the impact of the vehicles actually traveling on the road on the road cleaning and maintenance environment can be taken into account, thereby improving the accuracy of the road cleaning and maintenance environment assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0054] Figure 1 A schematic flow chart of a road cleaning and maintenance environment assessment method provided by one embodiment of the present invention;

[0055] Figure 2 A schematic diagram of a device for collecting road images and vehicle information in a road cleaning and maintenance environment assessment method provided by an embodiment of the present invention;

[0056] Figure 3 A schematic diagram of the form of vehicle information provided by an embodiment of the present invention;

[0057] Figure 4 A schematic diagram of a road image in a road cleaning and maintenance environment assessment method provided by an embodiment of the present invention;

[0058] Figure 5 A schematic flow chart of a road cleaning and maintenance environment assessment method provided in accordance with another embodiment of the present invention. DETAILED DESCRIPTION

[0059] 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 a road cleaning and maintenance environment assessment method proposed by the present invention, its specific implementation, structure, features and effects, in conjunction 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.

[0060] 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.

[0061] The specific scheme of the road cleaning and maintenance environment assessment method provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0062] See also Figure 1 , which shows a flow chart of a road cleaning and maintenance environment assessment method provided by an embodiment of the present invention. The method can be applied to a terminal or a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The method includes the following steps:

[0063] Step 102: Acquire a road image of the road and vehicle information of vehicles traveling on the road.

[0064] The road image is an image obtained by collecting images of the road.

[0065] In one embodiment, the road image and vehicle information can be obtained from an image acquisition device above the road or an image acquisition device on a vehicle traveling on the road. For example, the image acquisition device above the road can be such as Figure 2 The speed camera above the road shown in the figure is used to collect images of vehicles on the road in real time, and then identify the vehicle and measure its speed based on the image to determine whether it has violated the law.

[0066] In one embodiment, the vehicle information may include basic vehicle information, vehicle speed information, and time information. The basic vehicle information refers to the inherent information of the vehicle itself. For example, the basic vehicle information may include at least one of license plate information and vehicle model information. Time information refers to the time when the image of the vehicle is captured. The vehicle information may be represented as a time series according to the time information. Figure 3 As shown, an example of vehicle information is shown, where the horizontal axis is time and the vertical axis is vehicle speed. Each data point in the figure represents vehicle information corresponding to a vehicle.

[0067] Step 104: determining the actual damage degree of the road according to the road image.

[0068] In one embodiment, the road image may be converted into a grayscale image, edge detection may be performed on the grayscale image, and then the edges obtained by the edge detection may be analyzed, and the actual damage degree of the road may be determined according to the analysis result.

[0069] like Figure 4 The figure shows a road image. It is obvious that there is damage on the road in the figure. The actual damage extent of the damage can be determined based on the road image.

[0070] Step 106, determining the degree of wear caused by the vehicle on the road based on the vehicle information.

[0071] In one embodiment, the vehicles on the road are first clustered to obtain multiple clusters, and then for each cluster, the congestion coefficient and load coefficient of the cluster are determined according to the vehicle information, and the degree of wear caused by the vehicles on the road is determined according to the congestion coefficient and load coefficient of each cluster.

[0072] The traffic jam coefficient is used to characterize the severity of traffic jams in the cluster, and the load coefficient is used to characterize the load caused by the vehicles in the cluster on the road.

[0073] In one embodiment, the wear degree is positively correlated with the traffic jam coefficient. The wear degree is positively correlated with the load coefficient.

[0074] In one embodiment, the degree of wear caused by vehicles in the cluster to the road can be determined based on the congestion coefficient and load coefficient of the cluster, and then the degree of wear caused by vehicles to the road can be determined based on the mean of the wear degrees corresponding to each cluster.

[0075] Step 108, determining the density of traffic on the road based on the vehicle information.

[0076] In one embodiment, a maximum cluster can be determined from multiple clusters, and then for each maximum cluster, the change in the total number of vehicles and the time difference between the maximum cluster and its adjacent maximum clusters can be determined based on vehicle information. The traffic density on the road can be determined based on the change in the total number of vehicles and the time difference of each maximum cluster and the total number of vehicles in the maximum cluster.

[0077] In one embodiment, the traffic density of vehicles in each maximum cluster can be determined based on the change in the total number of vehicles in each maximum cluster and the time difference, as well as the total number of vehicles in the maximum cluster. Then, the traffic density on the road can be determined based on the average of the traffic density corresponding to each maximum cluster.

[0078] Step 110, determining the road cleaning and maintenance environment assessment result based on the degree of wear, actual damage and traffic density.

[0079] In one embodiment, the road cleaning and maintenance environment evaluation value can be determined based on the difference between the wear degree and the actual damage degree, and the traffic density, and then the road cleaning and maintenance environment evaluation result can be determined based on the cleaning and maintenance environment evaluation value.

[0080] In one embodiment, the cleaning and maintenance environment evaluation value is positively correlated with the difference between the wear degree and the actual damage degree, and is negatively correlated with the traffic density.

[0081] In one embodiment, the cleaning and maintenance environment evaluation value may be compared with a preset threshold value, and the cleaning and maintenance environment evaluation result of the road may be determined according to the comparison result.

[0082] In the above-mentioned road cleaning and maintenance environment assessment method, the actual damage degree of the road is determined based on the road image, and the wear degree of the road caused by the vehicle and the traffic density are determined based on the vehicle information. Finally, the road cleaning and maintenance environment assessment result is determined based on the wear degree, the actual damage degree and the traffic density. Not only the actual damage degree of the road itself can be taken into account, but also the impact of the vehicles actually traveling on the road on the road cleaning and maintenance environment can be taken into account, thereby improving the accuracy of the road cleaning and maintenance environment assessment.

[0083] In one embodiment, the vehicle information includes basic vehicle information, speed information and time information; determining the degree of wear caused by the vehicle on the road based on the vehicle information, including: clustering the vehicles on the road based on the time information to obtain multiple clusters; determining the traffic congestion coefficient of each cluster based on the basic vehicle information and speed information of the vehicles in the cluster; determining the load coefficient of the cluster based on the basic vehicle information and time information of the vehicles in the cluster; determining the degree of wear caused by the vehicle on the road based on the traffic congestion coefficient and load coefficient of each cluster.

[0084] Among them, the time of vehicles in the same cluster is similar, and the time of vehicles in different clusters is far different.

[0085] In one embodiment, the total number of vehicles, the number of large vehicles, and the number of small vehicles in the cluster can be determined based on the basic vehicle information of the vehicles in the cluster, and the average speed of the vehicles in the cluster, the average speed of large vehicles, and the average speed of small vehicles can be determined in combination with the vehicle speed information. Then, the traffic congestion coefficient of the cluster is determined based on the total number of vehicles, the number of large vehicles, the number of small vehicles, the average speed of vehicles, the average speed of large vehicles, and the average speed of small vehicles in the cluster.

[0086] The types of vehicles are divided into large vehicles and small vehicles in advance. The basic information of the vehicle may include at least one of the license plate information and the vehicle model information. The type of the vehicle may be determined directly according to the vehicle model information, or the vehicle model information may be determined according to the license plate information, and then the type of the vehicle may be determined according to the vehicle model information. Then, according to the types of each vehicle in the cluster, the number of large vehicles and the number of small vehicles in the cluster are determined. Then, according to the types of each vehicle and the speed information of each vehicle in the cluster, the average speed of large vehicles and the average speed of small vehicles in the cluster are determined.

[0087] In one embodiment, the total number of vehicles and the number of large vehicles in the cluster can be determined based on the basic vehicle information of the vehicles in the cluster, and the load factor of the cluster can be determined based on the proportion of the number of large vehicles to the total number of vehicles. Then, the load factor of the cluster can be determined based on the load factor of the cluster, time information, the number of large vehicles and the total number of vehicles.

[0088] In one embodiment, the degree of wear is positively correlated with the traffic jam coefficient and the load coefficient. It can be understood that the high density of vehicles caused by traffic jams will aggravate the wear of the road, so the degree of wear is positively correlated with the traffic jam coefficient. The greater the load caused by the vehicle on the road, the greater the pressure on the road, and the aggravated wear of the road, so the degree of wear is positively correlated with the load coefficient.

[0089] In one embodiment, the degree of wear caused by vehicles in the cluster to the road can be determined based on the product of the congestion coefficient and the load coefficient of the cluster, and then the degree of wear caused by vehicles to the road can be determined based on the average of the wear degrees corresponding to each cluster.

[0090] In one embodiment, the degree of wear caused by the vehicle on the road can be determined according to the following formula:

[0091]

[0092] Where MS represents the degree of wear, i represents an arbitrary cluster, and I represents the number of clusters. Represents the traffic congestion coefficient of cluster i. Represents the load factor of cluster i. th() represents a hyperbolic function, which is used for positive correlation normalization.

[0093] In the above embodiment, the vehicles on the road are clustered according to the time information to obtain a plurality of clusters, and then for each cluster, the traffic congestion coefficient of the cluster is determined according to the basic vehicle information and speed information of the vehicles in the cluster, and the load coefficient of the cluster is determined according to the basic vehicle information and time information of the vehicles in the cluster. Finally, the degree of wear caused by the vehicles on the road is determined according to the traffic congestion coefficient and load coefficient of each cluster. The degree of wear caused by the vehicles on the road can be accurately determined according to the traffic congestion situation of the vehicles and the load situation caused by the vehicles on the road.

[0094] In one embodiment, the traffic congestion coefficient of the cluster is determined based on the basic vehicle information and speed information of the vehicles in the cluster, including: determining the total number of vehicles, the number of large vehicles and the number of small vehicles in the cluster based on the basic vehicle information of the vehicles in the cluster, and determining the average speed of the vehicles in the cluster, the average speed of large vehicles and the average speed of small vehicles in the cluster in combination with the speed information; determining the number difference between large vehicles and small vehicles in the cluster based on the number of large vehicles and the number of small vehicles; determining the speed difference between large vehicles and small vehicles in the cluster based on the average speed of large vehicles and the average speed of small vehicles; determining the traffic congestion coefficient of the cluster based on the number difference, the speed difference, the total number of vehicles and the average speed of vehicles.

[0095] In one embodiment, the traffic jam coefficient is positively correlated with the total number of vehicles and the difference in number, and negatively correlated with the difference in vehicle speed and the average vehicle speed.

[0096] In one embodiment, a first product between the total number of vehicles and the number difference may be determined, a second product between the speed difference and the average vehicle speed may be determined, and a traffic congestion coefficient may be determined based on a ratio between the first product and the second product.

[0097] In one embodiment, a hyperbolic function may be applied to the ratio of the first product to the second product to obtain the traffic congestion coefficient.

[0098] In one embodiment, the traffic congestion coefficient of any cluster i can be determined according to the following formula: :

[0099]

[0100] Among them, i represents any cluster. represents the traffic congestion coefficient of cluster i. a represents large vehicles in the cluster. b represents small vehicles in the cluster. Represents the total number of vehicles in cluster i. represents the average speed of vehicles in cluster i. represents the number of large vehicles in cluster i, represents the number of small vehicles in cluster i. represents the average speed of large vehicles in cluster i. represents the average speed of small vehicles in cluster i. th() represents a hyperbolic function, which is used for positive correlation normalization.

[0101] It can be understood that for any cluster, the larger the total number of vehicles, the more vehicles there are on the road at the same time, and the more likely it is to have a traffic jam, so the traffic jam coefficient and the total number of vehicles in cluster i The smaller the average speed of vehicles on the road in the cluster, the more likely it is to be congested, so the congestion coefficient and the average speed of vehicles in cluster i Since there may be some large buses and trucks on a specific road, the greater the difference in the number of large vehicles and small vehicles in the cluster, the smaller the speed difference between large vehicles and small vehicles in the cluster, indicating a greater possibility of collective traffic jams. Therefore, the traffic jam coefficient The ratio of the quantity difference to the speed difference There is a positive correlation.

[0102] In the above embodiment, the number difference between large vehicles and small vehicles in the cluster is determined based on the number of large vehicles and the number of small vehicles, the speed difference between large vehicles and small vehicles in the cluster is determined based on the average speed of large vehicles and the average speed of small vehicles, and the traffic congestion coefficient of the cluster is determined based on the number difference, the speed difference, the total number of vehicles and the average speed of vehicles, which can accurately determine the traffic congestion coefficient of the cluster.

[0103] In one embodiment, the load factor of the cluster is determined based on basic vehicle information and time information of the vehicles in the cluster, including: determining the total number of vehicles and the number of large vehicles in the cluster based on the basic vehicle information of the vehicles in the cluster, and determining the time point of the cluster based on the time information of the vehicles in the cluster; determining the load factor of the cluster based on the proportion of the number of large vehicles to the total number of vehicles; determining the load factor difference based on the load factor of the cluster and the load factor of an adjacent cluster; determining the proximity of the cluster to night based on the time point of the cluster; determining the load factor of the cluster based on the load factor difference, the proximity to night, the number of large vehicles and the total number of vehicles.

[0104] The night proximity refers to the proximity between the time point of the cluster and the night.

[0105] In one embodiment, the adjacent clusters may be the two clusters before and after a certain cluster. In other embodiments, the adjacent clusters may also be the four clusters before and after a certain cluster, without limitation.

[0106] In one embodiment, an average value of the load factors of each adjacent cluster may be determined, and then the load factor difference may be determined based on the difference between the load factor of the cluster and the average value of the load factors of the adjacent clusters.

[0107] In one embodiment, the time point of the cluster may be determined according to the average value of the time points of each vehicle in the cluster.

[0108] In one embodiment, the proximity of the clusters to nighttime may be determined based on the difference between the time point of the cluster and the reference time point.

[0109] In one embodiment, the reference time point may be 12 o'clock, and the proximity of the cluster to night is determined according to the difference between the time point of the cluster and 12 o'clock.

[0110] In one embodiment, the load factor is positively correlated with the proximity of night. The load factor is positively correlated with the total number of vehicles. The load factor is positively correlated with the number of large vehicles. The load factor is negatively correlated with the difference in load factors.

[0111] In one embodiment, the load factor of the cluster can be determined based on the ratio of the night proximity to the load factor difference multiplied by the number of large vehicles and the total number of vehicles. In one embodiment, the load factor of the cluster can be obtained by taking a hyperbolic function of the result of multiplying the ratio of the night proximity to the load factor difference multiplied by the number of large vehicles and the total number of vehicles.

[0112] In one embodiment, the load factor of the cluster may be determined according to the following formula:

[0113]

[0114] Among them, i represents any cluster. represents the load factor of cluster i. represents the time point of cluster i. represents the load factor of cluster i. Represents the average load factor of the adjacent clusters of cluster i. represents the total number of vehicles in cluster i. a represents a large vehicle within the cluster. Represents the number of large vehicles in cluster i. th() represents a hyperbolic function, which is used for positive correlation normalization.

[0115] It can be understood that the difference between the time point of the cluster and the reference time point 12 The larger the value, the closer the time inside the cluster is to night, and the difference between the load factor of the cluster and the average load factor of the adjacent clusters The smaller it is, the closer the proportion of large vehicles in the cluster is to that in the adjacent cluster. and The ratio between The larger the value, the larger the load factor is. The larger the load factor is, the larger the load on the road is. and The more large vehicles there are in a cluster, the greater the load on the road caused by the vehicles in the cluster. Therefore, the load factor of cluster i is and the number of large vehicles in cluster i The more the total number of vehicles in the cluster, the greater the load of the vehicles in the cluster on the road. Therefore, the load coefficient of cluster i is and the total number of vehicles in cluster i There is a positive correlation.

[0116] In the above embodiment, the load factor of the cluster can be accurately determined according to the load factor difference, the night proximity, the number of large vehicles and the total number of vehicles.

[0117] In one embodiment, the vehicle information includes basic vehicle information and time information; determining the density of traffic on the road based on the vehicle information, including: clustering the vehicles on the road based on the time information to obtain multiple clusters; determining the total number of vehicles in each cluster based on the basic vehicle information; determining a maximum cluster from multiple clusters based on the total number of vehicles in each cluster; determining, for each maximum cluster, based on the total number of vehicles, a change in the total number of vehicles between the maximum cluster and its adjacent maximum clusters, and determining a time difference between the maximum cluster and its adjacent maximum clusters based on the time information; determining the density of traffic on the road based on the change in the total number of vehicles corresponding to each maximum cluster, the time difference and the total number of vehicles in the maximum cluster.

[0118] Among them, the change in the total number of vehicles is used to characterize the difference between the total number of vehicles in the two maximum clusters and the total number of vehicles in the cluster between the two maximum clusters.

[0119] In one embodiment, if the total number of vehicles in a cluster is greater than the total number of vehicles in each of two adjacent clusters, the cluster is determined to be a maximum cluster, that is, the total number of vehicles in the maximum cluster is greater than the total number of vehicles in each of two adjacent clusters.

[0120] In one embodiment, the adjacent maximum cluster of a maximum cluster may be a maximum cluster that is closest in time to the maximum cluster.

[0121] In the above embodiment, for each maximum cluster, the change in the total number of vehicles between the maximum cluster and the adjacent maximum clusters is determined based on the total number of vehicles, and the time difference between the maximum cluster and the adjacent maximum clusters is determined based on the time information. Finally, based on the change in the total number of vehicles corresponding to each maximum cluster, the time difference and the total number of vehicles in the maximum cluster, the traffic density on the road can be accurately determined.

[0122] In one embodiment, based on the total number of vehicles, the change in the total number of vehicles between the maximum cluster and the adjacent maximum clusters of the maximum cluster is determined, including: determining the mean of the total number of vehicles in the clustering clusters between the maximum cluster and the adjacent maximum clusters of the maximum cluster as the first mean; determining the mean of the total number of vehicles in the maximum cluster and the adjacent maximum clusters of the maximum cluster as the second mean; and determining the change in the total number of vehicles between the maximum cluster and the adjacent maximum clusters of the maximum cluster based on the ratio between the first mean and the second mean.

[0123] In one embodiment, the traffic density corresponding to the maximum cluster can be determined by dividing the product of the total number of vehicles corresponding to the maximum cluster and the total number of vehicles in the maximum cluster by the time difference between the maximum cluster and the adjacent maximum cluster. Then, the traffic density on the road is determined based on the average of the traffic density corresponding to each maximum cluster.

[0124] In one embodiment, the density of traffic on the road can be determined according to the following formula:

[0125]

[0126] Among them, CM represents the density of traffic on the road, and j represents any maximum cluster. represents the adjacent maximal cluster of the maximal cluster. J represents the number of maximal clusters. Represents the total number of vehicles in the maximum cluster j. represents the adjacent maximal cluster of maximal cluster j The total number of vehicles in . Represents the maximum cluster j and the adjacent maximum clusters of maximum cluster j The mean of the total number of vehicles in the clusters between . Represents the maximum cluster j and the adjacent maximum clusters of maximum cluster j th() represents a hyperbolic function, which is used for positive correlation normalization.

[0127] It can be understood that the mean of the total number of vehicles in the clusters between the largest cluster and the adjacent largest cluster is Must be smaller than the mean of the total number of vehicles in the maximum cluster and the adjacent maximum clusters of the maximum cluster ,so It is obviously a proper fraction (i.e. a fraction whose numerator is smaller than the denominator, i.e. smaller than 1), so the ratio The larger the value is, the closer the ratio is to 1, indicating that the total number of vehicles in each cluster between the maximum cluster and the adjacent maximum cluster is smaller than the difference between the maximum cluster and the adjacent maximum cluster, which means that the traffic flow is larger and the difference is not large. Therefore, the traffic density CM is related to the ratio. The smaller the time difference between the maximum cluster and the adjacent maximum cluster, the closer the maximum cluster is to the adjacent maximum cluster, which indicates that the traffic density on the road is higher. Therefore, the traffic density CM is related to the time difference. The more vehicles in the largest cluster, the higher the density of traffic flow. Therefore, the density of traffic flow CM is negatively correlated with the total number of vehicles in the largest cluster. There is a positive correlation.

[0128] In the above embodiment, the mean of the total number of vehicles in the clusters between the maximum cluster and the adjacent maximum cluster of the maximum cluster is determined as the first mean, and the mean of the total number of vehicles in the maximum cluster and the adjacent maximum cluster of the maximum cluster is determined as the second mean. According to the ratio between the first mean and the second mean, the change of the total number of vehicles between the maximum cluster and the adjacent maximum cluster of the maximum cluster can be accurately determined. Then, according to the accurate change of the total number of vehicles, the time difference and the total number of vehicles in the maximum cluster, the density of traffic on the road can be accurately determined.

[0129] In one embodiment, a cleaning and maintenance environment assessment result of a road is determined based on the degree of wear, the actual degree of damage, and the density of traffic, including: determining a cleaning and maintenance environment assessment value of the road based on the difference between the degree of wear and the actual degree of damage, and the density of traffic; comparing the cleaning and maintenance environment assessment value with a preset threshold, and determining the cleaning and maintenance environment assessment result of the road based on the comparison result.

[0130] In one embodiment, the road cleaning and maintenance environment assessment value may be determined based on the ratio of the difference between the degree of wear and tear and the actual degree of damage to the traffic density.

[0131] In one embodiment, the road cleaning and maintenance environment evaluation value may be determined according to the following formula:

[0132]

[0133] Among them, YH represents the road cleaning and maintenance environment assessment value. MS represents the degree of wear and tear of the road by vehicles. SU represents the actual degree of damage to the road. CM represents the traffic density of the road. th() represents a hyperbolic function, which is used for positive correlation normalization.

[0134] It can be understood that the smaller the difference between the degree of wear and tear of the road caused by vehicles and the actual degree of damage to the road, the closer the actual degree of damage to the road caused by vehicles, indicating that the road maintenance is not timely, therefore, the clean maintenance environment assessment value is positively correlated with the difference between the degree of wear and the actual degree of damage. The higher the traffic density, the worse the road cleanliness and maintenance conditions, and the higher the maintenance difficulty, therefore, the clean maintenance environment assessment value is negatively correlated with the traffic density.

[0135] In one embodiment, the cleaning and maintenance environment evaluation value is compared with a preset threshold value. If the comparison result is that the cleaning and maintenance environment evaluation value is greater than the preset threshold value, the cleaning and maintenance environment evaluation result of the road is a first result; if the comparison result is that the cleaning and maintenance environment evaluation value is less than or equal to the preset threshold value, the cleaning and maintenance environment evaluation result of the road is a second result. The cleaning and maintenance environment represented by the first result is better than the cleaning and maintenance environment represented by the second result.

[0136] In one embodiment, the first result indicates that the cleaning and maintenance environment is good, and the second result indicates that the cleaning and maintenance environment is poor.

[0137] In the above embodiment, the cleaning and maintenance environment evaluation value of the road can be accurately determined based on the difference between the degree of wear and the actual degree of damage, as well as the traffic density, and then the cleaning and maintenance environment evaluation value is compared with a preset threshold value. Based on the comparison result, the cleaning and maintenance environment evaluation result of the road can be accurately determined.

[0138] In one embodiment, the cleaning and maintenance environment evaluation result includes a first result and a second result; the cleaning and maintenance environment represented by the first result is better than the cleaning and maintenance environment represented by the second result; the method also includes: generating a cleaning and maintenance strategy for the road according to the cleaning and maintenance environment evaluation result; the cleaning and maintenance strategy includes the cleaning and maintenance frequency and the cleaning and maintenance resource input; the cleaning and maintenance frequency corresponding to the first result is greater than the cleaning and maintenance frequency corresponding to the second result; the cleaning and maintenance resource input corresponding to the first result is less than the cleaning and maintenance resource input corresponding to the second result.

[0139] In one embodiment, the input amount of cleaning and maintenance resources may include the input amount of resources such as manpower and equipment required for cleaning and maintenance.

[0140] It is understandable that roads with poor cleaning and maintenance environments are not easy to maintain, so a lower cleaning and maintenance frequency is required, but more manpower and equipment are required in each cleaning and maintenance process; for roads with good cleaning and maintenance environments, a higher cleaning and maintenance frequency can be used, but less manpower and equipment can be invested in each cleaning and maintenance process.

[0141] like Figure 5As shown, it is a schematic diagram of the overall process of the road cleaning and maintenance method in the above embodiment, which includes the following steps: step 502, obtaining a road image of the road and vehicle information of vehicles passing on the road; step 504, determining the actual damage degree of the road according to the road image; step 506, determining the wear degree of the vehicle on the road according to the vehicle information; step 508, determining the traffic density on the road according to the vehicle information; step 510, determining the road cleaning and maintenance environment assessment result according to the wear degree, the actual damage degree and the traffic density; step 512, generating a cleaning and maintenance strategy for the road according to the cleaning and maintenance environment assessment result.

[0142] In the above embodiment, a cleaning and maintenance strategy for the road can be accurately generated according to the cleaning and maintenance environment assessment result. The cleaning and maintenance strategy includes the cleaning and maintenance frequency and the cleaning and maintenance resource input, so that the road cleaning and maintenance can be carried out efficiently and with high quality.

[0143] In one embodiment, determining the actual degree of damage to a road based on a road image includes: converting the road image into a grayscale image; performing edge detection on the grayscale image to obtain road marking edges, road damage edges, and road material particle edges; analyzing the road marking edges, road damage edges, and road material particle edges, and determining the actual degree of damage to the road based on the analysis results.

[0144] In one embodiment, edge detection may use methods such as canny edge detection.

[0145] In the above embodiment, the road image is converted into a grayscale image, and edge detection is performed on the grayscale image to obtain the edges of road markings, the edges of damaged roads, and the edges of road material particles. The edges of road markings, the edges of damaged roads, and the edges of road material particles are analyzed, and the actual degree of damage to the road is determined based on the analysis results, which can accurately determine the actual degree of damage to the road.

[0146] In one embodiment, the edges of road markings, damaged edges of the road, and edges of road material particles are analyzed, and the actual degree of damage to the road is determined based on the analysis results, including: determining the integrity of the road markings based on the edges of the road markings; determining the size and degree of damage on the road based on the damaged edges of the road; determining the edge length and gradient of the road material particles based on the edges of the road material particles; determining the actual degree of damage to the road based on the integrity of the road markings, the size and degree of damage, and the edge length and gradient of the road material particles.

[0147] Among them, road material particles are particles of materials used to pave roads. For example, asphalt particles. Asphalt particles on roads will gradually wear away during use, causing the lines between particles to become less clear.

[0148] In the above embodiment, the integrity of the road markings is determined according to the edge of the road markings, the size and degree of damage on the road are determined according to the edge of the road damage, and the edge length and gradient of the road material particles are determined according to the edge of the road material particles. Finally, the actual degree of damage to the road can be accurately determined according to the integrity of the road markings, the size and degree of damage, and the edge length and gradient of the road material particles.

[0149] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0150] It should be noted that the data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0151] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0152] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

[0154] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0155] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A road cleaning and maintenance environment assessment method, characterized in that: The method comprises: Acquire a road image of a road and vehicle information of vehicles traveling on the road; determining an actual degree of damage to the road according to the road image; determining, based on the vehicle information, a degree of wear and tear caused by the vehicle on the road; Determining the density of traffic on the road according to the vehicle information; Determining a cleaning and maintenance environment assessment result of the road according to the degree of wear, the actual degree of damage and the traffic density; The vehicle information includes basic vehicle information, vehicle speed information and time information; and determining the degree of wear caused by the vehicle on the road according to the vehicle information includes: Clustering the vehicles on the road according to the time information to obtain a plurality of clusters; For each cluster, determine the traffic congestion coefficient of the cluster according to the basic vehicle information and the vehicle speed information of the vehicles in the cluster; Determining a load factor of the cluster according to the basic vehicle information and the time information of the vehicles in the cluster; Determining the degree of wear and tear caused by vehicles on the road according to the congestion coefficient and the load coefficient of each of the clusters; The determining the traffic congestion coefficient of the cluster according to the basic vehicle information and the vehicle speed information of the vehicles in the cluster includes: Determine the total number of vehicles, the number of large vehicles and the number of small vehicles in the cluster according to the basic vehicle information of the vehicles in the cluster, and determine the average speed of the vehicles, the average speed of large vehicles and the average speed of small vehicles in the cluster in combination with the vehicle speed information; Determine the difference between the number of large vehicles and the number of small vehicles in the cluster according to the number of large vehicles and the number of small vehicles; Determine the speed difference between the large vehicles and the small vehicles in the cluster according to the average speed of the large vehicles and the average speed of the small vehicles; Determining the traffic congestion coefficient of the cluster according to the quantity difference, the vehicle speed difference, the total number of vehicles and the average vehicle speed; The determining the load factor of the cluster according to the basic vehicle information and the time information of the vehicles in the cluster includes: Determine the total number of vehicles and the number of large vehicles in the cluster according to the basic vehicle information of the vehicles in the cluster, and determine the time point of the cluster according to the time information of the vehicles in the cluster; Determining the load factor of the cluster according to the proportion of the number of large vehicles to the total number of vehicles; Determining a load factor difference based on the load factor of the cluster and the load factors of adjacent clusters; Determining the proximity of the clusters to night based on the time points of the clusters; The load factor of the cluster is determined based on the load factor difference, the proximity of night, the number of large vehicles, and the total number of vehicles.

2. A road cleaning and maintenance environment assessment method according to claim 1, characterized in that: The vehicle information includes basic vehicle information and time information; and determining the density of traffic on the road according to the vehicle information includes: Clustering the vehicles on the road according to the time information to obtain a plurality of clusters; Determine the total number of vehicles in each of the clusters according to the basic information of the vehicles; Determine a maximum cluster from a plurality of clusters according to the total number of vehicles in each of the clusters; For each of the maximum clusters, respectively, according to the total number of vehicles, determine the change in the total number of vehicles between the maximum cluster and an adjacent maximum cluster of the maximum cluster, and determine the time difference between the maximum cluster and an adjacent maximum cluster of the maximum cluster according to the time information; The density of traffic on the road is determined according to the change in the total number of vehicles corresponding to each of the maximum clusters, the time difference and the total number of vehicles in the maximum clusters.

3. A road cleaning and maintenance environment assessment method according to claim 2, characterized in that: The determining, according to the total number of vehicles, a change in the total number of vehicles between the maximum cluster and an adjacent maximum cluster of the maximum cluster includes: Determine a mean of the total number of vehicles in the clusters between the maximum cluster and the adjacent maximum clusters of the maximum cluster as a first mean; Determine a mean of the total number of vehicles in the maximum cluster and the maximum clusters adjacent to the maximum cluster as a second mean; According to the ratio between the first mean and the second mean, the change in the total number of vehicles between the maximum cluster and the adjacent maximum clusters of the maximum cluster is determined.

4. A road cleaning and maintenance environment assessment method according to any one of claims 1 to 3, characterized in that: Determining the cleaning and maintenance environment assessment result of the road according to the wear degree, the actual damage degree and the traffic density includes: Determining a cleaning and maintenance environment assessment value of the road according to a difference between the wear degree and the actual damage degree, and the traffic density; The cleaning and maintenance environment evaluation value is compared with a preset threshold value, and the cleaning and maintenance environment evaluation result of the road is determined according to the comparison result.

5. A road cleaning and maintenance environment assessment method according to any one of claims 1 to 3, characterized in that: The cleaning and maintenance environment assessment results include a first result and a second result; The cleaning and maintenance environment represented by the first result is better than the cleaning and maintenance environment represented by the second result; The method further comprises: Generating a cleaning and maintenance strategy for the road according to the cleaning and maintenance environment assessment result; The cleaning and maintenance strategy includes the cleaning and maintenance frequency and the cleaning and maintenance resource input; the cleaning and maintenance frequency corresponding to the first result is greater than the cleaning and maintenance frequency corresponding to the second result; the cleaning and maintenance resource input corresponding to the first result is less than the cleaning and maintenance resource input corresponding to the second result.

6. A road cleaning and maintenance environment assessment method according to any one of claims 1 to 3, characterized in that: Determining the actual damage degree of the road according to the road image includes: Converting the road image into a grayscale image; Performing edge detection on the grayscale image to obtain road marking edges, road damage edges, and road material particle edges; The road marking edges, the damaged edges of the road and the edges of the road material particles are analyzed, and the actual damage degree of the road is determined according to the analysis results.

7. A road cleaning and maintenance environment assessment method according to claim 6, characterized in that: The analyzing the edges of the road markings, the damaged edges of the road and the edges of the road material particles, and determining the actual degree of damage to the road according to the analysis results, includes: Determining the integrity of the road markings according to the road marking edges; Determining the size and degree of damage on the road according to the damaged edge of the road; Determining edge length and gradient of the road material particles according to the edge of the road material particles; The actual degree of damage to the road is determined based on the integrity of the markings, the size and degree of damage to the road, and the edge length and gradient of the road material particles.

Images