Urban traffic intelligent patrol method based on visual large model
Through the intelligent urban traffic inspection method based on visual big model, the acquisition sequence is set using road traffic data and common data to conduct intelligent inspection of urban roads, solving the problems of inflexible patrols, high cost and lag in the existing technology, and realizing the Efficient and intelligent urban road patrol and repair.
Patent Information
- Application Number
- CN202411770304.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-04
- Publication Date
- 2025-02-18
AI Technical Summary
The existing intelligent urban traffic inspection technology has problems such as fixed patrol, the inability to take into account multiple lanes at the same time, the cost of patrols is high and there is lag.
The intelligent urban traffic inspection method based on visual large models is adopted. By obtaining road traffic data and road common data, setting up a collection sequence, collecting, detecting, and repairing urban road surface images, and combining three-dimensional models to show the degree of damage.
It has achieved orderly collection of urban roads, improved patrol efficiency, reduced patrol costs, and achieved timely repair and intelligent visualization of damaged urban road areas.
Smart Images
Figure CN119479304A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of urban traffic, and in particular is an intelligent urban traffic inspection method based on a large visual model. Background Art
[0002] Urban transportation refers to public travel and passenger and freight transportation in the road (ground, underground, elevated, waterway, cableway, etc.) system in the city (including urban areas and suburbs). Before vehicles were used as a means of transportation, urban public travel was mainly based on walking, riding livestock, sedan chairs, etc. Urban transportation refers to the flow and interaction between different modes of transportation such as vehicles, pedestrians and non-motorized vehicles in the urban environment. It covers the planning and management of roads, public transportation systems, traffic signals, parking facilities and related infrastructure, aiming to achieve efficient, safe and sustainable development of transportation. Good management of urban transportation not only affects the city's traffic efficiency and residents' travel convenience, but also is related to environmental protection, economic development and the optimization of the overall functions of the city. The current urban traffic intelligent patrol technology mainly collects traffic data in real time through monitoring cameras and sensors to identify traffic flow, violations and road damage.
[0003] In the prior art, the inspection of urban roads is usually carried out in a fixed manner, and the inspection vehicle is driven for a long time during the inspection. The inspection vehicle cannot take into account the road conditions of multiple lanes at the same time during each inspection, and multiple lanes of the same road need to be inspected multiple times, which increases the inspection cost of urban roads. In addition, the current inspection method has a lag. When problems are found during road inspections, staff need to be dispatched to conduct on-site surveys before maintenance can be carried out. In order to solve the above technical problems, the present invention proposes an urban traffic intelligent inspection method based on a large visual model. Summary of the invention
[0004] The purpose of the present invention is to propose an intelligent urban traffic inspection method based on a large visual model to solve the problems raised in the above background technology.
[0005] The technical problems to be solved by the present invention are: How to realize intelligent inspection of urban road traffic based on visual big model.
[0006] In order to achieve the above object, the present invention adopts the following technical solutions: The urban traffic intelligent patrol method based on the visual big model is as follows: Step S100, obtaining road traffic data and road commonality data of urban roads; Step S200, setting a collection sequence of road surface images corresponding to urban roads based on road flow data and road commonality data, and collecting road surface images corresponding to urban roads in sequence through the collection sequence; Step S300, detecting the road surface image corresponding to the urban road to obtain damaged area information of the road surface image corresponding to the urban road; Step S400, obtaining the degree of damage of the damaged area in the road surface image corresponding to the urban road based on the damaged area information and the road traffic data analysis, and repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage; Step S500, combining the three-dimensional model of the urban road and mapping the degree of damage to the three-dimensional model of the urban road for display.
[0007] Furthermore, the road traffic data are the daily traffic volume and time period traffic volume of urban roads in the past month; The road commonality data includes the number of times the urban roads are shared as co-linear roads, as well as the length and number of lanes of the roads as co-linear roads.
[0008] Furthermore, the step S200 includes the following sub-steps: Step S2001, obtaining the road traffic data of the urban road, obtaining the daily traffic volume and time period traffic volume of the urban road in the past month, adding and averaging the daily traffic volume to obtain the average daily traffic volume RLi of the urban road in the past month, where i is the number of the urban road; Step S2002, then obtaining the road commonality data of the urban roads, and obtaining the number of collinearity GCi, road length CDi and number of lanes DSi of the urban roads as collinear roads; Step S2003, the road supervision value DJi of the urban road is calculated by the formula, and the specific formula is as follows: DJi=RLi×a1+GCi×a2+DSi×a3+CDi×a4; where a1, a2, a3 and a4 are all weight coefficients with fixed values, and a1>a2>a3>a4; Step S2004, comparing the road supervision value with the road supervision threshold, and determining whether the priority level of the urban road is the first priority level, the second priority level, or the third priority level; Step S2005, traverse and compare the road supervision values of urban roads to obtain the maximum value among the road supervision values, take the urban road corresponding to the maximum value among the road supervision values as the collection object, and take any end of the urban road as the starting end of the collection sequence; Step S2006, when the collection of the city road as the starting end is completed, the priority levels of other city roads connected to the city road are obtained, and the city road with the highest priority is selected as the next collection object according to the priority levels. Similarly, the collection objects are arranged in order in the set, and the collection sequence of the road surface images corresponding to the city roads can be obtained; Step S2007, obtaining the traffic flow of any city road in the past month, traversing and comparing the traffic flow of the city road in the past month, obtaining the minimum value of the traffic flow of the city road in the time period, and taking the time period corresponding to the minimum value of the traffic flow of the time period as the collection time period of the city road; Similarly, the acquisition time periods of all urban roads are obtained according to the above steps, and the mode of the acquisition time periods is taken as the working time period of the road surface image corresponding to the urban road.
[0009] Further, the priority of the first priority level is higher than that of the second priority level, and the priority of the second priority level is higher than that of the third priority level.
[0010] Furthermore, the step S300 includes the following sub-steps: Step S310, converting the road surface image corresponding to the urban road into a grayscale image; Step S320: if the grayscale image is not damaged, no operation is performed; if the grayscale image is damaged, proceed to the next step; Step S330, calculating the damaged affected area of the damaged area in the grayscale image corresponding to the urban road; Step S340, calculating the damage depth of the damaged area in the road surface image corresponding to the urban road based on the grayscale image; Step S350: Record the damaged affected area and the maximum pothole depth as damaged area information of the damaged area.
[0011] Furthermore, the step S330 includes the following sub-steps: Step S331, converting the grayscale image into a binary image, and obtaining edge pixel points of the damaged area corresponding to the damaged condition in the binary image; Step S332, connecting the edge pixels one by one to obtain a contour map of the damaged area in the road surface image corresponding to the urban road, constructing a damaged impact area corresponding to the damaged area based on the contour map, and calculating the damaged impact area of the damaged impact area; Step S333: when the damaged affected area is less than or equal to the damaged affected area threshold, the corresponding road surface image is deleted; when the damaged affected area is greater than the damaged affected area threshold, the damaged affected area is recorded in the damaged area information of the corresponding road surface image of the urban road.
[0012] Furthermore, the step S340 includes the following sub-steps: Step S341, obtaining the grayscale value of each pixel in the damaged area, and counting the maximum grayscale value and the minimum grayscale value of the pixels in the damaged area; Step S343, calculating the maximum pothole depth of the damaged area by combining the maximum grayscale value and the minimum grayscale value.
[0013] Furthermore, the calculation process of the damaged impact area is as follows: Obtain the contour map of the damaged area, and draw four groups of straight lines tangent to the outermost edge points of the contour map from the top, bottom, left and right directions respectively. The area enclosed by the four groups of straight lines is the damaged impact area. The damaged impact area of the damaged impact area is calculated using the rectangular area formula.
[0014] Furthermore, the step S400 includes the following sub-steps: Step S410, obtaining a traffic flow coefficient of the urban road corresponding to the damaged area according to the average daily traffic flow; Step S420, calculating the damage hazard value of the damaged area in the road surface image corresponding to the urban road by a formula, the specific formula is as follows: CD=(MJ×j1+SD×j2)×CLX;wherein, MJ is the area of the damaged area, SD is the maximum pothole depth, CLX is the traffic flow coefficient, j1 and j2 are weight coefficients with fixed values, j2>j1; Step S430, determining the damage hazard degree of the damaged area in the road surface image corresponding to the urban road according to the damaged interval to which the damage hazard value belongs; Step S440: repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage.
[0015] Furthermore, the process of obtaining the traffic flow coefficient is as follows: If the average daily traffic volume is less than the first traffic volume threshold, the traffic volume coefficient of the urban road is Y1; If the average daily traffic volume is greater than or equal to the first traffic volume threshold and less than the second traffic volume threshold, the traffic volume coefficient of the urban road is Y2; If the average daily traffic volume is greater than or equal to the second traffic volume threshold, the traffic volume coefficient of the urban road is Y3; wherein the first traffic volume threshold is less than the second traffic volume threshold, Y1<Y2<Y3; The process of determining the degree of damage is as follows: If the damage hazard value belongs to the third damage interval, the damage hazard level of the damaged area is a high damage hazard level; If the damage hazard value belongs to the second damage interval, the damage hazard level of the damaged area is the medium damage hazard level; If the damage hazard value belongs to the first damage interval, the damage hazard level of the damaged area is a low damage hazard level; The endpoint value of the third damaged interval is greater than the endpoint value of the second damaged interval, and the endpoint value of the second damaged interval is greater than the endpoint value of the first damaged interval.
[0016] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention sets a collection sequence of road surface images corresponding to urban roads based on road flow data and road commonality data, collects road surface images corresponding to urban roads in sequence through the collection sequence, realizes orderly collection of road surface images corresponding to urban roads, improves inspection efficiency and reduces inspection costs; 2. The present invention detects the road surface image corresponding to the urban road, obtains the damaged area information of the road surface image corresponding to the urban road, obtains the damage hazard degree of the damaged area in the road surface image corresponding to the urban road based on the damaged area information and road traffic data analysis, and repairs the damaged area in the road surface image corresponding to the urban road according to the damage hazard degree, thereby realizing rapid detection of the road surface image corresponding to the urban road, and realizing timely and orderly repair of the damaged area of the urban road according to the damage degree; 2. The present invention combines the three-dimensional model of the urban road and maps the degree of damage to the three-dimensional model of the urban road for display, thereby realizing intelligent visualization of the damaged area in the urban road. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.
[0018] Figure 1 is the overall system block diagram of the present invention; Figure 2 This is a schematic diagram of the structure of the co-linear road in the present invention; Figure 3 It is a structural schematic diagram of the damaged area in the present invention; Figure 4 for Figure 3 The enlarged view of point A in the middle; Figure 5 It is a schematic diagram of the structure of the computing device in the present invention. DETAILED DESCRIPTION
[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] Embodiment 1: See also Figure 1-Figure 4As shown, the technical solution provided by the present invention is: an intelligent urban traffic inspection method based on a visual large model, and the method is specifically as follows: Step S100, obtaining road traffic data and road commonality data of urban roads; It should be noted that the road traffic data are the daily and time period traffic volumes of urban roads in the past month, and the road commonality data are the number of times urban roads are shared as co-linear roads, as well as the length and number of lanes of co-linear roads. Figure 2 As shown, the collinear road can be understood as the necessary road from one location to another, from point A to point B or from point A to point C. The urban road between point E and point F is the necessary road, and the number of times the urban road between point E and point F is shared as a collinear road is 2. Similarly, Figure 2 The urban road between point E and point F is used as a collinear road for a total of 8 times. In practice, there may be no road commonality data for the urban road, that is, the urban road is not a collinear road.
[0021] Step S200, setting a collection sequence of road surface images corresponding to urban roads based on road traffic data and road commonality data, and collecting road surface images corresponding to urban roads in sequence through the collection sequence; in practice, the collection of road surface images corresponding to urban roads can be achieved by using drones; In this embodiment, step S200 includes the following sub-steps: Step S2001, obtaining the road traffic data of the urban road, obtaining the daily traffic volume and time period traffic volume of the urban road in the past month, adding and averaging the daily traffic volume to obtain the average daily traffic volume RLi of the urban road in the past month, where i is the number of the urban road; Step S2002, then obtaining the road commonality data of the urban roads, and obtaining the number of collinearity GCi, road length CDi and number of lanes DSi of the urban roads as collinear roads; Step S2003, the road supervision value DJi of the urban road is calculated by the formula, and the specific formula is as follows: DJi=RLi×a1+GCi×a2+DSi×a3+CDi×a4; where a1, a2, a3 and a4 are all weight coefficients with fixed values, and a1>a2>a3>a4; Step S2004, comparing the road supervision value with a road supervision threshold, the road supervision threshold includes a first road supervision threshold and a second road supervision threshold, the first road supervision threshold is less than the second road supervision threshold; If the road supervision value is greater than the second road supervision threshold, the priority level of the urban road is the first priority level; if the road supervision value is less than the second road supervision threshold and greater than or equal to the first road supervision threshold, the priority level of the urban road is the second priority level; if the road supervision value is less than the first road supervision threshold, the priority level of the urban road is the third priority level; wherein the priority level of the first priority level is higher than the priority level of the second priority level, and the priority level of the second priority level is higher than the priority level of the third priority level; Step S2005, traverse and compare the road supervision values of urban roads to obtain the maximum value among the road supervision values, take the urban road corresponding to the maximum value among the road supervision values as the collection object, and take any end of the urban road as the starting end of the collection sequence; Step S2006, when the collection of the city road as the starting end is completed, the priority levels of other city roads connected to the city road are obtained, and the city road with the highest priority is selected as the next collection object according to the priority levels. Similarly, the collection objects are arranged in order in the set, and the collection sequence of the road surface images corresponding to the city roads can be obtained; Step S2007, obtaining the traffic flow of any city road in the past month, traversing and comparing the traffic flow of the city road in the past month, obtaining the minimum value of the traffic flow of the city road in the time period, and taking the time period corresponding to the minimum value of the traffic flow of the time period as the collection time period of the city road; Similarly, the acquisition time periods of all urban roads are obtained according to the above steps, and the mode of the acquisition time periods is taken as the working time period of the road surface image corresponding to the urban road.
[0022] Step S300, detecting the road surface image corresponding to the urban road to obtain damaged area information of the road surface image corresponding to the urban road; In this embodiment, step S300 includes the following sub-steps: Step S310, converting the road surface image corresponding to the urban road into a grayscale image; Specifically, the grayscale calculation formula G=0.3×R+0.587×G+0.114×B is used to convert the pixel value of each pixel in the road surface image into the corresponding grayscale value; Step S320: if there is no damage in the grayscale image, no operation is performed; if there is damage in the grayscale image, the process proceeds to the next step; wherein the damage refers to the presence of potholes or potholes on the corresponding road surface of the urban road; Among them, whether there is damage in the grayscale image can be determined by the difference of pixels in the grayscale image; Step S330, calculating the damaged affected area of the damaged area in the grayscale image corresponding to the urban road; The sub-steps of step S330 are specifically as follows: Step S331, converting the grayscale image into a binary image, and obtaining edge pixel points of the damaged area corresponding to the damaged condition in the binary image; Specifically, the Sobel operator is used to calculate the gradient of the grayscale image I in the horizontal direction Gx and the vertical direction Gy, and the edge strength of each pixel is calculated according to Gx and Gy; Furthermore, a rectangular coordinate system is established for the grayscale image I. Each pixel in the grayscale image has a coordinate (x, y). In the grayscale image I, I(x, y) represents the grayscale value of the pixel at the coordinate (x, y). The horizontal Sobel operator convolution kernel is Gx= , the vertical Sobel operator convolution kernel is Gy= , according to Gx and Gy, we can get the edge strength G of each pixel = When the edge strength is greater than the edge threshold, the pixel value of the pixel is set to 255. When the pixel value is 255, the pixel is white, indicating an edge pixel. When the edge strength is less than or equal to the edge threshold, the pixel value of the pixel is set to 0. When the pixel value is 0, the pixel is black, indicating a non-edge pixel. Step S332, connecting the edge pixels one by one to obtain a contour map of the damaged area in the road surface image corresponding to the urban road, constructing a damaged impact area corresponding to the damaged area based on the contour map, and calculating the damaged impact area of the damaged impact area, specifically: Obtain the contour map of the damaged area, and draw four groups of straight lines tangent to the outermost edge points of the contour map from the four directions of top, bottom, left and right. The area enclosed by the four groups of straight lines is the damaged impact area. The damaged impact area of the damaged impact area is calculated using the rectangular area formula; Step S333: when the damaged affected area is less than or equal to the damaged affected area threshold, the corresponding road surface image is deleted; when the damaged affected area is greater than the damaged affected area threshold, the damaged affected area is recorded in the damaged area information of the corresponding road surface image of the urban road; It should be explained that the damaged area threshold is used to exclude false positives caused by normal seams or slight unevenness; Step S340, calculating the damage depth of the damaged area in the road surface image corresponding to the urban road based on the grayscale image; In this embodiment, the damaged area is preferably a pit or a groove, and the damaged depth of the pit or the groove is calculated according to the gray value; The sub-steps of step S340 are specifically as follows: Step S341, obtaining the grayscale value of each pixel in the damaged area, and counting the maximum grayscale value and the minimum grayscale value of the pixels in the damaged area; Step S343, calculating the maximum pothole depth of the damaged area by combining the maximum grayscale value and the minimum grayscale value; Specifically, the grayscale value corresponding to each pixel in the grayscale image is compared with the maximum grayscale value to obtain the difference between the grayscale value corresponding to each pixel and the maximum grayscale value. The difference is recorded as the grayscale difference. The grayscale difference is traversed and compared to obtain the maximum value of the grayscale difference. The maximum value of the grayscale difference is the maximum pothole depth. Step S350: Record the damaged affected area and the maximum pothole depth as damaged area information of the damaged area.
[0023] Step S400, obtaining the degree of damage of the damaged area in the road surface image corresponding to the urban road based on the damaged area information and the road traffic data analysis, and repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage; In this embodiment, step S400 includes the following sub-steps: Step S410, obtaining a traffic flow coefficient of the urban road corresponding to the damaged area according to the average daily traffic flow; If the average daily traffic volume is less than the first traffic volume threshold, the traffic volume coefficient of the urban road is Y1; if the average daily traffic volume is greater than or equal to the first traffic volume threshold and less than the second traffic volume threshold, the traffic volume coefficient of the urban road is Y2; if the average daily traffic volume is greater than or equal to the second traffic volume threshold, the traffic volume coefficient of the urban road is Y3; wherein the first traffic volume threshold is less than the second traffic volume threshold, Y1<Y2<Y3; Step S420, calculating the damage hazard value of the damaged area in the road surface image corresponding to the urban road by a formula, the specific formula is as follows: CD=(MJ×j1+SD×j2)×CLX;wherein, MJ is the area of the damaged area, SD is the maximum pothole depth, CLX is the traffic flow coefficient, j1 and j2 are weight coefficients with fixed values, j2>j1; Step S430, determining the damage hazard degree of the damaged area in the road surface image corresponding to the urban road according to the damaged interval to which the damage hazard value belongs; If the damage hazard value belongs to the third damage interval, the damage hazard level of the damaged area is a high damage hazard level; If the damage hazard value belongs to the second damage interval, the damage hazard level of the damaged area is the medium damage hazard level; If the damage hazard value belongs to the first damage interval, the damage hazard level of the damaged area is a low damage hazard level; The endpoint value of the third damaged interval is greater than the endpoint value of the second damaged interval, and the endpoint value of the second damaged interval is greater than the endpoint value of the first damaged interval; Step S440: repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage.
[0024] Step S500, combining the three-dimensional model of the urban road and mapping the damage degree to the three-dimensional model of the urban road for display; Among them, the three-dimensional model of the urban road is an existing technology. The three-dimensional model can be specifically referred to the layer in the navigation software, and the 3D stereoscopic road of the urban road can be obtained by modifying the layer; For example, a high degree of damage may be displayed by marking in red, a medium degree of damage may be displayed by marking in blue, and a low degree of damage may be displayed by marking in yellow.
[0025] In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.
[0026] Embodiment 2: Figure 3 The following is a schematic diagram of the structure of a computer device, such as Figure 3 As shown, the computer device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute the urban traffic intelligent inspection method based on the visual large model, the method comprising: obtaining the road flow data and road commonality data of the urban road; setting the acquisition sequence of the road surface image corresponding to the urban road based on the road flow data and the road commonality data, and sequentially collecting the road surface images corresponding to the urban road through the acquisition sequence; detecting the road surface image corresponding to the urban road to obtain the damaged area information of the road surface image corresponding to the urban road; obtaining the degree of damage of the damaged area in the road surface image corresponding to the urban road based on the damaged area information and the road flow data analysis, and repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage; combining the three-dimensional model of the urban road, and mapping the degree of damage to the three-dimensional model of the urban road for display.
[0027] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0028] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the urban traffic intelligent patrol method based on the visual large model provided by the above-mentioned methods, and the method includes: obtaining road flow data and road commonality data of urban roads; setting an acquisition sequence of road surface images corresponding to urban roads based on the road flow data and road commonality data, and sequentially acquiring road surface images corresponding to urban roads through the acquisition sequence; detecting the road surface images corresponding to urban roads to obtain damaged area information of the road surface images corresponding to urban roads; obtaining the degree of damage of the damaged area in the road surface images corresponding to urban roads based on the damaged area information and road flow data analysis, and repairing the damaged area in the road surface images corresponding to urban roads according to the degree of damage; combining with a three-dimensional model of the urban road, and mapping the degree of damage to the three-dimensional model of the urban road for display.
[0029] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned urban traffic intelligent patrol method based on visual large model, the method comprising: obtaining road flow data and road commonality data of urban roads; setting a collection sequence of road surface images corresponding to urban roads based on the road flow data and road commonality data, and collecting road surface images corresponding to urban roads in sequence through the collection sequence; detecting the road surface images corresponding to urban roads to obtain damaged area information of the road surface images corresponding to urban roads; obtaining the degree of damage of the damaged area in the road surface images corresponding to urban roads based on the damaged area information and road flow data analysis, and repairing the damaged area in the road surface images corresponding to urban roads according to the degree of damage; combining with a three-dimensional model of the urban road, and mapping the degree of damage to the three-dimensional model of the urban road for display.
[0030] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0031] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0032] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. An intelligent urban traffic inspection method based on a large visual model, characterized in that: The specific methods of urban traffic intelligent patrol are as follows: Step S100, obtaining road traffic data and road commonality data of urban roads; Step S200, setting a collection sequence of road surface images corresponding to urban roads based on road flow data and road commonality data, and collecting road surface images corresponding to urban roads in sequence through the collection sequence; Step S300, detecting the road surface image corresponding to the urban road to obtain damaged area information of the road surface image corresponding to the urban road; Step S400, obtaining the degree of damage of the damaged area in the road surface image corresponding to the urban road based on the damaged area information and the road traffic data analysis, and repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage; Step S500, combining the three-dimensional model of the urban road and mapping the degree of damage to the three-dimensional model of the urban road for display.
2. The urban traffic intelligent inspection method based on visual big model according to claim 1 is characterized in that: The road traffic data are the daily and period traffic volumes of urban roads in the past month; The road commonality data includes the number of times the urban roads are shared as co-linear roads, as well as the length and number of lanes of the roads as co-linear roads.
3. The urban traffic intelligent inspection method based on visual big model according to claim 2 is characterized in that: The step S200 includes the following sub-steps: Step S2001, obtaining the road traffic data of the urban road, obtaining the daily traffic volume and time period traffic volume of the urban road in the past month, adding and averaging the daily traffic volume to obtain the average daily traffic volume RLi of the urban road in the past month, where i is the number of the urban road; Step S2002, then obtaining the road commonality data of the urban roads, and obtaining the number of collinearity GCi, road length CDi and number of lanes DSi of the urban roads as collinear roads; Step S2003, the road supervision value DJi of the urban road is calculated by the formula, and the specific formula is as follows: DJi=RLi×a1+GCi×a2+DSi×a3+CDi×a4; where a1, a2, a3 and a4 are all weight coefficients with fixed values, and a1>a2>a3>a4; Step S2004, comparing the road supervision value with the road supervision threshold, and determining whether the priority level of the urban road is the first priority level, the second priority level, or the third priority level; Step S2005, traverse and compare the road supervision values of urban roads to obtain the maximum value among the road supervision values, take the urban road corresponding to the maximum value among the road supervision values as the collection object, and take any end of the urban road as the starting end of the collection sequence; Step S2006, when the collection of the city road as the starting end is completed, the priority levels of other city roads connected to the city road are obtained, and the city road with the highest priority is selected as the next collection object according to the priority levels. Similarly, the collection objects are arranged in order in the set, and the collection sequence of the road surface images corresponding to the city roads can be obtained; Step S2007, obtaining the traffic flow of any city road in the past month, traversing and comparing the traffic flow of the city road in the past month, obtaining the minimum value of the traffic flow of the city road in the time period, and taking the time period corresponding to the minimum value of the traffic flow of the time period as the collection time period of the city road; Similarly, the acquisition time periods of all urban roads are obtained according to the above steps, and the mode of the acquisition time periods is taken as the working time period of the road surface image corresponding to the urban road.
4. The urban traffic intelligent inspection method based on visual big model according to claim 3 is characterized in that: The first priority level has a higher priority than the second priority level, and the second priority level has a higher priority than the third priority level.
5. The urban traffic intelligent inspection method based on visual big model according to claim 3 is characterized in that: The step S300 includes the following sub-steps: Step S310, converting the road surface image corresponding to the urban road into a grayscale image; Step S320: if the grayscale image is not damaged, no operation is performed; if the grayscale image is damaged, proceed to the next step; Step S330, calculating the damaged affected area of the damaged area in the grayscale image corresponding to the urban road; Step S340, calculating the damage depth of the damaged area in the road surface image corresponding to the urban road based on the grayscale image; Step S350: Record the damaged affected area and the maximum pothole depth as damaged area information of the damaged area.
6. The urban traffic intelligent inspection method based on visual big model according to claim 5 is characterized in that: The step S330 includes the following sub-steps: Step S331, converting the grayscale image into a binary image, and obtaining edge pixel points of the damaged area corresponding to the damaged condition in the binary image; Step S332, connecting the edge pixels one by one to obtain a contour map of the damaged area in the road surface image corresponding to the urban road, constructing a damaged impact area corresponding to the damaged area based on the contour map, and calculating the damaged impact area of the damaged impact area; Step S333: when the damaged affected area is less than or equal to the damaged affected area threshold, the corresponding road surface image is deleted; when the damaged affected area is greater than the damaged affected area threshold, the damaged affected area is recorded in the damaged area information of the corresponding road surface image of the urban road.
7. The urban traffic intelligent inspection method based on visual big model according to claim 5 is characterized in that: The step S340 includes the following sub-steps: Step S341, obtaining the grayscale value of each pixel in the damaged area, and counting the maximum grayscale value and the minimum grayscale value of the pixels in the damaged area; Step S343, calculating the maximum pothole depth of the damaged area by combining the maximum grayscale value and the minimum grayscale value.
8. The urban traffic intelligent inspection method based on visual big model according to claim 6 is characterized in that: The calculation process of the damaged affected area is as follows: Obtain the contour map of the damaged area, and draw four groups of straight lines tangent to the outermost edge points of the contour map from the top, bottom, left and right directions respectively. The area enclosed by the four groups of straight lines is the damaged impact area. The damaged impact area of the damaged impact area is calculated using the rectangular area formula.
9. The urban traffic intelligent inspection method based on visual big model according to claim 5 is characterized in that: The step S400 includes the following sub-steps: Step S410, obtaining a traffic flow coefficient of the urban road corresponding to the damaged area according to the average daily traffic flow; Step S420, calculating the damage hazard value of the damaged area in the road surface image corresponding to the urban road by a formula, the specific formula is as follows: CD=(MJ×j1+SD×j2)×CLX;wherein, MJ is the area of the damaged area, SD is the maximum pothole depth, CLX is the traffic flow coefficient, j1 and j2 are weight coefficients with fixed values, j2>j1; Step S430, determining the damage hazard degree of the damaged area in the road surface image corresponding to the urban road according to the damaged interval to which the damage hazard value belongs; Step S440: repairing the damaged area in the road surface image corresponding to the urban road according to the degree of damage.
10. The urban traffic intelligent inspection method based on visual big model according to claim 9 is characterized in that: The process of obtaining the traffic flow coefficient is: If the average daily traffic volume is less than the first traffic volume threshold, the traffic volume coefficient of the urban road is Y1; If the average daily traffic volume is greater than or equal to the first traffic volume threshold and less than the second traffic volume threshold, the traffic volume coefficient of the urban road is Y2; If the average daily traffic volume is greater than or equal to the second traffic volume threshold, the traffic volume coefficient of the urban road is Y3; wherein the first traffic volume threshold is less than the second traffic volume threshold, Y1<Y2<Y3; The process of determining the degree of damage is as follows: If the damage hazard value belongs to the third damage interval, the damage hazard level of the damaged area is a high damage hazard level; If the damage hazard value belongs to the second damage interval, the damage hazard level of the damaged area is the medium damage hazard level; If the damage hazard value belongs to the first damage interval, the damage hazard level of the damaged area is a low damage hazard level; The endpoint value of the third damaged interval is greater than the endpoint value of the second damaged interval, and the endpoint value of the second damaged interval is greater than the endpoint value of the first damaged interval.