A road construction progress tracking and monitoring method

Abstract

The present invention relates to the field of image processing technology, and more particularly to a method for tracking and monitoring road construction progress. The method comprises: acquiring a road construction image of a target road, determining a suspected road connected domain from the road construction image; determining a first probability that the suspected road connected domain is a road region; selecting a suspected road connected domain whose first probability is greater than or equal to a first threshold as a road region; determining a second probability that the road region is a paved road region based on the first probability and the grayscale values ​​of pixels in the road region, and selecting a road region whose second probability is greater than or equal to a second threshold as a paved road region; and determining a construction progress ratio of the target road in the road construction image based on a first sum of the first areas of all paved road regions in the road construction image and a second sum of the second areas of all road regions in the target road. The present invention improves the accuracy of results of tracking and monitoring road construction progress.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for tracking and monitoring road construction progress. Background Art

[0002] Road construction progress tracking and monitoring is a management activity that ensures project progress is on schedule and promptly identifies and resolves potential issues. Effective progress tracking and monitoring provides insight into actual road progress. Through real-time data collection, progress comparison, and quality control, road construction progress tracking and monitoring can optimize construction management, improve efficiency, and increase safety, ensuring on-time and high-quality project completion.

[0003] In some scenarios, when tracking and monitoring road construction progress, drones and other devices are often used to capture road images. These images are then segmented using the K-means clustering algorithm to identify paved road areas. This is because the K-means clustering algorithm only clusters pixels of the same color. Since non-road areas in an image may have similar colors to paved roads, using color to filter these areas is inaccurate and can easily misidentify paved areas, leading to inaccurate results in tracking and monitoring road construction progress. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy of the results of tracking and monitoring the progress of road construction, the purpose of the present invention is to provide a method for tracking and monitoring the progress of road construction. The technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for tracking and monitoring road construction progress, comprising: acquiring a road construction image of a target road, determining a suspected road connected domain from the road construction image; determining a minimum circumscribed rectangle of the suspected road connected domain and a plurality of straight line segments of the suspected road connected domain; determining, based on a first parameter of the minimum circumscribed rectangle and a second parameter of each of the straight line segments, that the suspected road connected domain is a road surface morphology regularization analysis parameter of a road area; the first parameter being a first length of the longest side and a second length of the shortest side of the minimum circumscribed rectangle; the second parameter being the length of the straight line segment; determining, based on a grayscale value of a pixel point in the suspected road connected domain and a first number of pixel points, the suspected road connected domain; The road connected domain is a road area with a roadbed color contrast parameter; a first possibility that the suspected road connected domain is a road area is determined based on the pavement morphology regularity analysis parameter and the roadbed color contrast parameter; a suspected road connected domain with a first possibility greater than or equal to a first threshold is selected as a road area; a second possibility that the road area is a paved road area is determined based on the first possibility of the road area and the grayscale value of the pixel points in the road area, and a road area with a second possibility greater than or equal to a second threshold is selected as a paved road area; and a construction progress ratio of a target road in the road construction image is determined based on a first sum of the first areas of all paved road areas in the road construction image and a second sum of the second areas of all road areas in the target road.

[0006] Optionally, determining a suspected road connected domain from a road construction image includes: performing operations on the road construction image using a K-means clustering image segmentation algorithm to obtain multiple clusters; performing operations on two adjacent road construction images in the clusters using an image alignment operation, and recording an area where the overlapping connected domains in the two adjacent road construction images have changed as a suspected changed area; and determining the connected domain corresponding to the suspected changed area as the suspected road connected domain.

[0007] Optionally, determining the minimum circumscribed rectangle of the suspected road connected domain and multiple straight line segments of the suspected road connected domain includes: determining the minimum convex polygon containing all pixel points in the suspected road connected domain; determining a rectangle parallel to the edge by rotating each side of the minimum convex polygon; calculating the third area of ​​each rotated rectangle, and selecting the rectangle with the smallest third area as the minimum circumscribed rectangle; using an edge detection algorithm to operate on the suspected road connected domain to obtain multiple edge points; converting each edge point into polar coordinates, and accumulating the number of occurrences for each polar coordinate position in the Hough space; identifying the position with the highest cumulative number of occurrences for each polar coordinate position in the Hough space, and determining the straight line segments in the suspected road connected domain.

[0008] Optionally, determining that the suspected road connected domain is a road surface morphology regularity analysis parameter of the road area based on the first parameter of the minimum circumscribed rectangle and the second parameter of each straight line segment includes: calculating a first ratio between the first length of the longest side of the minimum circumscribed rectangle and the second length of the shortest side of the minimum circumscribed rectangle; superimposing the lengths of all straight line segments in the suspected road connected domain to obtain a first superposition value; calculating a second ratio of the first superposition value to the fourth area of ​​the suspected road connected domain, and a first product between the first ratio and the second ratio; and normalizing the first product to obtain the road surface morphology regularity analysis parameter of the road area.

[0009] Optionally, determining the roadbed color contrast parameter that the suspected road connected domain is a road area based on the grayscale values ​​of the pixels and the first number of pixels in the suspected road connected domain includes: superimposing the grayscale values ​​of all pixels in the suspected road connected domain to obtain a second superimposed value, and a third ratio between the second superimposed value and the first number; calculating the first difference between the grayscale value of each pixel in the suspected road connected domain and the third ratio, and superimposing each first difference to obtain a third superimposed value; calculating a fourth ratio between the third superimposed value and the first number; and performing inverse proportional normalization processing on the fourth ratio to obtain the roadbed color contrast parameter that the suspected road connected domain is a road area.

[0010] Optionally, determining the first possibility that the suspected road connected domain is a road area based on the pavement morphology regularity analysis parameters and the roadbed color contrast parameters includes: calculating the second product between the pavement morphology regularity analysis parameters and the roadbed color contrast parameters; normalizing the second product to obtain the first possibility that the suspected road connected domain is a road area.

[0011] Optionally, based on the first possibility of the road area and the grayscale values ​​of the pixels in the road area, determining the second possibility that the road area is a paved road area includes: calculating a first average value of the grayscale values ​​of all pixels in the road area, and a fifth ratio between the first possibility and the first average value; normalizing the fifth ratio to obtain the second possibility that the road area is a paved road area.

[0012] Optionally, determining the construction progress ratio of the target road in the road construction image based on the first sum of the first areas of all paved road areas in the road construction image and the second sum of the second areas of all road areas in the target road includes: determining a sixth ratio between the first sum and the second sum as the construction progress ratio of the target road in the road construction image.

[0013] Optionally, obtaining the road construction image of the target road includes: using a drone to photograph the target road at the same position of the target road every day to obtain a construction image; and using a mean filtering algorithm to operate on the construction image to obtain the road construction image.

[0014] The present invention has the following beneficial effects: first, a road construction image of a target road is acquired, and a suspected road connected domain is determined from the road construction image; then, a first possibility that the suspected road connected domain is a road area is determined based on a first parameter of a minimum circumscribed rectangle of the suspected road connected domain, a second parameter of a plurality of straight line segments of the suspected road connected domain, a grayscale value of pixels in the suspected road connected domain, and a first number of pixels; and the suspected road connected domain whose first possibility is greater than or equal to a first threshold is selected as a road area; second, a second possibility that the road area is a paved road area is determined based on the first possibility of the road area and the grayscale value of pixels in the road area, and a road area whose second possibility is greater than or equal to a second threshold is selected as a paved road area; finally, a construction progress ratio of the target road in the road construction image is determined based on a first sum of the first areas of all paved road areas in the road construction image and a second sum of the second areas of all road areas in the target road.

[0015] In this way, embodiments of the present invention can utilize various features of the suspected road connected domain to further screen road and paved road areas. For example, paved road areas are determined using the first parameter of the minimum circumscribed rectangle within the suspected road connected domain, the second parameter of multiple straight line segments within the suspected road connected domain, the grayscale value of pixels within the suspected road connected domain, and the first number of pixels. Finally, the construction progress ratio of the target road in the road construction image is determined based on the first sum of the first areas of all paved road areas and the second sum of the second areas of all road areas within the target road. This improves the accuracy of distinguishing between road and non-road areas, avoids misjudgment of paved road areas, and thus improves the accuracy of road construction progress tracking and monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 any creative work.

[0017] Figure 1 The present invention provides a flowchart of a method for tracking and monitoring road construction progress according to an embodiment of the present invention.

[0018] Figure 2 The present invention provides a schematic structural diagram of a road construction progress tracking and monitoring system according to an embodiment of the present invention.

[0019] Figure 3 A schematic structural diagram of a road construction progress tracking and monitoring system provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0020] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method for tracking and monitoring road construction progress according to the present invention, including its specific implementation, structure, features, and effectiveness. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0021] 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.

[0022] The specific scheme of the road construction progress tracking and monitoring method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0023] Example 1:

[0024] See also Figure 1 , which shows a flow chart of a road construction progress tracking and monitoring method provided by one embodiment of the present invention, including:

[0025] S101: Acquire a road construction image of a target road, and determine a suspected road connected region from the road construction image.

[0026] Specifically, the target road refers to a road for which road construction progress tracking is required. As an optional embodiment of the present invention, obtaining a road construction image of the target road includes: first, using a drone to photograph the target road at the same location on the target road every day to obtain a construction image; and then, performing a mean filter operation on the construction image to obtain a road construction image.

[0027] In this embodiment of the present invention, a drone is used to capture the entirety of the target road at the same location daily, capturing the entirety of the completed road. This produces a corresponding road construction image for each day. Furthermore, to improve image processing efficiency, this embodiment of the present invention also applies a mean filter to the road construction images to remove noise. Mean filtering is a well-known technique, and the specific method is not described here.

[0028] Furthermore, to accurately identify paved road areas, the present invention first applies a K-means clustering image segmentation algorithm to the road construction images to obtain several connected domains. As road construction progresses daily, the road area gradually changes. This change is exploited to align two adjacent road construction images, yielding several changing suspected road regions. Because non-road areas can also undergo minor changes due to segmentation errors, the characteristics of the road connected domains within these changing non-road areas are used for further screening. The shape of the road area tends to be long and narrow, and the grayscale values ​​of different pixels in the road area are relatively small, and the edges are relatively regular, that is, the edge lines of the road area are mostly straight lines. Therefore, the above features are used to screen the road area. After obtaining the road area, because the unpaved roads are compacted earth roads, their color is close to white, so the grayscale values ​​of the pixels belonging to the unpaved area in the road construction image are higher, while the paved roads are paved with asphalt, and the color of asphalt is black, so the grayscale values ​​of the pixels belonging to the paved road area in the road construction image are lower. This feature is then used to screen out the paved road area.

[0029] Furthermore, as road construction progresses each day, the area of ​​paved roads gradually changes, which manifests itself in road construction images as changes in the same area of ​​adjacent road construction images. Using these features, we can identify several suspected change regions in each road construction image.

[0030] Furthermore, as an optional embodiment of the present invention, determining a suspected road connected domain from a road construction image includes: performing operations on the road construction image using a K-means clustering image segmentation algorithm to obtain multiple clusters; performing operations on two adjacent road construction images in the cluster using an image alignment operation, and recording the area where the overlapping connected domains in the two adjacent road construction images have changed as a suspected changed area; and determining the connected domain corresponding to the suspected changed area as the suspected road connected domain.

[0031] Specifically, the embodiment of the present invention uses the K-means clustering image segmentation algorithm to perform operations on each road construction image according to the preset number of clusters to obtain a number of clusters, each cluster corresponding to a connected domain. Among them, the preset number of clusters in the embodiment of the present invention can be 4, which is used as an example for description. After clustering to obtain multiple clusters, the embodiment of the present invention uses the first cluster as the first cluster. As an example, we use image alignment to align the first road construction image and The road construction image is operated and the The areas where the overlapping connected domains in the road construction images have changed are recorded as suspected changed areas.

[0032] The connected domains where all suspected change regions are located are recorded as suspected road connected domains. Each road construction image is operated according to the above process to obtain several suspected change regions and corresponding suspected road connected domains for each road construction image.

[0033] S102: Determine a first possibility that the suspected road connected domain is a road area based on a first parameter of a minimum circumscribed rectangle of the suspected road connected domain, second parameters of a plurality of straight line segments of the suspected road connected domain, the grayscale values ​​of pixels in the suspected road connected domain, and a first number of pixels.

[0034] Specifically, the embodiments of the present invention use the above process to obtain several suspected road connected domains for each road construction image. Because non-road areas can also undergo slight changes due to algorithmic segmentation errors, the presence of non-road areas within suspected paved road connected domains necessitates further screening based on the characteristics of the suspected road connected domains. Suspected road connected domains tend to be regular and elongated, with relatively uniform colors and minimal grayscale differences between pixels. The embodiments of the present invention utilize these characteristics to calculate the first probability that the suspected road connected domain is a road area, further deriving the road area.

[0035] Furthermore, for any suspected road connected domain in a road construction image, the closer its shape is to a long strip, the more extensible and narrow the suspected road connected domain is in space, and this shape is usually consistent with the characteristics of a road area. Therefore, in this case, the more likely the suspected road connected domain is to be determined as a road area. And roads usually present relatively straight and regular edge contours, especially when roads are manually planned and designed, they often show higher straight line features. Therefore, areas with regular edges and tending to straight line shapes are often highly consistent with the characteristics of road areas. Therefore, the embodiment of the present invention calculates the road surface morphology regularity analysis parameters of each suspected road connected domain as a road area based on the above characteristics.

[0036] Furthermore, the real road area is usually paved with uniform materials, and its color presents a relatively single and stable feature. Due to the lack of significant color changes on the road surface, the grayscale value difference between different pixel points located in the road area in the road construction image is relatively small, and usually remains within a relatively uniform range. This similarity of grayscale values ​​is an important identification feature of the road area, and forms a clear contrast with areas with large grayscale fluctuations in the surrounding environment, such as grassland, buildings or water areas. By analyzing the grayscale value differences in the road construction image, the road area can be effectively identified, further improving the accuracy of road detection. Based on the above characteristics, the embodiment of the present invention calculates the roadbed color contrast parameters of each suspected road connected domain to be a road area. Finally, based on the pavement morphology regularity analysis parameters and the roadbed color contrast parameters, the first possibility that the suspected road connected domain is a road area is calculated.

[0037] Furthermore, as an optional embodiment of the present invention, determining the first possibility that the suspected road connected domain is a road area based on the first parameter of the minimum circumscribed rectangle of the suspected road connected domain, the second parameter of the multiple straight line segments of the suspected road connected domain, the grayscale value of the pixels in the suspected road connected domain, and the first number of pixels includes: determining the minimum circumscribed rectangle of the suspected road connected domain and the multiple straight line segments of the suspected road connected domain; determining the pavement morphology regularity analysis parameters that the suspected road connected domain is a road area based on the first parameter of the minimum circumscribed rectangle and the second parameter of each straight line segment; determining the roadbed color contrast parameters that the suspected road connected domain is a road area based on the grayscale value of the pixels in the suspected road connected domain and the first number of pixels; and determining the first possibility that the suspected road connected domain is a road area based on the pavement morphology regularity analysis parameters and the roadbed color contrast parameters. The first parameter is the first length of the longest side and the second length of the shortest side of the minimum circumscribed rectangle; the second parameter is the length of the straight line segment.

[0038] Specifically, an embodiment of the present invention uses a minimum bounding rectangle algorithm to calculate each suspected road connected domain in each road construction image to obtain the minimum bounding rectangle of all suspected road connected domains in each road construction image. As an optional embodiment of the present invention, determining the minimum bounding rectangle of the suspected road connected domain and multiple straight line segments of the suspected road connected domain includes: determining a minimum convex polygon containing all pixel points in the suspected road connected domain; determining a rectangle parallel to the edge by rotating each side of the minimum convex polygon; calculating the third area of ​​each rotated rectangle, and selecting the rectangle with the smallest third area as the minimum bounding rectangle; using an edge detection algorithm to calculate the suspected road connected domain to obtain multiple edge points; converting each edge point into polar coordinates, and accumulating the number of occurrences of each polar coordinate position in Hough space; identifying the position with the highest number of cumulative occurrences of each polar coordinate position in Hough space, and determining the straight line segments in the suspected road connected domain.

[0039] Specifically, the embodiment of the present invention is based on the Road construction image Take the suspected road connectivity domain as an example, first find the Road construction image The smallest convex polygon that contains all the pixels in the suspected road connected area. Then, by rotating each side of the smallest convex polygon, find a rectangle parallel to the side that can completely surround the point set. Then, calculate the area of ​​each rotated rectangle and select the rectangle with the smallest area as the final minimum enclosing rectangle. Then output the first Road construction image The coordinates, width and height of the minimum circumscribed rectangle of the suspected road connected domain.

[0040] More specifically, the embodiment of the present invention uses the Hough line detection algorithm to calculate the suspected road connected domain of each road construction image to obtain a number of straight line segments of the suspected road connected domain of each road construction image. Road construction image Take the suspected road connected domain as an example, first use the edge detection algorithm to Road construction image The suspected road connected domain is operated to obtain several edge points. Each edge point is then converted to polar coordinates. The number of occurrences of each polar coordinate position is then accumulated in Hough space. The straight lines in the road construction image are then found by identifying the highest value of the accumulated number of occurrences of each polar coordinate position in Hough space. The straight line segments are extracted based on the highest value of the accumulated number of occurrences of each polar coordinate position in Hough space and the straight line segments are drawn back to the first Road construction image suspected road connectivity domain.

[0041] Furthermore, as an optional embodiment of the present invention, determining that the suspected road connected domain is a road surface morphology regularity analysis parameter of the road area based on the first parameter of the minimum circumscribed rectangle and the second parameter of each straight line segment includes: calculating a first ratio between the first length of the longest side of the minimum circumscribed rectangle and the second length of the shortest side of the minimum circumscribed rectangle; superimposing the lengths of all straight line segments in the suspected road connected domain to obtain a first superposition value; calculating a second ratio of the first superposition value to the fourth area of ​​the suspected road connected domain, and a first product between the first ratio and the second ratio; and normalizing the first product to obtain the road surface morphology regularity analysis parameter of the road area.

[0042] Specifically, the embodiment of the present invention is based on the Road construction image For example, the suspected road connectivity domain Road construction image The specific calculation formula corresponding to the pavement morphology regularization analysis parameters of the suspected road connectivity domain is as follows:

[0043]

[0044] In the above formula, Indicates the Road construction image The suspected road connectivity domain is the pavement morphology regularity analysis parameter of the road area. Indicates the Road construction image The length of the longest side of the minimum circumscribed rectangle of a suspected road connected domain. Indicates the Road construction image The length of the shortest side of the minimum circumscribed rectangle of a suspected road connectivity domain. Indicates the Road construction image The number of straight line segments in the suspected road connectivity domain. No. Road construction image The first suspected road connectivity domain The length of a straight line segment. Indicates the Road construction image The fourth area of ​​the suspected road connected domain. Represents a linear normalization function, which is used to Perform normalization processing.

[0045] It is worth noting that Road construction image The more the shape of the suspected road connected domain tends to be long and strip-shaped, the Road construction image The greater the possibility that the suspected road connected domain is a road area. Road construction image The more straight line segments there are in the suspected road connected domain, and the longer the straight line segments are, the Road construction image The more regular the suspected road connected domain, the more likely it is a road area. Thus, through the above embodiment of the present invention, each suspected road connected domain in each road construction image is calculated according to the above process to obtain the road surface morphology regularity analysis parameters for each suspected road connected domain in each road construction image.

[0046] Furthermore, as an optional embodiment of the present invention, determining the roadbed color contrast parameter of the suspected road connected domain as a road area based on the grayscale values ​​of the pixels in the suspected road connected domain and the first number of pixels includes: superimposing the grayscale values ​​of all pixels in the suspected road connected domain to obtain a second superimposed value, and a third ratio between the second superimposed value and the first number; calculating the first difference between the grayscale value of each pixel in the suspected road connected domain and the third ratio, and superimposing each first difference to obtain a third superimposed value; calculating the fourth ratio between the third superimposed value and the first number; and performing inverse proportional normalization processing on the fourth ratio to obtain the roadbed color contrast parameter of the suspected road connected domain as a road area.

[0047] Specifically, the embodiment of the present invention still takes the Road construction image For example, the suspected road connectivity domain Road construction image The specific calculation formula corresponding to the roadbed color contrast parameter of the suspected road connected domain is as follows:

[0048]

[0049] In the above formula, Indicates the Road construction image The suspected road connectivity domain is the roadbed color contrast parameter of the road area. Indicates the Road construction image The first number of pixels in the suspected road connected domain. Indicates the Road construction image The first suspected road connectivity domain The gray value of a pixel. represents the exponential function with natural numbers as base, Used for Perform inverse proportional normalization. Represents the absolute value function, which is used to Take the absolute value.

[0050] It is worth noting that if Road construction image The smaller the difference in grayscale values ​​between different pixels in a suspected road connected domain, the greater the likelihood that the suspected road connected domain is a road area. Furthermore, this embodiment of the present invention performs the above-described operation on each suspected road connected domain in each road construction image to obtain a roadbed color contrast parameter indicating that each suspected road connected domain in each road construction image is a road area.

[0051] Furthermore, as an optional embodiment of the present invention, determining the first possibility that the suspected road connected domain is a road area based on the pavement morphology regularity analysis parameters and the roadbed color contrast parameters includes: calculating the second product between the pavement morphology regularity analysis parameters and the roadbed color contrast parameters; normalizing the second product to obtain the first possibility that the suspected road connected domain is a road area.

[0052] Specifically, the embodiment of the present invention still takes the Road construction image For example, the connected area of ​​suspected unpaved roads Road construction image The specific calculation formula corresponding to the final probability that a suspected road connected region is a road area is as follows:

[0053]

[0054] In the above formula, Indicates the Road construction image The suspected road connected domain is the first possibility of the road area. Indicates the Road construction image The suspected road connectivity domain is the pavement morphology regularity analysis parameter of the road area. Indicates the Road construction image The suspected road connectivity domain is the roadbed color contrast parameter of the road area. Represents a linear normalization function, which is used to Perform normalization processing.

[0055] In this way, the embodiment of the present invention performs calculations on each suspected road connected domain in each road construction image according to the above process to obtain a first possibility that each suspected road connected domain in each road construction image is a road area.

[0056] S103: Select the suspected road connected region with a first possibility greater than or equal to a first threshold as the road area.

[0057] Specifically, after the embodiment of the present invention calculates the first possibility through the above process, it then uses the threshold analysis method to obtain the road area. Road construction image Taking a suspected road connected domain as an example, the process of judging whether it belongs to the road area is as follows: First, set the first threshold , then the Road construction image The first possibility that the suspected road connected domain is the road area Extraction and reuse With the first threshold Perform threshold comparison, if , then Road construction image The suspected road connected domains are road regions. At this point, the road regions in the road construction image are obtained. Through the above process, the embodiment of the present invention obtains several road regions for each road construction image. The first threshold value can be determined based on actual conditions and is not limited in this embodiment of the present invention.

[0058] S104 , determining a second possibility that the road area is a paved road area based on the first possibility of the road area and the grayscale values ​​of the pixels in the road area, and selecting a road area with the second possibility greater than or equal to a second threshold as a paved road area.

[0059] Specifically, because unpaved roads are compacted dirt roads, which are close to white in color, the grayscale values ​​of pixels in unpaved areas in road construction images are higher. Paved road areas are paved with asphalt, which is black in color, so the grayscale values ​​of pixels in paved areas are lower. The present invention utilizes these features to calculate the likelihood that a road area is paved, thereby filtering out paved areas.

[0060] Furthermore, as an optional embodiment of the present invention, determining the second possibility that the road area is a paved road area based on the first possibility of the road area and the grayscale values ​​of the pixels in the road area includes: calculating a first average value of the grayscale values ​​of all pixels in the road area, and a fifth ratio between the first possibility and the first average value; and normalizing the fifth ratio to obtain the second possibility that the road area is a paved road area.

[0061] Specifically, the embodiment of the present invention is still based on the first Road construction image For example, the road area Road construction image The specific calculation formula for the probability that a road area is a paved road area is as follows:

[0062]

[0063] In the above formula, Indicates the Road construction image Road areas are a second possibility for paved road areas. Indicates the Road construction image A road area is the first possibility for a road area. Indicates the Road construction image The mean grayscale value of all pixels in the road area. Represents a linear normalization function, which is used to Perform normalization processing.

[0064] It is worth noting that and Inversely proportional, because the paved area is paved with asphalt, the color is close to black, and the average gray value of all pixels in the area is small, so the Road construction image The larger the mean gray value of all pixels in the road area is, the Road construction image In this embodiment of the present invention, all road areas in each road construction image are calculated according to the above process to obtain the second probability that all road areas in each road construction image are paved roads.

[0065] Furthermore, the embodiment of the present invention then uses the threshold analysis method to obtain the paved road area. Road construction image Taking a road area as an example, the process of determining whether it belongs to a paved road area is as follows: First, set the second threshold ; Then put the Road construction image The second possibility is that the road area is a paved road connected area Extraction is then performed using With the second threshold Perform threshold comparison, if , then Road construction image The road areas are paved road areas. So far, the paved road areas are obtained. Through the above process, several paved road areas are obtained for each road construction image.

[0066] S105 : Determine a construction progress ratio of the target road in the road construction image based on a first sum of first areas of all paved road regions in the road construction image and a second sum of second areas of all road regions in the target road.

[0067] Specifically, through the above process of the embodiment of the present invention, the paved road area of ​​each road construction image is obtained. Here, the construction progress ratio of each road construction image is calculated using the ratio of the area of ​​the paved road area to the area of ​​all road areas.

[0068] Furthermore, as an optional embodiment of the present invention, determining the construction progress ratio of the target road in the road construction image based on the first sum of the first areas of all paved road areas in the road construction image and the second sum of the second areas of all road areas in the target road includes: determining a sixth ratio between the first sum and the second sum as the construction progress ratio of the target road in the road construction image.

[0069] Specifically, the embodiment of the present invention is based on the As an example, the road construction image The specific calculation formula for the construction progress ratio of a road construction image is:

[0070]

[0071] In the above formula, Indicates the Construction progress ratio of the road construction images. Indicates the The first sum value of the first areas of all paved road areas in the road construction image. Indicates the a second sum value of the second areas of all road regions in the road construction image;

[0072] It is worth noting that The larger the sum of the areas of all paved road areas in a road construction image is, the The larger the construction progress ratio of the road construction image, the higher the construction progress ratio of the road construction image. Calculate each road construction image according to the above process of the present invention to obtain the construction progress ratio of each road construction image.

[0073] Embodiments of the present invention can utilize various features of suspected road connected domains to further screen road and paved road areas. For example, paved road areas are determined using the first parameter of the minimum circumscribed rectangle within the suspected road connected domain, the second parameter of multiple straight line segments within the suspected road connected domain, the grayscale value of pixels within the suspected road connected domain, and the first number of pixels. Finally, the construction progress ratio of a target road in a road construction image is determined based on the first sum of the first areas of all paved road areas and the second sum of the second areas of all road areas within the target road. This improves the accuracy of distinguishing between road and non-road areas, avoids misjudgment of paved road areas, and thus enhances the accuracy of road construction progress tracking and monitoring results.

[0074] Example 2:

[0075] Corresponding to the road construction progress tracking and monitoring method provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a road construction progress tracking and monitoring system, which is used to execute the above road construction progress tracking and monitoring method. Figure 2 A schematic diagram of a road construction progress tracking and monitoring system according to another embodiment of the present invention is shown in FIG. Figure 2 As shown. The road construction progress tracking and monitoring system 200 includes: an acquisition module 201, configured to acquire a road construction image of a target road and determine a suspected road connected domain from the road construction image; a determination module 202, configured to determine a first possibility that the suspected road connected domain is a road region based on a first parameter of a minimum circumscribed rectangle of the suspected road connected domain, second parameters of a plurality of straight line segments of the suspected road connected domain, grayscale values ​​of pixels in the suspected road connected domain, and a first number of pixels; a selection module 203, configured to select a suspected road connected domain whose first possibility is greater than or equal to a first threshold as a road region; the determination module 202 is further configured to determine a second possibility that the road region is a paved road region based on the first possibility of the road region and the grayscale values ​​of pixels in the road region, and select a road region whose second possibility is greater than or equal to a second threshold as a paved road region; and the determination module 202 is further configured to determine a construction progress ratio of a target road in the road construction image based on a first sum of first areas of all paved road regions in the road construction image and a second sum of second areas of all road regions in the target road.

[0076] Embodiments of the present invention can utilize various features of suspected road connected domains to further screen road and paved road areas. For example, paved road areas are determined using the first parameter of the minimum circumscribed rectangle within the suspected road connected domain, the second parameter of multiple straight line segments within the suspected road connected domain, the grayscale value of pixels within the suspected road connected domain, and the first number of pixels. Finally, the construction progress ratio of a target road in a road construction image is determined based on the first sum of the first areas of all paved road areas and the second sum of the second areas of all road areas within the target road. This improves the accuracy of distinguishing between road and non-road areas, avoids misjudgment of paved road areas, and thus enhances the accuracy of road construction progress tracking and monitoring results.

[0077] Example 3:

[0078] Corresponding to the road construction progress tracking and monitoring method provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a road construction progress tracking and monitoring system, which is used to execute the above road construction progress tracking and monitoring method. Figure 3 A schematic diagram of a road construction progress tracking and monitoring system according to another embodiment of the present invention is shown in FIG. Figure 3 The road construction progress tracking and monitoring system may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302. The memory 302 is used to store computer programs that can be run on the processor 301. The processor 301 is used to execute the programs stored in the memory 302 to achieve the above Figure 1 The various steps in the method embodiment are described above. Memory 302 may be either transient or persistent storage. The application stored in memory 302 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for a road construction progress tracking and monitoring system.

[0079] Furthermore, the processor 301 can be configured to communicate with the memory 302, and execute a series of computer-executable instructions stored in the memory 302 on the road construction progress tracking and monitoring system. The road construction progress tracking and monitoring system can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0080] Specifically in this embodiment, the road construction progress tracking and monitoring system includes 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 bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1The various steps in the method embodiment have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described again here.

[0081] It should be noted that the road construction progress tracking and monitoring system provided by the embodiment of the present invention and the road construction progress tracking and monitoring method provided by the embodiment of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned road construction progress tracking and monitoring method, and has the same or similar beneficial effects, and the repetitions will not be repeated.

[0082] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A road construction progress tracking and monitoring method, characterized in that: include: Acquire a road construction image of a target road, and determine a suspected road connected region from the road construction image; Determine a minimum circumscribed rectangle of the suspected road connected domain and a plurality of straight line segments of the suspected road connected domain; determine a pavement morphology regularity analysis parameter indicating that the suspected road connected domain is a road region based on a first parameter of the minimum circumscribed rectangle and a second parameter of each of the straight line segments; the first parameter is a first length of the longest side and a second length of the shortest side of the minimum circumscribed rectangle; the second parameter is the length of the straight line segment; determine a roadbed color contrast parameter indicating that the suspected road connected domain is a road region based on the grayscale value of pixels and a first number of pixels in the suspected road connected domain; determine a first possibility that the suspected road connected domain is a road region based on the pavement morphology regularity analysis parameter and the roadbed color contrast parameter; Selecting a suspected road connected region where the first possibility is greater than or equal to a first threshold as the road area; determining, based on the first possibility of the road area and the grayscale values ​​of pixels in the road area, a second possibility that the road area is a paved road area, and selecting a road area where the second possibility is greater than or equal to a second threshold as the paved road area; determining a construction progress ratio of a target road in the road construction image based on a first sum of first areas of all paved road regions in the road construction image and a second sum of second areas of all road regions in the target road; The method for obtaining the road morphology regularity analysis parameter is as follows: calculating a first ratio between a first length of the longest side of the minimum circumscribed rectangle and a second length of the shortest side of the minimum circumscribed rectangle; superimposing the lengths of all straight line segments in the suspected road connected domain to obtain a first superposition value; calculating a second ratio of the first superposition value to a fourth area of ​​the suspected road connected domain, and a first product of the first ratio and the second ratio; and normalizing the first product to obtain the road morphology regularity analysis parameter of the road area. Among them, the method for obtaining the roadbed color contrast parameter is: superimposing the grayscale values ​​of all pixels in the suspected road connected domain to obtain a second superimposed value, and a third ratio between the second superimposed value and the first number; calculating the first difference between the grayscale value of each pixel in the suspected road connected domain and the third ratio, and superimposing each first difference to obtain a third superimposed value; calculating the fourth ratio between the third superimposed value and the first number; performing inverse proportional normalization processing on the fourth ratio to obtain the roadbed color contrast parameter of the suspected road connected domain as a road area.

2. The road construction progress tracking and monitoring method according to claim 1, characterized in that: Determining a suspected road connected area from the road construction image includes: Performing a K-means clustering image segmentation algorithm on the road construction image to obtain a plurality of clusters; Performing an image alignment operation on two adjacent road construction images in the cluster, and recording a region where the overlapping connected domains of the two adjacent road construction images have changed as a suspected changed region; The connected domain corresponding to the suspected change area is determined as the suspected road connected domain.

3. The road construction progress tracking and monitoring method according to claim 1 is characterized in that: The determining of the minimum circumscribed rectangle of the suspected road connected region and the plurality of straight line segments of the suspected road connected region includes: Determine a minimum convex polygon containing all pixels in the suspected road connected domain; By rotating each side of the minimum convex polygon, a rectangle parallel to the side is determined; Calculating the third area of ​​each rotated rectangle, and selecting the rectangle with the smallest third area as the minimum circumscribed rectangle; Using an edge detection algorithm to calculate the suspected road connected domain to obtain multiple edge points; Convert each edge point to polar coordinates and accumulate the number of occurrences for each polar coordinate position in Hough space; The position with the highest cumulative occurrence of each polar coordinate position in the Hough space is identified to determine a straight line segment in the suspected road connected domain.

4. The road construction progress tracking and monitoring method according to claim 1, characterized in that: The first possibility of determining that the suspected road connected region is a road area based on the road surface morphology regularity analysis parameter and the roadbed color contrast parameter includes: Calculating a second product between the pavement morphology regularity analysis parameter and the roadbed color contrast parameter; The second product is normalized to obtain a first possibility that the suspected road connected region is a road area.

5. The road construction progress tracking and monitoring method according to claim 1, characterized in that: The second possibility of determining that the road area is a paved road area according to the first possibility of the road area and the grayscale values ​​of the pixels in the road area includes: Calculating a first average value of grayscale values ​​of all pixels in the road area and a fifth ratio between the first likelihood and the first average value; Normalizing the fifth ratio to obtain a second possibility that the road area is a paved road area.

6. The road construction progress tracking and monitoring method according to claim 1, characterized in that: Determining the construction progress ratio of the target road in the road construction image according to a first sum of first areas of all paved road regions in the road construction image and a second sum of second areas of all road regions in the target road includes: A sixth ratio between the first sum and the second sum is determined as a construction progress ratio of the target road in the road construction image.

7. The road construction progress tracking and monitoring method according to claim 1, characterized in that: Acquiring a road construction image of a target road includes: Using a drone to photograph the target road at the same location on the target road every day to obtain a construction image; A mean filter algorithm is used to operate the construction image to obtain the road construction image.

Images