Regenerated asphalt mixing uniformity analysis method and system based on image recognition

Abstract

The invention discloses a recycled asphalt mixing uniformity analysis method and system based on image recognition. The method comprises the following steps: judging whether an image size difference value between any two first sub-images is greater than a preset size threshold value or not; if the size is not greater than the preset size threshold value, aggregating aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set; whether the number of target pixel point pairs meeting a preset condition is larger than a preset first number threshold value or not is judged, and the target aggregate pixel point pairs comprise target aggregate pixel points from two different target aggregate pixel point sets; and if the number is greater than the preset first number threshold value, generating an analysis result of uniform mixing of the recycled asphalt corresponding to the recycled asphalt image. Human subjective factors and aggregate distribution factors in a single particle size range can be avoided as far as possible, and the asphalt mixing uniformity can be conveniently and quickly detected.

Description

Technical Field

[0001] The present invention belongs to the technical field of recycled asphalt analysis, and particularly relates to a method and system for analyzing the mixing uniformity of recycled asphalt based on image recognition. Background Art

[0002] During the paving process of hot mix recycled asphalt mixture, segregation is likely to occur due to the uneven distribution of coarse and fine aggregates. The segregation of recycled asphalt mixture will cause the actual gradation and asphalt content to deviate seriously from the design values, resulting in uneven overall quality of the asphalt pavement. This will not only induce various early damages to the asphalt pavement, but also have an important impact on the long-term service performance of the pavement. Therefore, it is of great significance to analyze the mixing uniformity of recycled asphalt.

[0003] In the analysis of the mixing uniformity of recycled asphalt in the prior art, it is usually judged manually according to the aggregate distribution or the real-time aggregate distribution image is compared with the aggregate distribution image template, so as to realize the analysis of the mixing uniformity of recycled asphalt based on image recognition. Although these recognition methods have a relatively fast recognition speed, since there are various particle sizes of aggregates, the distribution of aggregates with various particle sizes may be different, resulting in low accuracy of these uniformity analysis methods. Summary of the Invention

[0004] The present invention provides a method and system for analyzing the mixing uniformity of recycled asphalt based on image recognition, which is used to solve the technical problem that the distribution of aggregates with various particle sizes may be different, resulting in low accuracy of the existing uniformity analysis methods.

[0005] In a first aspect, the present invention provides a method for analyzing the mixing uniformity of recycled asphalt based on image recognition, including: Obtaining a recycled asphalt image; Performing binarization processing on the recycled asphalt image according to different aggregate particle size ranges by using a preset processing strategy to obtain a recycled asphalt binarized image corresponding to the different particle size ranges; Dividing each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one set of image regions, wherein one set of image regions contains at least one recycled asphalt binarized image region obtained by dividing a recycled asphalt binarized image; Determining a minimum aggregate region in the first recycled asphalt binarized image region of each set of image regions, and intercepting at least one first sub-image containing only the minimum aggregate region, wherein the first recycled asphalt binarized image region is the recycled asphalt binarized image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binarized image region, and the minimum aggregate region is the smallest rectangular region containing all aggregate pixel points in the first recycled asphalt binarized image region; Determine whether the image size difference between any two first sub-images is greater than a preset size threshold; If it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set, where each target aggregate pixel point in a target aggregate pixel point set belongs to the same first sub-image; Determine whether the number of target pixel point pairs that meet the preset conditions is greater than a preset first quantity threshold, where the target aggregate pixel point pairs include target aggregate pixel points from two different target aggregate pixel point sets; If it is greater than the preset first quantity threshold, generate an analysis result of uniform mixing of the recycled asphalt corresponding to the recycled asphalt image.

[0006] In a second aspect, the present invention provides a recycled asphalt mixing uniformity analysis system based on image recognition, including: An acquisition module configured to acquire a recycled asphalt image; A preprocessing module configured to perform binarization processing on the recycled asphalt image according to different aggregate particle size ranges by using a preset processing strategy to obtain a recycled asphalt binarized image corresponding to the different particle size ranges; A partitioning module configured to partition each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one image region set, where an image region set contains at least one recycled asphalt binarized image region obtained by partitioning a recycled asphalt binarized image; An interception module configured to determine a minimum aggregate region in the first recycled asphalt binarized image region of each image region set and intercept at least one first sub-image that only contains the minimum aggregate region, where the first recycled asphalt binarized image region is the recycled asphalt binarized image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binarized image region, and the minimum aggregate region is the smallest rectangular region in the first recycled asphalt binarized image region that contains all aggregate pixel points; A first judgment module configured to judge whether the image size difference between any two first sub-images is greater than a preset size threshold; An aggregation module configured to, if it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set, where each target aggregate pixel point in a target aggregate pixel point set belongs to the same first sub-image; A second judgment module, configured to judge whether the number of target pixel point pairs meeting a preset condition is greater than a preset first quantity threshold, wherein the target aggregate pixel point pairs include target aggregate pixel points from two different target aggregate pixel point sets; A generation module, configured to generate an analysis result of uniform mixing of the recycled asphalt corresponding to the recycled asphalt image if it is greater than the preset first quantity threshold.

[0007] In a third aspect, an electronic device is provided, which includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method for analyzing the uniformity of recycled asphalt mixing based on image recognition according to any embodiment of the present invention.

[0008] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor is enabled to execute the steps of the method for analyzing the uniformity of recycled asphalt mixing based on image recognition according to any embodiment of the present invention.

[0009] The method and system for analyzing the uniformity of recycled asphalt mixing based on image recognition in the present application divide each recycled asphalt binary image through a preset two-dimensional coordinate system to obtain at least one image region set, and can perform partition analysis on the recycled asphalt image. Determine the smallest asphalt region in the first recycled asphalt binary image region of each image region set, and intercept at least one first sub-image only containing the smallest asphalt region, and judge whether the image size difference between any two first sub-images is greater than a preset size threshold. If it is greater than the preset size threshold, it means that the aggregate distribution in each particle size range is uneven, then it can be explained that the recycled asphalt corresponding to the recycled asphalt image is not evenly mixed, effectively improving the screening efficiency of uneven mixing of recycled asphalt. And aggregate pixel points in the at least one first sub-image are aggregated according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set, and it is judged whether the number of target pixel point pairs meeting a preset condition is greater than a preset first quantity threshold, realizing the determination of whether the recycled asphalt is evenly mixed according to the aggregate following situation in different aggregate particle size ranges, so as to be able to avoid as much as possible human subjective factors and the aggregate distribution factors in a single particle size range, and can conveniently and quickly detect the uniformity of recycled asphalt mixing. Description of the Drawings

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0011] Figure 1 It is a flowchart of a method for analyzing the uniformity of recycled asphalt mixture based on image recognition provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the sliding of a dynamic sliding window in a specific embodiment provided by an embodiment of the present invention; Figure 3 It is a structural block diagram of a system for analyzing the uniformity of recycled asphalt mixture based on image recognition provided by an embodiment of the present invention; Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0013] Please refer to Figure 1 , which shows a flowchart of a method for analyzing the uniformity of recycled asphalt mixture based on image recognition of the present application.

[0014] As Figure 1 shown, the method for analyzing the uniformity of recycled asphalt mixture based on image recognition specifically includes the following steps: Step S101, obtain a recycled asphalt image.

[0015] Step S102, according to different aggregate particle size ranges, perform binarization processing on the recycled asphalt image using a preset processing strategy to obtain a recycled asphalt binarized image corresponding to the different particle size ranges.

[0016] In this step, the regenerated asphalt image is grayscaled to obtain a grayscale regenerated asphalt image, and the grayscale regenerated asphalt image is binarized to obtain a first binarized regenerated asphalt image. Among them, in the first binarized regenerated asphalt image, the gray levels lower than the threshold are set as asphalt features, and those not lower than the threshold are set as aggregate features; different aggregate particle size ranges are set, and in the first binarized regenerated asphalt image, the aggregate features outside a certain aggregate particle size range are removed to obtain a binarized regenerated asphalt image corresponding to the certain aggregate particle size range, where the certain aggregate particle size range is any one of the different aggregate particle size ranges. For example, Figure 2 is a binarized regenerated asphalt image with a particle size of 9.5 - 16.5 mm.

[0017] Step S103: Divide each binarized regenerated asphalt image according to a preset two-dimensional coordinate system to obtain at least one set of image regions, where one set of image regions contains at least one binarized regenerated asphalt image region obtained by dividing a binarized regenerated asphalt image.

[0018] In this step, the center point of a certain binarized regenerated asphalt image is obtained; the certain binarized regenerated asphalt image is placed in the two-dimensional coordinate system, and the center point is aligned with the origin of the two-dimensional coordinate system. The edge line of the certain binarized regenerated asphalt image is parallel to the X-axis or Y-axis, and the binarized regenerated asphalt image region in the first quadrant, the binarized regenerated asphalt image region in the second quadrant, the binarized regenerated asphalt image region in the third quadrant, and the binarized regenerated asphalt image region in the fourth quadrant are obtained.

[0019] Step S104: Determine the smallest aggregate region in the binarized regenerated asphalt image region of each set of image regions, and intercept at least one first sub-image that only contains the smallest aggregate region, where the binarized regenerated asphalt image region is the binarized regenerated asphalt image region in the first quadrant of the at least one binarized regenerated asphalt image region in the two-dimensional coordinate system, and the smallest aggregate region is the smallest rectangular region that contains all aggregate pixel points in the binarized regenerated asphalt image region.

[0020] In this step, determine the smallest aggregate region in the binarized regenerated asphalt image regions in the second, third, and fourth quadrants of each set of image regions, and respectively intercept at least one second sub-image, at least one third sub-image, and at least one fourth sub-image that only contain the smallest aggregate region.

[0021] It should be noted that the subsequent steps performed on at least one second sub-image, at least one third sub-image, and at least one fourth sub-image are the same as those performed on at least one first sub-image, so they will not be elaborated here.

[0022] Step S105: Determine whether the image size difference between any two first sub-images is greater than a preset size threshold.

[0023] In a specific embodiment, after determining whether the image size difference between any two first sub-images is greater than a preset size threshold, if it is greater than the preset size threshold, a warning message corresponding to the uneven mixing of the recycled asphalt in the recycled asphalt image is directly generated.

[0024] Step S106: If it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one set of target aggregate pixel points, where each target aggregate pixel point in one set of target aggregate pixel points belongs to the same first sub-image.

[0025] In this step, please refer to Figure 2 , slide the dynamic sliding window with the initial size along the edge of a certain first sub-image for the first time, and during each slide, determine whether the number of aggregate pixel points in the dynamic sliding window is greater than a preset second quantity threshold, where the next slide distance of the dynamic sliding window is the size of the current dynamic sliding window; if it is not greater than the preset second quantity threshold, briefly expand the size of the dynamic sliding window along the sliding direction until the number of aggregate pixel points in the briefly expanded dynamic sliding window is greater than the preset second quantity threshold, where the "briefly expand" means that after expanding the size of the dynamic sliding window at the current sliding position, the size of the expanded dynamic sliding window is restored to the initial size at the next sliding position; determine the pixel point center position according to the positions of the aggregate pixel points in the briefly expanded dynamic sliding window, and take the aggregate pixel point closest to the pixel point center position among the respective aggregate pixel points as the target aggregate pixel point; slide the dynamic sliding window with the initial size along the edge of the second region in the certain first sub-image for the second time until the sliding trajectory of the dynamic sliding window covers all regions of the certain first sub-image, where the second region is the region obtained by subtracting the region covered by the dynamic sliding window during the first slide from the certain first sub-image; divide the target aggregate pixel points obtained during each slide into the set of target aggregate pixel points corresponding to the certain first sub-image.

[0026] It should be noted that if it is not greater than the preset second quantity threshold, the size of the dynamic sliding window is briefly enlarged along the sliding direction. This way of briefly enlarging the size can obtain sufficient aggregate pixel points while reducing the occurrence of irregularities in the subsequent formation of the second region caused by the synchronous enlargement of the length and width of the dynamic sliding window, thus facilitating the dynamic sliding window to traverse all aggregate features.

[0027] In this embodiment, the pixel point aggregation strategy is adopted, enabling all aggregate pixel points to participate in the process of determining the central position, thereby maximizing the accuracy of the defined target aggregate pixel points compared to the central pixel points obtained by clustering the aggregate pixel points at the edges discarded by other clustering algorithms. It can better represent the distribution of the aggregated aggregate pixel points.

[0028] Specifically, determining the pixel point central position based on the positions of each aggregate pixel point in the briefly enlarged dynamic sliding window includes, but is not limited to, placing the dynamic sliding window in a two-dimensional coordinate system and making one vertex of the dynamic sliding window coincide with the coordinate origin, thereby obtaining the coordinate positions of each aggregate pixel point, and determining a central position closest to each aggregate pixel point based on the coordinate positions of each aggregate pixel point, that is, obtaining the pixel point central position.

[0029] Step S107, determine whether the number of target pixel point pairs that meet the preset conditions is greater than the preset first quantity threshold, where the target aggregate pixel point pairs include target aggregate pixel points from two different target aggregate pixel point sets.

[0030] In this step, obtain a certain first target aggregate pixel point in the first target aggregate pixel point set and a certain second target aggregate pixel point in the second target aggregate pixel point set, where the first target aggregate pixel point set and the second target aggregate pixel point set are any two sets in at least one target aggregate pixel point set; Determine whether the distance between a certain first target aggregate pixel point and a certain second target aggregate pixel point is greater than the preset distance threshold, where a certain first target aggregate pixel point and a certain second target aggregate pixel point are any pixel points in the first target aggregate pixel point set and the second target aggregate pixel point set respectively; If it is greater than the preset distance threshold, do not define a certain first target aggregate pixel point and a certain second target aggregate pixel point as a target pixel point pair, and continue to determine whether the distance between a certain first target aggregate pixel point and other second target aggregate pixel points is greater than the preset distance threshold, where other second target aggregate pixel points are any pixel points in the second target aggregate pixel point set except a certain second target aggregate pixel point; If it is not greater than a preset distance threshold, a certain first target aggregate pixel point and a certain second target aggregate pixel point are defined as a target pixel point pair; Determine whether the number of target pixel point pairs is greater than a preset first quantity threshold.

[0031] In a specific embodiment, after determining whether the number of target pixel point pairs that meet the preset conditions is greater than the preset first quantity threshold, if it is not greater than the preset first quantity threshold, a warning message corresponding to the uneven mixing of the recycled asphalt in the recycled asphalt image is directly generated.

[0032] Step S108, if it is greater than the preset first quantity threshold, an analysis result corresponding to the uniform mixing of the recycled asphalt in the recycled asphalt image is generated.

[0033] In summary, the method of the present application divides each recycled asphalt binary image through a preset two-dimensional coordinate system to obtain at least one set of image regions, and can perform partition analysis on the recycled asphalt image. Determine the smallest asphalt region in the first recycled asphalt binary image region of each set of image regions, and intercept at least one first sub-image that only contains the smallest asphalt region, and judge whether the difference in image size between any two first sub-images is greater than a preset size threshold. If it is greater than the preset size threshold, it means that the aggregate distribution in each particle size range is uneven, then it can be explained that the recycled asphalt corresponding to the recycled asphalt image is unevenly mixed, effectively improving the discrimination efficiency of the uneven mixing of the recycled asphalt. And according to the preset pixel point aggregation strategy, the aggregate pixel points in the at least one first sub-image are aggregated to obtain at least one set of target aggregate pixel points, and it is judged whether the number of target pixel point pairs that meet the preset conditions is greater than the preset first quantity threshold, realizing the determination of whether the recycled asphalt is evenly mixed according to the aggregate following situation in different aggregate particle size ranges, so as to be able to avoid human subjective factors and the aggregate distribution factors in a single particle size range as much as possible, and can conveniently and quickly detect the evenness of the recycled asphalt mixture.

[0034] Please refer to Figure 3 , which shows a structural block diagram of a recycled asphalt mixture evenness analysis system based on image recognition according to the present application.

[0035] As Figure 3 shown, the recycled asphalt mixture evenness analysis system 200 includes an acquisition module 210, a preprocessing module 220, a division module 230, an interception module 240, a first judgment module 250, an aggregation module 260, a second judgment module 270, and a generation module 280.

[0036] Among them, the acquisition module 210 is configured to acquire a recycled asphalt image; the preprocessing module 220 is configured to perform binarization processing on the recycled asphalt image according to different aggregate particle size ranges by using a preset processing strategy to obtain a recycled asphalt binarized image corresponding to the different particle size ranges; the division module 230 is configured to divide each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one image region set, where an image region set includes at least one recycled asphalt binarized image region obtained by dividing a recycled asphalt binarized image; the interception module 240 is configured to determine a minimum aggregate region in the first recycled asphalt binarized image region of each image region set and intercept at least one first sub-image that only includes the minimum aggregate region, where the first recycled asphalt binarized image region is the recycled asphalt binarized image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binarized image region, and the minimum aggregate region is the smallest rectangular region in the first recycled asphalt binarized image region that includes all aggregate pixel points; the first judgment module 250 is configured to judge whether the difference in image size between any two first sub-images is greater than a preset size threshold; the aggregation module 260 is configured to, if it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set, where each target aggregate pixel point in a target aggregate pixel point set belongs to the same first sub-image; the second judgment module 270 is configured to judge whether the number of target pixel point pairs that meet the preset conditions is greater than a preset first number threshold, where the target aggregate pixel point pair includes target aggregate pixel points from two different target aggregate pixel point sets; the generation module 280 is configured to, if it is greater than the preset first number threshold, generate an analysis result of the uniform mixing of the recycled asphalt corresponding to the recycled asphalt image.

[0037] It should be understood that Figure 3 the modules described in Figure 1 correspond to the respective steps in the method described in the reference Figure 3 Therefore, the operations, features, and corresponding technical effects described above for the method also apply to

[0038] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor is caused to execute the method for analyzing the uniform mixing of recycled asphalt based on image recognition in any of the above method embodiments; As an implementation manner, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are set as: Obtain the recycled asphalt image; According to different aggregate particle size ranges, perform binarization processing on the recycled asphalt image using a preset processing strategy to obtain recycled asphalt binarized images corresponding to the different particle size ranges; Divide each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one set of image regions, where one set of image regions contains at least one recycled asphalt binarized image region obtained by dividing a recycled asphalt binarized image; Determine the minimum aggregate region in the first recycled asphalt binarized image region of each set of image regions, and intercept at least one first sub-image that only contains the minimum aggregate region, where the first recycled asphalt binarized image region is the recycled asphalt binarized image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binarized image region, and the minimum aggregate region is the smallest rectangular region in the first recycled asphalt binarized image region that contains all aggregate pixel points; Judge whether the difference in image size between any two first sub-images is greater than a preset size threshold; If it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one set of target aggregate pixel points, where each target aggregate pixel point in one set of target aggregate pixel points belongs to the same first sub-image; Judge whether the number of target pixel point pairs that meet the preset conditions is greater than a preset first quantity threshold, where the target aggregate pixel point pairs include target aggregate pixel points from two different sets of target aggregate pixel points; If it is greater than the preset first quantity threshold, generate an analysis result of the uniform mixing of the recycled asphalt corresponding to the recycled asphalt image.

[0039] A computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area can store an operating system and application programs required for at least one function; the storage data area can store data created according to the use of the recycled asphalt mixing uniformity analysis system based on image recognition, etc. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memories, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the computer-readable storage medium may optionally include a memory remotely provided relative to the processor, and these remote memories can be connected to the recycled asphalt mixing uniformity analysis system based on image recognition through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0040] Figure 4It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As Figure 4 shown, the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 may be connected through a bus or other means. Figure 4 Here, taking the connection through the bus as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements the method for analyzing the uniformity of recycled asphalt mixture based on image recognition in the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal inputs related to user settings and function controls of the system for analyzing the uniformity of recycled asphalt mixture based on image recognition. The output device 340 may include display devices such as a display screen.

[0041] The above electronic device can execute the method provided by the embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided by the embodiment of the present invention.

[0042] As an implementation manner, the above electronic device is applied to a system for analyzing the uniformity of recycled asphalt mixture based on image recognition, and is used for a client, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Obtain a recycled asphalt image; According to different aggregate particle size ranges, perform binarization processing on the recycled asphalt image by using a preset processing strategy to obtain recycled asphalt binarized images corresponding to the different particle size ranges; Divide each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one set of image regions, where one set of image regions contains at least one recycled asphalt binarized image region obtained by dividing a recycled asphalt binarized image; Determine the smallest aggregate region in the first recycled asphalt binarized image region of each set of image regions, and intercept at least one first sub-image that only contains the smallest aggregate region, where the first recycled asphalt binarized image region is the recycled asphalt binarized image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binarized image region, and the smallest aggregate region is the smallest rectangular region in the first recycled asphalt binarized image region that contains all aggregate pixel points; Determine whether the difference in image size between any two first sub-images is greater than a preset size threshold; If it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one set of target aggregate pixel points, where each target aggregate pixel point in a set of target aggregate pixel points belongs to the same first sub-image; Determine whether the number of pairs of target pixel points that meet the preset conditions is greater than a preset first quantity threshold, where the pairs of target aggregate pixel points include target aggregate pixel points from two different sets of target aggregate pixel points; If it is greater than the preset first quantity threshold, generate an analysis result corresponding to the regenerated asphalt image indicating that the regenerated asphalt is evenly mixed.

[0043] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0044] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for analyzing the uniformity of recycled asphalt mixture based on image recognition, characterized in that, Including: Obtain a recycled asphalt image; According to different aggregate particle size ranges, perform binarization processing on the recycled asphalt image by using a preset processing strategy to obtain recycled asphalt binarized images corresponding to the different particle size ranges; Divide each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one set of image regions, where one set of image regions contains at least one recycled asphalt binarized image region obtained by dividing a recycled asphalt binarized image; Determine the smallest aggregate region in the first recycled asphalt binarized image region of each set of image regions, and intercept at least one first sub-image that only contains the smallest aggregate region, where the first recycled asphalt binarized image region is the recycled asphalt binarized image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binarized image region, and the smallest aggregate region is the smallest rectangular region that contains all aggregate pixel points in the first recycled asphalt binarized image region; Judge whether the difference in image size between any two first sub-images is greater than a preset size threshold; If it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one set of target aggregate pixel points, where each target aggregate pixel point in one set of target aggregate pixel points belongs to the same first sub-image; Judge whether the number of pairs of target pixel points that meet the preset conditions is greater than a preset first quantity threshold, where the pairs of target aggregate pixel points include target aggregate pixel points from two different sets of target aggregate pixel points; If it is greater than the preset first quantity threshold, generate an analysis result of the uniform mixing of the recycled asphalt corresponding to the recycled asphalt image.

2. The method for analyzing the homogeneity of recycled asphalt mixture based on image recognition according to claim 1, characterized in that, The step of performing binarization processing on the recycled asphalt image by using a preset processing strategy according to different aggregate particle size ranges to obtain recycled asphalt binarized images corresponding to the different particle size ranges includes: Perform grayscale processing on the recycled asphalt image to obtain a recycled asphalt grayscale image, and perform binarization processing on the recycled asphalt grayscale image to obtain a first recycled asphalt binarized image, where in the first recycled asphalt binarized image, the gray levels lower than the threshold are set as asphalt features, and the gray levels not lower than the threshold are set as aggregate features; Set different aggregate particle size ranges, and remove the aggregate features outside a certain aggregate particle size range in the first recycled asphalt binarized image to obtain a recycled asphalt binarized image corresponding to the certain aggregate particle size range, where the certain aggregate particle size range is any range among the different aggregate particle size ranges.

3. The method for analyzing the homogeneity of recycled asphalt mixture based on image recognition according to claim 1, characterized in that, The step of dividing each recycled asphalt binarized image according to a preset two-dimensional coordinate system to obtain at least one set of image regions includes: Obtain the center point of a certain recycled asphalt binarized image; Place the binary image of a certain recycled asphalt into the two-dimensional coordinate system, align the center point with the origin of the two-dimensional coordinate system, and make the edge line of the binary image of the certain recycled asphalt parallel to the X-axis or Y-axis, so as to divide and obtain a first recycled asphalt binary image region in the first quadrant, a second recycled asphalt binary image region in the second quadrant, a third recycled asphalt binary image region in the third quadrant, and a fourth recycled asphalt binary image region in the fourth quadrant.

4. A method for analyzing the uniformity of recycled asphalt mixture based on image recognition according to claim 1, characterized in that After judging whether the difference in image size between any two first sub-images is greater than a preset size threshold, the method further includes: If it is greater than the preset size threshold, directly generate a warning message indicating uneven mixing of the recycled asphalt corresponding to the recycled asphalt image.

5. The method for analyzing the homogeneity of recycled asphalt mixture based on image recognition according to claim 1, characterized in that, The aggregating the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set includes: Making a first slide along the edge of a certain first sub-image with a dynamic sliding window of an initial size, and at each slide, judging whether the number of aggregate pixel points in the dynamic sliding window is greater than a preset second quantity threshold, where the next slide distance of the dynamic sliding window is the size of the current dynamic sliding window; If it is not greater than the preset second quantity threshold, briefly expand the size of the dynamic sliding window along the sliding direction until the number of aggregate pixel points in the briefly expanded dynamic sliding window is greater than the preset second quantity threshold, where the brief expansion means that after expanding the size of the dynamic sliding window at the current sliding position, the size of the expanded dynamic sliding window is restored to the initial size at the next sliding position; Determining the pixel point center position according to the positions of the respective aggregate pixel points in the briefly expanded dynamic sliding window, and taking the aggregate pixel point closest to the pixel point center position among the respective aggregate pixel points as the target aggregate pixel point; Making a second slide in the certain first sub-image along the edge of the second region with a dynamic sliding window of an initial size until the sliding trajectory of the dynamic sliding window covers all regions of the certain first sub-image, where the second region is the region obtained by subtracting the region covered by the dynamic sliding window during the first slide from the certain first sub-image; Dividing the target aggregate pixel points obtained at each slide into the target aggregate pixel point set corresponding to the certain first sub-image.

6. The method for analyzing the homogeneity of recycled asphalt mixture based on image recognition according to claim 1, characterized in that, The judging whether the number of target pixel point pairs satisfying the preset conditions is greater than a preset first quantity threshold includes: Obtaining a certain first target aggregate pixel point in the first target aggregate pixel point set and a certain second target aggregate pixel point in the second target aggregate pixel point set; Judging whether the distance between the certain first target aggregate pixel point and the certain second target aggregate pixel point is greater than a preset distance threshold; If it is greater than a preset distance threshold, then the certain first target aggregate pixel point and the certain second target aggregate pixel point are not defined as a target pixel point pair, and continue to determine whether the distance between the certain first target aggregate pixel point and any other second target aggregate pixel point is greater than the preset distance threshold, where the any other second target aggregate pixel point is any pixel point in the second target aggregate pixel point set excluding the certain second target aggregate pixel point; If it is not greater than the preset distance threshold, then the certain first target aggregate pixel point and the certain second target aggregate pixel point are defined as a target pixel point pair; Determine whether the number of the target pixel point pairs is greater than a preset first quantity threshold.

7. A method for analyzing the uniformity of recycled asphalt mixture based on image recognition according to claim 1, characterized in that After determining whether the number of target pixel point pairs that meet the preset conditions is greater than the preset first quantity threshold, the method further includes: If it is not greater than the preset first quantity threshold, directly generate a warning message of uneven mixing of the recycled asphalt corresponding to the recycled asphalt image.

8. A system for analyzing the homogeneity of recycled asphalt based on image recognition, characterized in that, including: An acquisition module, configured to acquire a recycled asphalt image; A preprocessing module, configured to perform binary processing on the recycled asphalt image according to different aggregate particle size ranges by using a preset processing strategy to obtain a recycled asphalt binary image corresponding to the different particle size ranges; A partitioning module, configured to partition each recycled asphalt binary image according to a preset two-dimensional coordinate system to obtain at least one image region set, where one image region set contains at least one recycled asphalt binary image region obtained by partitioning one recycled asphalt binary image; A cropping module, configured to determine a minimum aggregate region in the first recycled asphalt binary image region of each image region set, and crop at least one first sub-image that only contains the minimum aggregate region, where the first recycled asphalt binary image region is the recycled asphalt binary image region in the first quadrant of the two-dimensional coordinate system among the at least one recycled asphalt binary image region, and the minimum aggregate region is the smallest rectangular region in the first recycled asphalt binary image region that contains all aggregate pixel points; A first judgment module, configured to judge whether the difference in image size between any two first sub-images is greater than a preset size threshold; An aggregation module, configured to if it is not greater than the preset size threshold, aggregate the aggregate pixel points in the at least one first sub-image according to a preset pixel point aggregation strategy to obtain at least one target aggregate pixel point set, where each target aggregate pixel point in one target aggregate pixel point set belongs to the same first sub-image; A second judgment module, configured to judge whether the number of target pixel point pairs that meet the preset conditions is greater than a preset first quantity threshold, where the target aggregate pixel point pair includes target aggregate pixel points from two different target aggregate pixel point sets; A generation module, configured to if it is greater than the preset first quantity threshold, generate an analysis result of uniform mixing of the recycled asphalt corresponding to the recycled asphalt image.

9. An electronic device, characterized in that, including: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images