Road surface detection method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a road surface detection method and device, electronic equipment and a medium. The method comprises the following steps: acquiring a road surface image in a target time period when a moving target passes through a road surface; determining motion pixel points of floor tiles on the road surface according to the gray difference data of corresponding pixel points in different road surface images; wherein the moving pixel points are pixel points corresponding to moving parts on the floor tiles; and determining whether the floor tiles of the road surface have diseases or not according to the motion pixel points. According to the scheme, the situation that the external force affects the movement of the floor tile can be monitored in real time, then whether the floor tile has diseases or not is determined, the problem that missing detection is generated on the diseases which appear temporarily under the action of the external force is solved, and the timeliness and accuracy of floor tile disease detection are improved.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular, to a road surface detection method, device, electronic device and medium. Background Art

[0002] Pavement bricks are an important part of urban roads. With the increase of service time, pavement bricks usually suffer from diseases such as breakage, cracking, and loosening. When pavement bricks have diseases, it will bring potential safety hazards to road traffic. To reduce the incidence of danger and property losses of public roads of floor tile type, it is very necessary to detect and quickly maintain urban public roads in a timely manner.

[0003] Currently, the detection of pavement brick diseases is carried out by means of manual tools, and the severity assessment of diseases and the maintenance priority are also judged manually. Due to the large area of public roads, there are many types and quantities of floor tiles. Some diseases will only appear briefly in dynamic changes when the floor tiles are triggered by external forces (human / vehicle movement passing by), such as loosening caused by a complete brick surface but insufficiently compacted base layer, which is very likely to be missed during manual detection. In addition, manual detection has low efficiency, may affect the normal use of the road during detection, and cannot monitor the health status of pavement bricks in real time, and problems cannot be discovered in time. After the detection is completed, manual screening and classification of disease pictures and scheduling maintenance are carried out, which prolongs the life cycle of diseases and the scheduling rationality is low. Summary of the Invention

[0004] Embodiments of the present application provide a road surface detection method, device, electronic device and medium, which can monitor the movement of pavement bricks caused by external forces when a moving target passes through the road surface in real time, and improve the timeliness and accuracy of floor tile disease detection.

[0005] According to one aspect of the present application, a road surface detection method is provided, and the method includes:

[0006] Obtain a road surface image within a target time period when a moving target passes through the road surface;

[0007] Determine the moving pixel points of the floor tiles on the road surface according to the gray difference data of the corresponding pixel points in different road surface images; wherein, the moving pixel points are the pixel points corresponding to the moving parts on the floor tiles;

[0008] Determine whether there are diseases on the floor tiles of the road surface according to the moving pixel points.

[0009] According to one aspect of the present application, a road surface detection device is provided, and the device includes:

[0010] A road surface image acquisition module, configured to acquire a road surface image within a target time period when a moving target passes through the road surface;

[0011] A moving pixel point determination module, configured to determine moving pixel points of floor tiles on the road surface according to gray - scale difference data of corresponding pixel points in different road surface images; wherein, the moving pixel points are pixel points corresponding to the moving parts on the floor tiles.

[0012] A disease determination module, configured to determine whether there are diseases on the floor tiles of the road surface according to the moving pixel points.

[0013] According to another aspect of the present application, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory connected to the at least one processor for road surface detection; wherein,

[0016] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the road surface detection method of any embodiment of the present application.

[0017] According to another aspect of the present application, there is provided a computer - readable storage medium. The computer - readable storage medium stores computer instructions, and the computer instructions are used to implement the road surface detection method of any embodiment of the present application when executed by a processor.

[0018] The technical solution of the embodiment of the present application is to acquire road surface images within a target time period when a moving object passes through the road surface; determine moving pixel points of floor tiles on the road surface according to gray - scale difference data of corresponding pixel points in different road surface images; wherein, the moving pixel points are pixel points corresponding to the moving parts on the floor tiles; determine whether there are diseases on the floor tiles of the road surface according to the moving pixel points. The above - mentioned solution can monitor in real time whether the floor tiles on the road surface move due to external forces through the road surface images within the target time period when the target passes through the road surface, monitor the situation of external forces affecting the movement of the floor tiles, and then determine whether there are diseases on the floor tiles according to the degree of influence of external forces on the movement of the floor tiles, solving the problem of missed detection of diseases that appear briefly under the action of external forces, and improving the timeliness and accuracy of floor tile disease detection.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0021] Figure 1 is a flowchart of a road surface detection method provided in Embodiment 1 of the present application;

[0022] Figure 2 is a flowchart of a road surface detection method provided in Embodiment 2 of the present application;

[0023] Figure 3 is a flowchart of a road surface detection method provided in Embodiment 3 of the present application;

[0024] Figure 4 is a structural diagram of a maintenance system for the overall floor tiles provided in Embodiment 3 of the present application;

[0025] Figure 5 is a schematic structural diagram of a road surface detection device provided in Embodiment 4 of the present application;

[0026] Figure 6 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application. Specific Embodiments

[0027] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0028] It should be noted that the terms "first", "second", "third", "fourth", "actual", "preset", etc. in the specification, claims and accompanying drawings of the present application are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 The figure is a flowchart of a road surface detection method provided by Embodiment 1 of the present application. The embodiments of the present application are applicable to the situation of detecting road surfaces. Typically, it is applicable to the situation of detecting whether there are diseases on the floor tiles of the road surface. This method can be executed by a road surface detection device, which can be implemented in the form of hardware and / or software, and the road surface detection device can be configured in an electronic device. As Figure 1 shown, the method includes:

[0031] S110. Obtain road surface images within a target time period when a moving target passes through the road surface.

[0032] Among them, the moving target can be an object that can move, such as a motor vehicle, a non-motor vehicle, a pedestrian, etc. The movement of the moving target passing through the road surface can be continuous or non-continuous, and the speed is not limited. The road surface can be any road surface containing floor tiles. An image collector is deployed inside the surrounding environment of the road surface to collect road surface images for the road surface. The target time period is the time duration during which the moving target passing through the road surface can be collected by the image collector. The selection of the road surface images in the embodiments of the present application can be determined according to the actual situation. For example, all the road surface images collected by the image collector within the target time period can be selected, or the road surface images can be extracted from all the road surface images collected by the image collector at a preset interval or an unequal interval.

[0033] Exemplarily, the road surface can be monitored by an image collector, and road surface images are collected at a preset collection frequency. The road surface images collected by the image collector are identified. If it is recognized that the moving target starts to appear in the road surface image, this moment is taken as the starting moment of the target time period. If it is first recognized that the moving target disappears from the road surface image, this moment is taken as the ending moment of the target time period, and the road surface images collected by the image collector within the target time period are obtained.

[0034] In the embodiments of the present application, the road surface images can be first subjected to road surface detection to distinguish the road surface part and the background part in the road surface images, so as to specifically detect whether there is an area corresponding to the moving target passing through the road surface. The road surface detection can be performed using a neural network model. It is also possible for the user to mark the road surface part and the background part on the road surface image, so as to distinguish the road surface and the background and specifically detect whether there is a passing moving target on the road surface.

[0035] S120. Determine the moving pixel points of the floor tiles on the road surface according to the gray difference data of the corresponding pixel points in different road surface images; among them, the moving pixel points are the pixel points corresponding to the moving part on the floor tiles.

[0036] Among them, the grayscale difference data can reflect the grayscale value differences of corresponding same pixel points in different road surface images. Only some floor tiles on the road surface may be in motion, and only some positions of the floor tiles in motion may be in motion. For example, half of a floor tile moves up and down while the other half does not move. The moving pixel points are the pixel points corresponding to the moving parts on the floor tile.

[0037] Exemplarily, the grayscale values of corresponding same pixel points in different road surface images can be compared to determine the grayscale difference data of the same pixel point. The different road surface images used to determine the grayscale difference data can be two adjacent frames of road surface images, or three adjacent frames of road surface images, or four adjacent frames of road surface images. The number of different road surface images is not limited herein. Specifically, taking the number of different road surface images as an example, it can be traversed from the first frame in the road surface images to determine the grayscale difference data between the first frame and the second frame, then traverse the second frame to determine the grayscale difference data between the second frame and the third frame, then traverse the third frame to determine the grayscale difference data between the third frame and the fourth frame, until all the road surface images are traversed. The moving pixel points within the target time period are determined according to the grayscale difference data. The time when the moving pixel points move can be determined according to the image acquisition time corresponding to the road surface image, reflecting the time when the floor tile moves.

[0038] S130. Determine whether there are diseases on the floor tiles of the road surface according to the moving pixel points.

[0039] Exemplarily, the diseases of the floor tiles include cracking, splitting, loosening, etc. In the embodiments of the present application, the diseases of the floor tiles caused by external forces are mainly detected, such as the floor tiles moving, cracking, splitting, etc. briefly due to the passing of a moving target. The characteristics of the moving pixel points can reflect the movement characteristics of the floor tiles, and whether there are diseases on the floor tiles can be determined according to the movement characteristics of the floor tiles.

[0040] Specifically, the corresponding floor tiles can be determined according to the grayscale value, color characteristics, brightness characteristics, etc. of the moving pixel points, and whether there are diseases on the floor tiles can be determined according to the moving pixel points of the floor tiles and the movement data for determining diseases.

[0041] The technical solution of the embodiment of the present application is to obtain a road surface image within a target time period when a moving target passes through the road surface; determine the moving pixel points of the floor tiles on the road surface according to the gray difference data of the corresponding pixel points in different road surface images, where the moving pixel points are the pixel points corresponding to the moving parts on the floor tiles; determine whether there are diseases on the floor tiles of the road surface according to the moving pixel points. The above solution can monitor in real time whether the floor tiles on the road surface move due to external forces through the road surface image within the target time period when the target passes through the road surface, monitor the situation of external forces affecting the movement of the floor tiles, and then determine whether there are diseases on the floor tiles according to the degree of influence of external forces on the movement of the floor tiles, solving the problem of missed detection of diseases that appear briefly under the action of external forces, and improving the timeliness and accuracy of floor tile disease detection.

[0042] Embodiment 2

[0043] Figure 2 It is a flowchart of a road surface detection method provided by the second embodiment of the present application. The second embodiment of the present application is optimized based on the above embodiment. For the solutions not described in detail in the second embodiment of the present application, please refer to the above embodiment. As Figure 2 shown, the method of the second embodiment of the present application specifically includes the following steps:

[0044] S210. Obtain a road surface image within a target time period when a moving target passes through the road surface.

[0045] S220. Compare the gray values of the corresponding pixel points in a preset number of adjacent road surface images within the target time period to determine the gray difference data.

[0046] Among them, the preset number of frames can be determined according to the actual situation. For example, it can be determined as two frames, or it can be determined as three frames, four frames or five frames, etc. There is no specific limitation, and it can be determined according to the acquisition frequency of the image collector. If the acquisition frequency is high, the preset number of frames can be increased; if the acquisition frequency is low, the preset number of frames can be reduced. In addition, the applicable scenarios of a relatively small preset number of frames and a relatively large preset number of frames can be different. For example, a relatively small preset number of frames can be applicable to the scenario where the floor tiles move slowly, and a relatively large preset number of frames can be applicable to the scenario where the floor tiles move quickly, so as to improve the detection accuracy of the moving pixel points. For example, two frames can be applicable to the scenario where the floor tiles move slowly, and three frames can be applicable to the scenario where the floor tiles move quickly. When the movement speed of the floor tiles is unknown, the present application embodiment can be executed with two frames as the preset number of frames, and the present application embodiment can also be executed with three frames as the preset number of frames, and then the final detection result can be selected from the floor tile disease detection results obtained respectively. The above solution can cover the situations of slow and fast movement of floor tiles through multiple detections, avoiding the problem that it is difficult to apply to the fast movement of floor tiles when only detecting through adjacent two road surface images, resulting in inaccurate detection of floor tile movement.

[0047] In an embodiment of the present application, the gray values of corresponding pixel points in adjacent preset number of frames of road surface images can be compared. For example, the absolute value of the difference between the gray values of corresponding pixel points in adjacent preset number of frames of road surface images is taken to determine the gray difference data. The comparison scheme with the preset number of frames being two frames can be seen in the above embodiment.

[0048] In an embodiment of the present application, if the preset number of frames includes at least three frames, then the gray values of corresponding pixel points in adjacent preset number of frames of road surface images within the target time period are compared to determine the gray difference data, including:

[0049] Compare the gray values of corresponding pixel points in two adjacent frames of road surface images to determine the gray difference value corresponding to each pixel point;

[0050] For the same pixel point, take the maximum value among the gray difference values corresponding to this pixel point as the gray difference data of this pixel point.

[0051] Exemplarily, the preset number of frames may include at least three frames. If the preset number of frames is at least three frames, then for at least three adjacent frames of road surface images, the gray values of every two adjacent frames of road surface images are compared to determine the gray difference value corresponding to each pixel point after comparison. For the same pixel point, take the maximum value among the corresponding gray difference values as the gray difference data of this pixel point. For example, assume the preset number of frames is three frames, then compare the gray values of the first frame and the second frame among the three frames to determine the first gray difference value D 1 (x, y) = |p k (x,y) - p k-1 (x,y)|, p k (x,y) represents the gray value of the pixel point in the k-th road surface image, p k-1 (x,y) represents the gray value of the corresponding pixel point in the (k - 1)-th road surface image. Compare the gray values of the second frame and the third frame among the three frames to determine the second gray difference value D 2 (x, y) = |p k+1 (x,y) - p k (x,y)|. p k+1 (x,y) represents the gray value of the corresponding pixel point in the (k + 1)-th road surface image. Take the maximum value between the first gray difference value and the second gray difference value as the gray difference data of this pixel point. Assume that the first gray difference values of all pixel points determined according to the first frame and the second frame are The second gray difference values of all pixel points determined according to the second frame and the third frame are Then take the maximum value of the gray difference values corresponding to each pixel point between the first gray difference value and the second gray difference value to obtain the gray difference data as The matrix of the above grayscale differences is only illustrated by taking 9 pixel points as an example. The actual number of pixel points is determined according to the road surface image. Similarly, when the preset number of frames is four or more, multiple grayscale differences can be determined first according to every two adjacent road surface images, and then the maximum value of the grayscale differences is determined as the grayscale difference data.

[0052] S230. If there is grayscale difference data corresponding to a pixel point that is greater than the preset grayscale difference data, determine the moving pixel points of the floor tiles on the road surface according to this pixel point.

[0053] Exemplarily, the preset grayscale difference data can be determined in advance. For example, it can be data representing a large grayscale difference. If there is grayscale difference data corresponding to a pixel point that is greater than the preset grayscale difference data, it means that the grayscale difference data corresponding to this pixel point is large. Normally, if the floor tiles do not move, the grayscale value of the corresponding pixel point will not change. If the grayscale difference data corresponding to the pixel point is large, it means that the floor tile corresponding to this pixel point may have moved, and this pixel point can be determined as the moving pixel point of the floor tile on the road surface.

[0054] Exemplarily, the road surface image can also be binarized. If the grayscale difference data of a pixel point is greater than the preset grayscale difference data, the grayscale value of this pixel point is set to 255, otherwise it is set to 0, so as to more intuitively and quickly determine the moving pixel points in the road surface image.

[0055] In the embodiment of the present application, the method further includes:

[0056] Identify the moving target and / or background area in the road surface image, and determine the target pixel points corresponding to the moving target and / or background area;

[0057] If there is grayscale difference data corresponding to a pixel point that is greater than the preset grayscale difference data, determining the moving pixel points of the floor tiles on the road surface according to this pixel point includes:

[0058] Remove the target pixel points from the pixel points whose grayscale difference data is greater than the preset grayscale difference data to obtain the moving pixel points.

[0059] Exemplarily, in the road surface image, the moving pixel points do not necessarily all belong to the floor tiles, and may also be the pixel points corresponding to the moving target, or the pixel points of the moving objects in the background, such as the pixel points corresponding to the leaves swaying in the wind, flying objects flying in the air, etc. The road surface image can be identified to identify the moving target and / or background area, and the pixel points belonging to the moving target and / or background area are removed from the pixel points whose grayscale difference data is greater than the preset grayscale difference data to obtain the moving pixel points. The above solution can improve the accuracy of identifying the moving pixel points and avoid the problem that the pixel points belonging to other moving objects are misjudged as the moving pixel points of the floor tiles, resulting in inaccurate moving pixel points.

[0060] S240. Determine whether there are diseases on the floor tiles of the road surface based on the moving pixel points.

[0061] The embodiment of the present application provides a road surface detection method, which obtains a road surface image within a target time period when a moving target passes through the road surface, compares the gray values of corresponding pixel points in a preset number of adjacent road surface images within the target time period to determine gray difference data; if there is gray difference data corresponding to a pixel point that is greater than the preset gray difference data, then determine the moving pixel points of the floor tiles on the road surface according to this pixel point. Determine whether there are diseases on the floor tiles of the road surface based on the moving pixel points. The above solution can accurately determine the change of the gray value of the pixel point over time according to the comparison of the gray values of the corresponding pixel points in a preset number of adjacent road surface images, and then determine whether there is movement of the floor tiles on the road surface, and can monitor in real time and accurately the movement of the road surface floor tiles caused by external forces when the moving target passes, and then determine whether there are diseases on the floor tiles according to the movement situation.

[0062] Embodiment III

[0063] Figure 3 It is a flowchart of a road surface detection method provided by Embodiment III of the present application. The embodiment of the present application is optimized based on the above embodiment, and the solutions not described in detail in the embodiment of the present application can be seen in the above embodiment. As Figure 3 shown, the method of the embodiment of the present application specifically includes the following steps:

[0064] S310. Obtain a road surface image within a target time period when a moving target passes through the road surface.

[0065] S320. Determine the moving pixel points of the floor tiles on the road surface according to the gray difference data of the corresponding pixel points in different road surface images; where the moving pixel points are the pixel points corresponding to the moving parts on the floor tiles.

[0066] S330. For each floor tile, determine the movement offset of the floor tile according to the movement continuity characteristics of the moving pixel points belonging to the floor tile; where the movement offset includes the maximum offset during the movement of the floor tile and / or the final offset at the end of the movement relative to the start time of the movement.

[0067] Among them, each floor tile on the road surface can be recognized and tracked and detected. Specifically, information such as the initial appearance features, tile type, location, affiliated road section, disease record, disease video, maintenance record, etc. of the floor tiles can be pre-recorded in the floor tile filing content. The initial appearance features may include information such as the gray value, color, brightness, etc. of the pixel points corresponding to the floor tiles. The arrangement and distribution of each floor tile can be recognized based on the initial appearance features of the floor tiles, as well as the pixel point range belonging to the same floor tile. For a floor tile, determine the motion continuity feature of the motion pixel points belonging to the floor tile. Specifically, record the position of the motion pixel points in the previous frame of road surface image, and in the next frame of road surface image, find the motion pixel points located within the preset range of this position and with a gray value difference less than the preset difference from the motion pixel points of the floor tile in the previous frame of road surface image, or find in the next frame of road surface image the motion pixel points with a gray value difference less than the preset difference from the motion pixel points of the floor tile in the previous frame of road surface image and with the smallest distance from the motion pixel points of the floor tile in the previous frame of road surface image, and determine that this motion pixel point and the motion pixel point in the previous frame of road surface image are the same pixel point, and based on the motion offset of this motion pixel point, determine the motion offset of the floor tile. For example, if the motion pixel points of the floor tile in the previous frame of road surface image are the pixel points in the first row and the first four columns, and in the next frame of road surface image, the motion pixel points in the second row and the first four columns have the same gray value as them, then it is considered that the motion pixel points in the second row and the first four columns in the next frame are the same pixel points as the pixel points in the first row and the first four columns in the previous frame. The movement of this pixel point from the first row to the second row is the motion offset of the motion pixel point. Specifically, the average value or the maximum value of the motion offsets of all the motion pixel points belonging to the same floor tile can be used as the motion offset of the floor tile.

[0068] In the embodiment of the present application, the motion offset may include the maximum offset during the movement of the floor tile. For example, compare the motion pixel points in each road surface image with the corresponding motion pixel points in the first frame of road surface image respectively, determine the real-time offset of the same floor tile in each road surface image relative to the initial movement moment respectively, and use the maximum value of the real-time offsets as the maximum offset.

[0069] The motion offset may also include the final offset of the floor tile at the end of the movement relative to the start of the movement. For example, compare the motion pixel points in the last frame of road surface image with the corresponding motion pixel points in the first frame of road surface image, determine the motion offset of the pixel points, and determine the final offset of the floor tile according to the maximum value or the average value of the motion offsets of the pixel points.

[0070] S340. Determine whether there is a disease in the floor tiles of the road surface according to the motion offset and the preset offset threshold.

[0071] Exemplarily, the preset offset threshold can be determined in advance according to the actual situation, which is the threshold for reflecting whether the floor tile is significantly offset and belongs to a disease. For example, according to road safety requirements, the maximum displacement allowed for the floor tile to move without affecting the normal movement of the moving target can be calculated. It can also be determined by querying relevant traffic requirement standards. The movement offset is compared with the preset offset threshold to determine whether there is a disease in the floor tiles on the road surface. For example, if the movement offset is greater than the preset offset threshold, it is determined that there is a disease in the floor tile; otherwise, it is determined that there is no disease in the floor tile. Thus, based on the movement offset of the floor tile, it can be accurately determined whether there is a disease in the floor tile that can affect normal traffic or the normal movement of the moving target.

[0072] In the embodiment of the present application, the movement offset includes the maximum offset of the floor tile during the movement process and the final offset at the end of the movement relative to the start time of the movement;

[0073] After determining whether there is a disease in the floor tiles on the road surface according to the movement offset and the preset offset threshold, the method further includes:

[0074] The maximum offset and the final offset are weighted and summed to obtain an offset parameter;

[0075] According to the offset parameter and the influence parameter of the disease on the road surface, or according to the offset parameter, the influence parameter of the disease on the road surface, the detection result of whether there is a disease in the floor tile, and the global disease detection result, the disease level of the floor tiles on the road surface is determined; wherein, the global disease detection result is obtained by detecting the road surface image within a global time period longer than the target time period.

[0076] Exemplarily, in the case where the movement offset includes the maximum offset and the final offset, weights can be set for the maximum offset and the final offset, and the maximum offset and the final offset are weighted and summed according to the weights to obtain an offset parameter. For example, the offset parameter S = αS1 + βS2, where S1 is the maximum offset, α is the weight of the maximum offset, S2 is the final offset, and β is the weight of the final offset. Different types of diseases of the floor tile may have different degrees of influence on the road surface. For example, the influence degree of cracks on the road surface is relatively small, and the influence degree of loosening on the road surface is relatively large. Therefore, the influence parameter of the disease on the road surface can be determined in advance to reflect the influence degree of the disease on the road surface. The disease level of the floor tile can be determined according to the offset parameter and the influence parameter of the disease on the road surface.

[0077] The disease level of the floor tiles can also be determined based on the offset parameter, the parameter of the influence of the disease on the road surface, and the global disease detection result. The global disease detection result can be the movement condition of the floor tiles over a relatively long period of time. For example, it is the disease condition of the floor tiles detected from the road surface images within a global time period longer than the target time period. Specifically, the weight of the disease detection result can be determined according to the detection result of whether there is a disease in the floor tiles determined in S340 and the global disease detection result. For example, if it is determined in S340 that there is no disease in the floor tiles and the global disease detection result determines that there is no disease in the floor tiles, then the weight of the disease detection result is determined to be w1, which can be 0; if it is determined in S340 that there is no disease in the floor tiles and the global disease detection result determines that there is a disease in the floor tiles, then the weight of the disease detection result is determined to be w2, which can be 1; if it is determined in S340 that there is a disease in the floor tiles and the global disease detection result determines that there is no disease in the floor tiles, then the weight of the disease detection result is determined to be w2, which can be 2; if it is determined in S340 that there is a disease in the floor tiles and the global disease detection result determines that there is a disease in the floor tiles, then the weight of the disease detection result is determined to be w4, which can be 3. The disease level of the floor tiles can be determined according to the product of the offset parameter, the parameter of the influence of the disease on the road surface, and the weight of the disease detection result.

[0078] In the embodiment of the present application, the determination process of the global disease detection result includes:

[0079] Obtain road surface images within the global time period, and extract road surface images of a preset number of frames at a preset time interval;

[0080] Determine the moving pixel points of the floor tiles on the road surface according to the gray difference data of the corresponding pixel points in different road surface images among the road surface images of the preset number of frames;

[0081] Determine the global disease detection result of the floor tiles on the road surface according to the moving pixel points.

[0082] The detection process of floor tile diseases in the above embodiments can be referred to as on-demand detection, and the global disease detection process as routine detection. Exemplarily, for the determination of the global disease detection result, the process principle is the same as that of the floor tile disease detection result in the above embodiments. The difference is that the road surface images are taken from the road surface images within a longer global time period. The starting time of the normal state of the floor tile in the floor tile filing content can be used as the starting time, and any time can be used as the ending time to determine the global time period. The global time period can be, for example, one day, one month, one year, etc. And a preset number of frames of road surface images are extracted at preset time intervals as continuous road surface images. For example, a preset number of frames of road surface images can be randomly extracted every day, or the preset number of frames to be extracted can be determined according to the traffic of moving objects on the road surface. The preset time interval can also be adjusted. According to the gray-scale difference data of the corresponding pixel points in different road surface images among the preset number of frames of road surface images, the moving pixel points of the floor tiles on the road surface are determined. Similarly to the above embodiments, the gray-scale values of the corresponding pixel points of every two adjacent frames of the preset number of frames of road surface images can be subtracted, and / or the gray-scale values of the corresponding pixel points of every three adjacent frames of the preset number of frames of road surface images can be subtracted to determine the gray-scale difference data. The determination method of the gray-scale difference data is the same as that in the above embodiments. It is not limited to adjacent two frames and three frames, and can also be adjacent four frames, five frames, etc. According to the moving pixel points, the global disease detection result of the floor tiles on the road surface is determined, and the determination method is the same as that in the above embodiments. After determining the global disease detection result, the global disease level can also be determined. Exemplarily, the maximum offset and the final offset in the global disease detection process are weighted and summed to obtain an offset parameter. According to the detection result of whether there is a disease of the floor tile determined in S340 and the global disease detection result, the disease detection result weight is determined. According to the product of the offset parameter, the influence parameter of the disease on the road surface, and the disease detection result weight, the global disease level is determined. The maximum value of the disease level of the floor tile determined in the above embodiments and the global disease level can be taken as the final disease level of the floor tile. The beneficial effect of the above solution is that the global disease detection is carried out based on the road surface images within a longer global time period to assist in determining the final disease level of the floor tiles, so as to more comprehensively consider the movement damage of the floor tiles within a long time range, and improve the credibility and accuracy of the floor tile disease level.

[0083] In the embodiments of the present application, in the disease detection at any stage, as long as it is detected through the road surface image that when a moving object passes through the road surface floor tile, and the floor tile splashes water, the stone rolls, resulting in abnormal movement of the moving object, etc. due to the movement, the disease level of the floor tile is set to the highest level.

[0084] In the embodiments of the present application, the method further includes:

[0085] According to the disease levels of the floor tiles on the road surface, determine the disease level of the road surface;

[0086] Determine the maintenance priority of the road surface according to the disease level of the road surface and the flow of moving objects passing through the road surface within a preset time period.

[0087] Exemplarily, when there are diseases in floor tiles, the maintenance priority of the road surface can be determined, so as to determine whether the road surface needs to be maintained and the order of maintenance. Specifically, the disease level of the road surface can be determined according to the disease levels of each floor tile on the road surface. The disease level of the road surface is the sum of the disease levels of each floor tile. The flow of moving objects passing through the road surface within a preset time period can be determined, that is, the number of moving objects passing through the road surface per unit time. According to the product of the disease level of the road surface and the flow of moving objects passing through the road surface within the preset time period, the maintenance priority is determined. Different preset time periods can be selected respectively, and the time period with fewer moving objects on the road surface and the road surface being relatively idle can be selected for maintenance, which is convenient for the development of maintenance and reduces the impact on the passage of moving objects. When there are at least two types of moving objects, the flow of different types of moving objects can be determined respectively, and weighted summation is performed to obtain the final flow. Assuming that the vehicle flow is p1, the corresponding weight is a1, and the pedestrian flow is p2, the corresponding weight is a2, then the flow of moving objects passing through the road surface within the preset time period is a1*p1 + a2*p2. The above solution can accurately determine the maintenance priorities of different road surfaces, so as to select the floor tiles with serious diseases and few moving objects on the road surface for priority maintenance according to the ranking of the maintenance priorities, reducing the impact of maintenance on the use of the road surface.

[0088] An embodiment of the present application provides a road surface detection method. For each floor tile, determine the movement offset of the floor tile according to the movement continuity feature of the movement pixel points belonging to the floor tile; wherein, the movement offset includes the maximum offset during the movement of the floor tile and / or the final offset at the end of the movement relative to the start of the movement; determine whether there are diseases in the floor tiles of the road surface according to the movement offset and a preset offset threshold. The above solution can more intuitively and accurately evaluate whether the floor tile will affect the normal passage of the road surface through the quantitative movement offset, so as to accurately determine whether there are diseases in the floor tile, improving the reliability and accuracy of disease detection.

[0089] In an embodiment of the present application, if it is detected that there are diseases in the floor tiles, the video within the time period when the diseases exist is saved for subsequent viewing or application.

[0090] For the maintenance system of the whole floor tile such as Figure 4As shown in the figure. The file module can record the file information of road floor tiles, including the content of road file creation, such as positioning, construction team information, delivery date, maintenance frequency, vehicle flow and / or pedestrian flow, etc., and also includes the content of floor tile file creation, such as initial appearance characteristics, floor tile type, location, section to which it belongs, disease record, disease video, maintenance record, etc. The monitoring module can detect floor tile diseases, monitor the flow of moving objects, and collect road digit data, and upload the detection results of floor tile diseases and road maintenance data to the road floor tile file. The analysis module can determine the road surface maintenance plan according to the detection results of the diseases, notify the implementation team to arrange the implementation, and obtain the road surface maintenance data after implementation, and upload it to the file module to form a closed loop.

[0091] Embodiment 4

[0092] Figure 5 As shown in the figure, it is a schematic structural diagram of a road surface detection device provided in Embodiment 4 of the present application. This device can execute the road surface detection method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the method. As Figure 5 shown, the device includes:

[0093] A road surface image acquisition module 410, configured to acquire a road surface image within a target time period when a moving object passes through the road surface;

[0094] A moving pixel point determination module 420, configured to determine the moving pixel points of the floor tiles on the road surface according to the gray level difference data of the corresponding pixel points in different road surface images; wherein, the moving pixel points are the pixel points corresponding to the moving parts on the floor tiles;

[0095] A disease determination module 430, configured to determine whether there are diseases on the floor tiles of the road surface according to the moving pixel points.

[0096] In the embodiment of the present application, the moving pixel point determination module 420 includes:

[0097] A gray level difference data determination unit, configured to compare the gray level values of the corresponding pixel points in a preset number of adjacent road surface images within the target time period to determine the gray level difference data;

[0098] A comparison unit, configured to, if there is gray level difference data corresponding to a pixel point greater than the preset gray level difference data, determine the moving pixel points of the floor tiles on the road surface according to this pixel point.

[0099] In the embodiment of the present application, if the preset number of frames includes at least three frames, the moving pixel point determination module 420 includes:

[0100] A comparison unit, configured to compare the gray level values of the corresponding pixel points in two adjacent road surface images to determine the gray level difference value corresponding to each pixel point;

[0101] A maximum value determination unit, which is configured to, for the same pixel point, use the maximum value among the grayscale difference values corresponding to the pixel point as the grayscale difference data of the pixel point.

[0102] In an embodiment of the present application, the device further includes:

[0103] An identification module, which is configured to identify a moving target and / or a background area in the road surface image, and determine target pixel points corresponding to the moving target and / or the background area;

[0104] A comparison unit, specifically configured to:

[0105] Remove the target pixel points from the pixel points whose grayscale difference data is greater than a preset grayscale difference data to obtain the moving pixel points.

[0106] In an embodiment of the present application, a disease determination module 430 includes:

[0107] A motion offset amount determination unit, which is configured to, for each floor tile, determine the motion offset amount of the floor tile according to the motion continuity characteristics of the moving pixel points belonging to the floor tile; wherein, the motion offset amount includes the maximum offset amount during the motion of the floor tile and / or the final offset amount at the end of the motion relative to the start time of the motion;

[0108] A determination unit, which is configured to determine whether there is a disease in the floor tiles of the road surface according to the motion offset amount and a preset offset amount threshold.

[0109] In an embodiment of the present application, the motion offset amount includes the maximum offset amount during the motion of the floor tile, and the final offset amount at the end of the motion relative to the start time of the motion;

[0110] The device further includes:

[0111] An offset parameter determination module, which is configured to perform a weighted sum of the maximum offset amount and the final offset amount to obtain an offset parameter;

[0112] A disease level determination unit, which is configured to determine the disease level of the floor tiles of the road surface according to the offset parameter and the influence parameter of the disease on the road surface, or according to the offset parameter, the influence parameter of the disease on the road surface, the detection result of whether there is a disease in the floor tiles, and the global disease detection result; wherein, the global disease detection result is detected according to the road surface images within a global time period longer than a target time period.

[0113] In an embodiment of the present application, the device further includes:

[0114] A global image acquisition module, configured to acquire road surface images within a global time period, and extract a preset number of frames of road surface images at preset time intervals;

[0115] A grayscale difference data determination module, configured to determine moving pixel points of floor tiles on the road surface according to grayscale difference data of corresponding pixel points in different road surface images among the preset number of frames of road surface images;

[0116] A global disease detection result determination module, configured to determine a global disease detection result of the floor tiles on the road surface according to the moving pixel points.

[0117] In an embodiment of the present application, the device further includes:

[0118] A road surface disease level determination module, configured to determine the disease level of the road surface according to the disease levels of each floor tile on the road surface;

[0119] A maintenance priority determination module, configured to determine the maintenance priority of the road surface according to the disease level of the road surface and the traffic flow of moving targets passing through the road surface within a preset time period.

[0120] A road surface detection device provided by an embodiment of the present application can execute a road surface detection method provided by any embodiment of the present application, and has function modules and beneficial effects corresponding to the execution of the method.

[0121] Embodiment Five

[0122] Figure 6 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described herein and / or claimed.

[0123] As Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory connected to the at least one processor 11 for road surface detection, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0124] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a road surface detection unit 19, such as a network card, a modem, a wireless road surface detection transceiver, etc. The road surface detection unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0125] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the road surface detection method.

[0126] In some embodiments, the road surface detection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the road surface detection unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the road surface detection method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the road surface detection method by any other appropriate means (e.g., by means of firmware).

[0127] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0128] The computer programs for implementing the methods of this application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable pavement detection device, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0129] In the context of this application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0131] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data path detection (e.g., a path detection network). Examples of path detection networks include: local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0132] The computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a path detection network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0133] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this application can be executed in parallel, sequentially, or in a different order, as long as the information desired by the technical solution of this application can be achieved, and this is not limited herein.

[0134] The above specific implementation manners do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. A road surface detection method, characterized in that, the method includes: Obtaining road surface images within a target time period when a moving object passes over the road surface; Determining the moving pixel points of floor tiles on the road surface according to the gray level difference data of corresponding pixel points in different road surface images; wherein, the moving pixel points are the pixel points corresponding to the moving parts on the floor tiles; Determining whether there are diseases on the floor tiles of the road surface according to the moving pixel points.

2. The method according to claim 1, characterized in that, Determining the moving pixel points of floor tiles on the road surface according to the gray level difference data of corresponding pixel points in different road surface images includes: Comparing the gray level values of corresponding pixel points in a preset number of adjacent frames of road surface images within the target time period to determine the gray level difference data; If there is pixel point whose corresponding gray level difference data is greater than the preset gray level difference data, then determining the moving pixel points of floor tiles on the road surface according to this pixel point.

3. The method according to claim 2, characterized in that, If the preset number of frames includes at least three frames, then comparing the gray level values of corresponding pixel points in a preset number of adjacent frames of road surface images within the target time period to determine the gray level difference data, including: Comparing the gray level values of corresponding pixel points in two adjacent frames of road surface images to determine the gray level difference value corresponding to each pixel point; For the same pixel point, taking the maximum value among the gray level difference values corresponding to this pixel point as the gray level difference data of this pixel point.

4. The method according to claim 2 or 3, characterized in that, the method further includes: Identifying the moving object and / or background area in the road surface image to determine the target pixel points corresponding to the moving object and / or background area; If there is pixel point whose corresponding gray level difference data is greater than the preset gray level difference data, then determining the moving pixel points of floor tiles on the road surface according to this pixel point, including: Removing the target pixel points from the pixel points whose gray level difference data is greater than the preset gray level difference data to obtain the moving pixel points.

5. The method according to claim 1, characterized in that, Determining whether there are diseases on the floor tiles of the road surface according to the moving pixel points includes: For each floor tile, determining the movement offset of the floor tile according to the movement continuity characteristics of the moving pixel points belonging to this floor tile; wherein, the movement offset includes the maximum offset during the movement of the floor tile and / or the final offset at the end of the movement relative to the start of the movement; Determining whether there are diseases on the floor tiles of the road surface according to the movement offset and a preset offset threshold.

6. The method according to claim 5, characterized in that, the movement offset includes the maximum offset during the movement of the floor tile and the final offset at the end of the movement relative to the start of the movement; After determining whether there are diseases on the floor tiles of the road surface according to the movement offset and a preset offset threshold, the method further includes: Performing weighted summation on the maximum offset and the final offset to obtain an offset parameter; Determine the disease level of the floor tiles on the road surface according to the offset parameter and the parameter of the impact of the disease on the road surface, or according to the offset parameter, the parameter of the impact of the disease on the road surface, the detection result of whether there is a disease in the floor tiles, and the global disease detection result; wherein, the global disease detection result is obtained by detecting road surface images within a global time period longer than the target time period. The determination process of the global disease detection result includes: Obtain road surface images within the global time period, and extract a preset number of frames of road surface images at preset time intervals. Determine the moving pixel points of the floor tiles on the road surface according to the gray-scale difference data of the corresponding pixel points in different road surface images. Determine the global disease detection result of the floor tiles on the road surface according to the moving pixel points.

7. According to the method described in claim 6, It is characterized in that The method further includes: Determine the disease level of the road surface according to the disease levels of the floor tiles on the road surface. Determine the maintenance priority of the road surface according to the disease level of the road surface and the flow of moving targets passing through the road surface within a preset time period.

8. A road surface detection device, It is characterized in that The device includes: A road surface image acquisition module, configured to acquire road surface images within the target time period when a moving target passes through the road surface. A moving pixel point determination module, configured to determine the moving pixel points of the floor tiles on the road surface according to the gray-scale difference data of the corresponding pixel points in different road surface images; wherein, the moving pixel points are the pixel points corresponding to the moving parts on the floor tiles. A disease determination module, configured to determine whether there is a disease in the floor tiles on the road surface according to the moving pixel points.

9. An electronic device, It is characterized in that The electronic device includes: At least one processor; and A memory connected to the at least one processor for road surface detection; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the road surface detection method described in any one of claims 1-7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute the road surface detection method described in any one of claims 1-7 when executed.

Images