CN115830029B - Spring soil detection method based on computer vision - Google Patents
Spring soil detection method based on computer vision Download PDFInfo
- Publication number
- CN115830029B CN115830029B CN202310139076.1A CN202310139076A CN115830029B CN 115830029 B CN115830029 B CN 115830029B CN 202310139076 A CN202310139076 A CN 202310139076A CN 115830029 B CN115830029 B CN 115830029B
- Authority
- CN
- China
- Prior art keywords
- pixel
- soil
- value
- depth image
- difference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a spring soil detection method based on computer vision. The invention improves the spring soil detection accuracy and reduces the detection cost.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a spring soil detection method based on computer vision.
Background
Channel engineering is an important component of foundation engineering, which includes but is not limited to earthwork excavation and filling processes, highway engineering and roadbed engineering, and most of the construction processes of the engineering are needed to be carried out on the basis of soil bodies, and in the construction process, engineering diseases which become spring soil can occur due to the change of the water content of the soil bodies, and if the spring soil problem can not be treated in time, the construction quality and the construction process can be seriously affected. When the spring soil problem is serious, the spring soil can be directly identified from the soil surface characteristics, and when the spring soil problem is slight, the spring soil can be identified only by detecting the water content of the soil. However, since the construction site is relatively large, it is not realistic to detect the construction site by using a method for detecting the water content of soil, in order to improve the detection efficiency of spring soil, the prior art generally implements the detection of spring soil at the construction site according to a method for training a neural network.
The inventors have found in practice that the above prior art has the following drawbacks:
in the prior art, data is generally collected as training data in the construction process according to construction equipment to train the neural network, and spring soil detection of a construction site is realized according to the trained neural network, but a large amount of historical data is required to ensure the accuracy of identification of the neural network by the method for training the neural network, so that the cost is high, the accuracy of the neural network is seriously affected when error data exists in the historical data, and the accuracy of corresponding detection of the spring soil is insufficient. The prior art method of detecting spring soil by training a neural network is costly and inaccurate.
Disclosure of Invention
In order to solve the technical problems that the cost of a method for detecting spring soil by training a neural network is high and the method is not accurate enough in the prior art, the invention aims to provide a spring soil detection method based on computer vision, and the adopted technical scheme is as follows:
the invention provides a spring soil detection method based on computer vision, which comprises the following steps:
acquiring an original depth image before loading and a loaded depth image after loading of each soil compacting area, and obtaining a pressure change height image according to the difference between the original depth image and the loaded depth image of each soil compacting area;
obtaining a concave region and a convex region according to pixel values in the original depth image; obtaining the shaping compressibility of each soil compacting region according to the pixel value distribution characteristics of the pixel points in the concave region and the convex region in the pressure change height map;
obtaining shaping flatness according to the pixel value change characteristic difference between the original depth image and the load depth image, and obtaining shaping deformation according to the shaping compression degree and the shaping flatness of each soil compacting area;
obtaining a pixel point characteristic value sequence in the load depth image according to the moving direction of the soil compactor; obtaining the ground elasticity significance of each soil compacting area according to the element value distribution trend characteristic in the pixel point characteristic value sequence;
And obtaining the spring soil saliency of each soil compacting area according to the molding deformation degree and the ground elasticity saliency of each soil compacting area, and finishing the spring soil detection according to the spring soil saliency.
Further, the method for acquiring the concave area and the convex area of the pressure change height map comprises the following steps:
dividing pixel values of all pixel points in the original depth image by adopting an OTSU maximum inter-class variance method to obtain a division threshold, wherein the division threshold is a depth threshold, pixel points corresponding to pixel values larger than the depth threshold in the original depth image are marked as concave pixel points, pixel points corresponding to pixel values smaller than the depth threshold in the original depth image are marked as convex pixel points, an area formed by all the concave pixel points is marked as a concave area, and an area formed by all the convex pixel points is marked as a convex area.
Further, the method for obtaining the molding compression degree comprises the following steps:
in the pressure change height map, calculating the average value of pixel values of all pixel points of the concave area and marking the average value as a characteristic value of the concave area, calculating the average value of pixel values of all pixel points of the convex area and marking the characteristic value of the convex area, calculating the difference value between the depth threshold value and the characteristic value of the convex area and marking the difference value as a convex difference value, calculating the difference value between the characteristic value of the concave area and the depth threshold value and marking the difference value as a concave difference value, and taking the ratio of the convex difference value and the concave difference value as the weight value of the characteristic value of the convex area; and adding the result of multiplying the weight value by the characteristic value of the convex area with the characteristic value of the concave area to obtain the molding compression degree of the corresponding soil compacting area.
Further, the method for acquiring the pixel value variation characteristic comprises the following steps:
optionally selecting one of the original depth image and the load depth image as a target image;
and taking each pixel point of the target image as a central pixel point, acquiring a gray level co-occurrence matrix according to the pixel values of the pixel points in a preset neighborhood range of the central pixel point, calculating the contrast corresponding to the gray level co-occurrence matrix, and recording the accumulated sum of the contrast corresponding to all the pixel points in the target image as a pixel value change characteristic.
Further, the method for obtaining the shaping flatness comprises the following steps:
calculating the difference between the pixel value change characteristics of the pressure change height map and the load depth image in the same soil compacting region, marking the difference as flatness difference, and marking the ratio between the flatness difference and the pixel value change characteristics of the load depth image as the shaping flatness of the corresponding soil compacting region.
Further, the method for acquiring the pixel point characteristic value sequence comprises the following steps:
in the load depth image, the reverse direction of the movement direction of the soil compactor is taken as the stress characteristic direction;
and counting the median value of pixel values of each row of pixel points in the load depth image, marking the median value as a pixel point characteristic value, and arranging the pixel point characteristic values in order of the stress characteristic direction to obtain a pixel point characteristic value sequence.
Further, the method for acquiring the element value distribution trend feature in the pixel point feature value sequence comprises the following steps:
obtaining a hurst index by adopting an aggregation variance method for the pixel characteristic value sequence, and recording the hurst index of the pixel characteristic value sequence as an autocorrelation characteristic value of the load depth image;
calculating element difference values between every two adjacent elements in the pixel characteristic value sequence, marking the element difference values as pixel difference characteristic values, forming a sequence by taking the pixel difference characteristic values as elements according to the sequence of the elements in the pixel characteristic value sequence, and marking the sequence as a pixel difference characteristic value sequence;
calculating standard deviation among various elements in the pixel point difference characteristic value sequence, recording the standard deviation as characteristic value difference standard deviation of the load depth image, detecting abnormal data of the pixel point difference characteristic value sequence, and counting the number of abnormal values;
and recording the autocorrelation characteristic value, the pixel point difference characteristic value, the characteristic value difference standard deviation and the abnormal value quantity of the load depth image as the distribution trend characteristic.
Further, the method for acquiring the ground elasticity significance comprises the following steps:
The load depth image of the target soil compacting region is obtained, the product of the characteristic value difference standard deviation of the load depth image and the abnormal value quantity is recorded as an abnormal condition characteristic value, the ratio of the autocorrelation characteristic value of the load depth image to the abnormal condition characteristic value plus a preset constant coefficient is calculated and is recorded as an inclined characteristic value, the ratio of the sum of the difference characteristic values of all pixels of the load depth image to the element quantity in the pixel difference characteristic value sequence is recorded as an inclined change degree, and the product of the inclined characteristic value of the load depth image and the inclined change degree is recorded as the ground elasticity significance of the corresponding target soil compacting region.
Further, the method for obtaining the spring soil saliency comprises the following steps:
and carrying out proportional normalization on the ratio of the molding compression degree to the ground elasticity significance in the same soil compacting region by adopting a hyperbolic tangent function to obtain the spring significance.
Further, the method for acquiring the pressure change height map comprises the following steps:
obtaining the original depth image and the load depth image which correspond to each soil compacting area and have the same size; and marking the pixel values of the target pixel points in the original depth image and the load depth image in the same soil compacting region as the pixel values of the target pixel points in the pressure change height map, and changing the target pixel points to obtain the pixel value of each pixel point in the pressure change height map.
The invention has the following beneficial effects:
the invention is based on the soil body difference corresponding to the spring soil and the normal soil, and analyzes the soil body according to the elastic deformation characteristic and the inclination characteristic of the spring soil. In order to embody the elastic deformation characteristics of the spring soil, the invention obtains the shaping compression degree according to the pixel value distribution characteristics in the pressure change height image, and introduces the pixel value change characteristic difference between the images before and after rolling in the soil compacting area on the basis to obtain the shaping flatness, and obtains the shaping deformation degree according to the shaping flatness and the shaping compression degree, so that the shaping deformation degree represents the elastic deformation characteristics of the spring soil more accurately. Further, according to the invention, through the inclination characteristic of the spring soil after being rolled, the ground elasticity significance of each soil compacting area is obtained according to the element value distribution trend characteristic in the pixel point characteristic value sequence, and the inclination characteristic of the spring soil is represented through the ground elasticity significance. The spring soil saliency is further obtained according to the molding deformation degree and the ground elasticity saliency of each soil compacting area, and the spring soil saliency is combined with the elastic deformation characteristics and the inclination characteristics of the soil body, so that the detection accuracy of the spring soil is higher. Furthermore, the method for detecting the spring soil by the image processing method has lower cost compared with the method for detecting the spring soil by the neural network in the prior art. In conclusion, the spring soil detection accuracy is improved, and meanwhile, the detection cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for detecting spring soil based on computer vision according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating load depth image direction analysis according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of the computer vision-based spring soil detection method according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a concrete scheme of a spring soil detection method based on computer vision, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting spring soil based on computer vision according to an embodiment of the invention is shown, where the method includes:
step S1: and acquiring an original depth image before loading and a loaded depth image after loading of each soil compacting region, and obtaining a pressure change height image according to the difference between the original depth image and the loaded depth image of each soil compacting region.
The invention aims to perform image processing on images before and after rolling according to the height change characteristics before and after rolling of soil body by a soil compactor and the inclination characteristics after rolling, and further realize the detection of spring soil according to the image processing result. The precondition of image processing is that an image of a processing target is obtained, and the fact that the spring soil is rolled and then appears as height change or depth change on physical characteristics is considered, so that the effect of image processing by adopting a depth camera to collect soil images is better than that of an industrial camera reflecting the soil colors, and the depth camera is adopted as image collecting equipment.
The spring soil detection method provided by the invention needs to be obtained according to the height change of soil before and after rolling, and the depth images before and after rolling in the same area need to be shot, so that the same depth cameras are arranged before and after the soil compactor. In order to ensure the accuracy of the depth image photographed by the depth camera and facilitate the subsequent analysis, the photographing angle of the depth camera is set to be vertically downward, and the horizontal heights of the two depth cameras are consistent, and in addition, the setting positions of the two depth cameras in the horizontal direction are required to be ensured to be on the symmetry axis of the soil compactor. The method comprises the steps that an original depth image corresponding to a target soil is shot before a soil compactor rolls the target soil, a load depth image corresponding to the target soil is shot after the soil compactor rolls the target soil, the original depth image corresponding to the target soil corresponds to pixel points on the load depth image one by one, and pixel values corresponding to each pixel point in the original depth image and the load depth image are distances between a shooting instant depth camera and the surface of the soil, wherein the units are millimeters.
In addition, in order to enable the front and rear depth cameras to capture depth images of the same soil compacting region, when the distance traveled by the soil compactor coincides with the distance between the front and rear depth cameras, the corresponding front and rear depth cameras are captured once, respectively. In the embodiment of the invention, the travel distance of the compactor is obtained according to the travel time and the instantaneous speed of the compactor. And further acquiring an original depth image before loading and a loaded depth image after loading of each soil compacting area according to the depth camera.
And obtaining an original depth image and a load depth image of each soil compacting area through a depth camera. Considering that the spring soil has elastic deformation characteristics which cannot be directly shaped due to the fact that the water content is too high, the change difference of the spring soil before and after rolling is too small compared with that of the normal soil, and therefore the pixel value difference between an original depth image and a load depth image of each soil pressing area can be used as a condition for detecting the spring soil. Specific: and obtaining a pressure change height map according to the difference between the original depth image and the load depth image of each soil compacting region. Namely, under the same soil compacting region, the pixel value of each pixel point in the pressure change height map is the difference value between the pixel values of the pixel points at the corresponding positions in the original depth image and the load depth image. Preferably, an original depth image and a load depth image which correspond to each soil compacting area and have the same size are obtained; and marking the pixel values of the target pixel points in the original depth image and the load depth image in the same soil compacting region as the pixel values of the target pixel points in the pressure change height image, and changing the target pixel points to obtain the pixel value of each pixel point in the pressure change height image. Expressed in terms of the formula:
Wherein, the liquid crystal display device comprises a liquid crystal display device,
for the coordinates +.>
Corresponding pixel values of the pixel points in the compaction change height map;
for the coordinates +.>
Corresponding pixel values of the pixel points of the (b) in the original depth map; />
Is given by the coordinates
Corresponding pixel values in the loaded depth map.
Step S2: obtaining a concave region and a convex region according to pixel values in an original depth image; and obtaining the shaping compressibility of each soil compacting region according to the pixel value distribution characteristics of the pixel points in the concave region and the convex region in the pressure change height map.
So far, an original depth image, a load depth image and a compaction change height image corresponding to each soil compacting area are obtained through the step S1. Because gaps exist among soil particles of the normal soil body, the gaps among the corresponding soil particles are reduced after the normal soil body is rolled by the road roller, and the physical characteristics of the gaps are shown as obvious change of the height of the soil body rolled by the soil compactor relative to the original height; the spring soil is deformed to the shape before rolling due to the elastic deformation characteristic of the spring soil, and the physical characteristic of the spring soil is that the height of the soil body rolled by the soil compactor is not obvious relative to the original height. Therefore, the compression characteristics of the soil body are reflected according to the height change of the soil body after rolling, and the characteristics of the spring soil are further characterized according to the compression characteristics. However, the height change of the soil body after rolling is not only determined by the soil type of the soil body, but also the surface concave-convex degree of the soil body needs to be considered, and the concrete is that:
Due to the nature of the construction environment, the soil surface height of the construction site is often uneven. When normal soil is rolled by the soil compactor, the convex part of the soil drops obviously after rolling; the concave part is relatively low, so that the concave part of the soil body can be filled by the soil passing through the convex part after rolling, and the corresponding descending degree is relatively small, so that the concave-convex degree of the soil body before rolling needs to be considered when the compression characteristics of the soil body are reflected, namely, different weights are given to the concave part and the convex part of the surface of the soil body when the compression characteristics of the soil body are calculated, and comprehensive evaluation is carried out.
The invention marks the compression characteristics of the soil body as the shaping compression degree, obtains the concave area and the convex area according to the pixel value in the original depth image, and further obtains the shaping compression degree corresponding to the soil body through the pressure change height map. The original depth image is first required to distinguish between the raised and recessed areas of the soil region. Preferably, the division threshold is obtained by dividing pixel values of all pixel points in the original depth image by adopting an OTSU maximum inter-class variance method, the division threshold is a depth threshold, the pixel points corresponding to the pixel values which are larger than the depth threshold in the original depth image are marked as concave pixel points, the pixel points corresponding to the pixel values which are smaller than the depth threshold in the original depth image are marked as convex pixel points, the area formed by all the concave pixel points is marked as a concave area, and the area formed by all the convex pixel points is marked as a convex area. It should be noted that, the OTSU maximum inter-class variance method is well known in the art, and is not further limited and described herein.
And further obtaining the shaping compressibility of each soil compacting region according to the pixel value distribution characteristics of the pixel points in the concave region and the convex region in the pressure change height map. Preferably, in the pressure change height map, calculating the average value of pixel values of all pixel points in a concave area and marking the average value as a characteristic value of the concave area, calculating the average value of pixel values of all pixel points in a convex area and marking the characteristic value as the characteristic value of the convex area, calculating the difference value between a depth threshold value and the characteristic value of the convex area and marking the difference value as a convex difference value, calculating the difference value between the characteristic value of the concave area and the depth threshold value and marking the difference value as a concave difference value, and taking the ratio of the convex difference value to the concave difference value as the weight value of the characteristic value of the convex area; and adding the result of multiplying the weight value by the characteristic value of the convex area with the characteristic value of the concave area to obtain the molding compressibility of the corresponding soil compacting area. Expressed in terms of the formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,
shaping compressibility of the soil compacting zone, +.>
Is the depth threshold value corresponding to the soil compacting area, +.>
The coordinates in the concave area which is the soil compacting area are +.>
Corresponding pixel values in the pressure change height map,
the sum of the pixel values of all the pixel points in the concave area of the soil compacting area in the pressure change height chart is accumulated, 
The coordinates in the raised area which is the soil compacting area are +.>
Corresponding pixel values of the pixel points of (2) in the pressure change height map, < +.>
For the sum of the pixel values of all pixel points in the convex area of the soil compacting area in the pressure change height map, +.>
The number of pixel points in the concave area of the soil compacting area is +.>
The number of pixel points in the convex area of the soil compacting area.
The degree of plastic compression calculated by the formula reflects the degree of height change of the soil body after the soil compacting area is compacted by the soil compacting machine, and when the degree of height change is larger, the plastic deformation of the soil body is more obvious, and the corresponding saliency of spring soil is lower. In addition, the formula considers the influence of the concave-convex degree of the soil body, takes the mean value of pixel values of different concave-convex regions as the compression degree of the corresponding region, respectively gives different weights to the compression degree of the convex region and the compression degree of the concave region to further calculate the molding compression degree, and the weight of the compression degree of the concave region is set as 1 because the difference of the height change corresponding to the normal soil body when the soil body corresponding to the concave region is spring soil is not large, but the weight of the compression degree of the convex region is expressed as the formula because the height change corresponding to the normal soil body exists in an obvious region when the soil body corresponding to the convex region is spring soil 
Namely, the difference ratio between the difference of the compression degree of the convex area and the depth threshold value and the difference of the compression degree of the concave area and the depth threshold value is used as the weight of the compression degree of the convex area, the weight considers that the depth threshold value is used as the dividing basis of the convex area and the concave area, and the convex area is obviously reduced when compressed and is more easily used as the distinguishing standard of the spring soil, so that the calculated modeling compression degree can more accurately characterize the spring soil characteristics by taking the difference of the depth threshold value and the corresponding concave-convex area as the weight of the convex area. Further pressing the raised area of the soil pressing areaThe compression degree and the compression degree of the concave area are respectively endowed with corresponding weights and then summed up, and the molding compression degree of the soil compacting area can be obtained.
Step S3: and obtaining the shaping flatness according to the pixel value change characteristic difference between the original depth image and the loaded depth image, and obtaining the shaping deformation according to the shaping compression degree and the shaping flatness of each soil compacting area.
So far, the shaping compression degree of all the soil compacting areas is obtained through the step S2, and the shaping compression degree is obtained according to the difference between the height change of the soil body corresponding to the spring soil before and after compression and the height change of the normal soil body before and after compression. In addition, after the normal soil body is rolled by the soil compactor, the surface of the soil body is smoother, but after the soil body corresponding to the spring soil is rolled by the soil compactor, the change is less compared with the change before the rolling of the soil body by the soil compactor due to the elastic deformation characteristic of the spring soil. Therefore, the analysis can be performed according to the change of the flatness of the soil compacting area before and after being compacted by the compactor. The flatness of the soil body is expressed as the variation degree of pixel values of the pixel points on the depth image, namely when the uneven characteristics of pits and depressions on the surface of the soil body are obvious, the variation characteristics of the pixel values of the corresponding pixel points are large; conversely, when the land is relatively flat, the pixel value change characteristic of the corresponding pixel point is small.
According to the method, flatness change before and after rolling of the soil compacting area is represented by the shaping flatness, and comparison is needed according to the condition before and after rolling of the soil compacting area, so that pixel value change characteristics of an original depth image and a load depth image corresponding to the soil compacting area are needed to be obtained firstly, and the pixel value change characteristics are obtained according to pixel value distribution change in the image. The specific method for acquiring the pixel value change characteristics comprises the following steps: optionally selecting one of the original depth image and the load depth image as a target image; and taking each pixel point of the target image as a central pixel point, acquiring a gray level co-occurrence matrix according to the pixel values of the pixel points in a preset neighborhood range of the central pixel point, calculating the contrast corresponding to the gray level co-occurrence matrix, and recording the accumulated sum of the contrast corresponding to all the pixel points in the target image as a pixel value change characteristic. In the embodiment of the invention, the preset neighborhood range is a 5*5 window range. It should be noted that, the method for obtaining the gray level co-occurrence matrix and the method for calculating the contrast of the gray level co-occurrence matrix are well known to those skilled in the art, and are not further limited and described herein.
And obtaining the shaping flatness according to the difference of the pixel value change characteristics between the original depth image and the load depth image after obtaining the pixel value change characteristics of the image before and after the soil compacting area is compacted by the soil compactor through calculation. Specifically: optionally selecting one of the original depth image and the load depth image as a target image; and taking each pixel point of the target image as a central pixel point, acquiring a gray level co-occurrence matrix according to the pixel values of the pixel points in a preset neighborhood range of the central pixel point, calculating the contrast corresponding to the gray level co-occurrence matrix, and recording the accumulated sum of the contrast corresponding to all the pixel points in the target image as a pixel value change characteristic. Expressed in terms of the formula:
Wherein, the liquid crystal display device comprises a liquid crystal display device,
representing the shaping flatness of the soil compacting zone, < ->
Representing coordinates of +.>
The pixel value of the pixel point of (2) in the original depth image changes the characteristic value,/for the pixel point>
Representing coordinates of +.>
The pixel value of the pixel points in the load depth image changes the characteristic value, < + >>
A pixel value variation characteristic representing the original depth image,
representing the pixel value variation characteristics of the load depth image.
The calculated shaping flatness can reflect the flatness change of the soil body surface of the soil compacting area after being rolled by the soil compacting machine, when the flatness change is smaller, the compaction degree change of the soil body of the corresponding soil compacting area after being rolled by the soil compacting machine is smaller, the corresponding shaping flatness is smaller, the soft plastic state of the soil body is more obvious, and the significance of the corresponding spring soil is lower. The difference between the pixel value change characteristics of the original depth image and the load depth image of the soil compacting area is used as the flatness change of the soil surface, the change characteristics of the soil compacting area after rolling can be clearly represented, the pixel value change characteristics of the load depth image are used as denominators to limit the change characteristics, and the spring soil characteristics of the soil are more obvious.
Thus, the molding compression degree and the molding flatness corresponding to all the soil compacting areas are obtained, and the molding compression degree and the molding flatness can reflect the difference between the normal soil body and the soil body corresponding to the spring soil, so that the molding compression degree and the molding flatness of the soil compacting areas are combined to jointly represent the difference between the normal soil body and the soil body corresponding to the spring soil, and the representation value obtained by combining the molding compression degree and the molding flatness is recorded as the molding deformation degree, and the corresponding combination method comprises the following steps: taking the product of the molding compression degree and the molding flatness of each soil compacting area as the molding deformation degree. Expressed in terms of the formula:
Wherein, the liquid crystal display device comprises a liquid crystal display device,
for the shaping deformability of the soil compacting zone, < >>
Shaping compressibility of the soil compacting zone, +.>
Is the shaping flatness of the soil compacting area. The molding deformation value reflects the molding deformation degree of the soil compacting region before and after rolling by the soil compacting machine, and the molding deformation value is measured from the two aspects of the height compression change degree and the surface leveling change degree respectively, when the molding compression degree and the molding leveling degree are larger, the corresponding molding deformation degree is larger, and the spring soil saliency of the corresponding soil compacting region is smaller.
Step S4: obtaining a pixel point characteristic value sequence in the load depth image according to the movement direction of the soil compactor; and obtaining the ground elasticity significance of each soil compacting area according to the element value distribution trend characteristic in the pixel point characteristic value sequence.
So far, the shaping deformation degree of all the soil compacting areas is obtained through the step S2 and the step S3. Considering that the soil body corresponding to the spring soil is damaged due to the fact that the water content is large and capillary holes among soil particles are damaged, the capability of the water in the spring soil to permeate and diffuse outwards is affected, the strength of the soil body is further reduced, and the spring soil body is characterized in that the soil body can elastically vibrate. When the soil compactor rolls on the soil body corresponding to the spring soil, the periphery of a rolling area can bulge, the whole volume of the corresponding soil body is not compressed, and the front side and the rear side of the soil compactor are tilted in the direction away from the vehicle in a tilting manner. And when the normal soil body is rolled by the soil compactor, the volume can shrink, and the corresponding inclination characteristic can be ignored. The invention therefore analyzes according to the characteristic of inclination exhibited during the rolling of the soil mass.
When the soil body is rolled by the soil compactor, if the rolled soil body is spring soil, the images before and after rolling show obvious inclination characteristics, but the inclination characteristics of the soil body can be influenced due to the fact that the surface flatness of the soil body before rolling is poor and the heights of different positions are inconsistent. Therefore, in order to reduce the influence of the soil surface unevenness on the inclined characteristics, the method analyzes the rolled soil image, namely, the load depth image is used as an analysis object of the inclined characteristics.
The stress characteristic direction is obtained according to the condition that the soil compacting area represented by the load depth image is compacted, and the shortest load depth image separated from the compaction time is further analyzed. When the spring soil characteristics of the soil body of the soil pressing area are obvious, the ground heights shown along the stress characteristic direction are sequentially increased on the corresponding load depth map; in contrast, when the spring soil characteristics of the soil body of the soil compacting area are not obvious, the ground height shown along the stress characteristic direction does not change obviously on the corresponding load depth map. Because the camera position for acquiring the load depth image is fixed, the stress direction analysis can be performed by taking the moving direction of the soil compactor as a basis, and then the characteristic value sequence of the pixel points in the load depth image is obtained.
Preferably, in order to embody the characteristics of the spring soil on the load depth map of the soil compacting region, namely the characteristics that the ground heights are sequentially increased along the stress characteristic direction, the invention analyzes according to the pixel value characteristics of each row of pixel points or each column of pixel points on the load depth map. Because the load depth image represents the information that the soil compacting area is compacted by the soil compacting machine, the opposite direction of the soil compacting machine is taken as the stress characteristic direction. Referring to fig. 2, a schematic diagram of load depth image direction analysis provided by an embodiment of the present invention is shown, in fig. 2, the load depth image is acquired by default, the lower boundary is a side close to the soil compactor, the upper boundary is a side far away from the soil compactor, and because the camera for obtaining the load depth image in the embodiment of the present invention is fixed in position, the moving direction of the soil compactor can be considered to be perpendicular to the horizontal boundary of the load depth image, i.e. the direction in which the upper boundary of the load depth image points vertically to the lower boundary is considered to be the moving direction of the soil compactor, the stress feature direction is the lower boundary points vertically to the upper boundary, the lower boundary is defined as the stress side, and the upper boundary is defined as the stress opposite side.
Considering that when the protrusion or depression of the soil surface corresponding to the soil compacting area is more obvious, namely, a larger pit or soil pile appears, the pixel value of the corresponding pixel point is more extreme, and the analysis of the pixel value characteristics of each row of pixel points can be influenced. In order to better characterize the pixel value characteristics of each row of pixel points, the method selects the median value of the pixel values of each row of pixel points as the pixel point characteristic value corresponding to the pixel points, arranges the pixel point characteristic values in the stress characteristic direction as an order to obtain a pixel point characteristic value sequence, and can analyze the inclination characteristics of the soil compacting region according to the distribution trend characteristics of the pixel point characteristic values in the pixel point characteristic value sequence.
The pixel characteristic value sequence can represent the pixel value change corresponding to the pixel points in the load depth image, so that the inclination characteristic of the current soil compacting area after rolling can be analyzed through the distribution trend characteristic of the element values in the pixel characteristic value sequence, and when the spring soil characteristic of the soil body of the soil compacting area is obvious, the corresponding pixel characteristic sequence is an obvious increment sequence with smaller fluctuation; when the spring soil characteristics of the soil body of the soil compacting area are not obvious, the corresponding pixel point characteristic sequence is a sequence without obvious change characteristics. Therefore, in order to embody the characteristics of the spring soil, the numerical variation of the characteristic value of the inner pixel point of the pixel point characteristic sequence needs to be analyzed, so as to obtain the ground elasticity significance of the soil compacting region.
Preferably, considering that the numerical value of the corresponding pixel point sequentially increases from the stress side to the stress side opposite side when the soil body corresponding to the spring soil is crushed, the greater the weight of the soil compactor is, the greater the autocorrelation of the corresponding sequence is, so that the characteristic sequence of the corresponding pixel point of the spring soil has long-term memory. Therefore, the invention takes the autocorrelation of the pixel point characteristic sequence of the spring soil corresponding load depth image and the incremental characteristic of elements into consideration, acquires the hurst index corresponding to the pixel point characteristic sequence, wherein the hurst index can reflect the autocorrelation of the pixel point characteristic sequence, and when the spring soil characteristic corresponding to the soil compacting region is obvious, the corresponding hurst index is in numerical value
Within range and close to 1. And obtaining a hurst index by adopting an aggregation variance method for the pixel characteristic value sequence, and marking the hurst index of the pixel characteristic value sequence as an autocorrelation characteristic value of the load depth image. It should be noted that, the method of polymerization variance is well known in the art, and is not further limited and described herein.
In order to make the incremental characteristic of the elements clearer and reflect the abnormal data in the pixel characteristic sequence, element difference values between every two adjacent elements in the pixel characteristic value sequence are further calculated, the element difference values are recorded as pixel difference characteristic values, the pixel difference characteristic values are used as elements to form a sequence according to the sequence of the elements in the pixel characteristic value sequence, and the sequence is recorded as a pixel difference characteristic value sequence. Under the condition of analyzing the inclination characteristic, the pixel point difference characteristic value sequence can accurately reflect the pixel point characteristic value change process.
Calculating standard deviation among various elements in the pixel point difference characteristic value sequence and recording the standard deviation as characteristic value difference standard deviation of the load depth image, wherein the characteristic value difference standard deviation can reflect whether the pixel point characteristic value has regularity in the change process.
Abnormal data detection is carried out on the pixel point difference characteristic value sequence, the abnormal value quantity is counted, the abnormal value quantity can reflect the abnormal degree of the pixel point characteristic value sequence, and the characteristic of the abnormal degree of the pixel point characteristic value sequence can be more accurate by combining the standard deviation. In the embodiment of the invention, the adopted abnormal data detection method is an LOF abnormal data detection method. It should be noted that, the LOF abnormal data detection method is well known in the art, and is not further limited and described herein.
And recording the autocorrelation characteristic value, the pixel point difference characteristic value, the characteristic value difference standard deviation and the abnormal value quantity of the load depth image as element value distribution trend characteristics in the pixel point characteristic value sequence.
And further obtaining the ground elasticity significance of each soil compacting region according to the element value distribution trend characteristic in the pixel point characteristic value sequence of the load depth image. Preferably, a load depth image of the target soil compacting region is obtained, the product of the characteristic value difference standard deviation of the load depth image and the number of abnormal values is recorded as an abnormal condition characteristic value, the ratio of the autocorrelation characteristic value of the load depth image to the abnormal condition characteristic value plus a preset constant coefficient is calculated and is recorded as an inclined characteristic value, the ratio of the sum of all pixel point difference characteristic values of the load depth image and the number of elements in a pixel point difference characteristic value sequence is recorded as an inclined change degree, and the product of the inclined characteristic value of the load depth image and the inclined change degree is recorded as the ground elasticity significance of the corresponding target soil compacting region. Expressed in terms of the formula:
Wherein, the liquid crystal display device comprises a liquid crystal display device,
for the ground elasticity significance corresponding to the soil compacting area, < ->
Corresponding hurst index for soil compacting zone,/->
Difference standard deviation of characteristic values corresponding to soil compacting areas, < ->
For the number of abnormal values corresponding to the soil compacting area, < + >>
For the number of pixel difference characteristic values, +.>
Is the difference characteristic value of the pixel points, +.>
Representing the sum of all pixel difference characteristic values in the pixel difference characteristic value sequence, +.>
Is the serial number of the pixel difference characteristic value in the pixel difference characteristic value sequence,
is a constant coefficient. In the present embodiment, the constant coefficient +.>
Set to 1, constant coefficient->
The function of (2) is to ensure that the denominator is not zero so that the formula is meaningful. When the spring soil characteristics of the soil body are more obvious, corresponding +.>
The bigger the->
The larger the corresponding ground elasticity significance is greater.
The calculation formula of the ground elasticity significance considers that when the soil body inclination characteristic is obvious, the corresponding ground height is obvious in an increasing or decreasing condition. The invention uses the average value of the difference characteristic values of all pixel points as the inclination change degree, and the larger the average value is, the larger the inclination degree is, and the influence of the error condition on the inclination characteristic calculation can be reduced while the inclination change degree is clearly reflected by using an averaging method. In addition, as the inclination degree of the soil body corresponding to the spring soil after being rolled is related to the weight of the soil compactor and the self-correlation of the inclination characteristics of the soil body is corresponding to the soil body, the influence of the characteristic self-correlation of the hurst index is introduced. Meanwhile, the calculation of the inclination characteristic is influenced by the abnormal condition when the soil body is inclined, and the product of the standard deviation of the characteristic value difference and the quantity of the abnormal value is used as the characteristic value of the abnormal condition, so that the smaller the standard deviation of the characteristic value difference and the quantity of the abnormal value, the more regular the element distribution in the characteristic value sequence of the pixel point difference is, namely the more obvious the inclination corresponding to the opposite surface is. Because the hurst index is positively correlated with the ground elasticity significance and the abnormal condition characteristic value is negatively correlated with the ground elasticity significance, the ratio of the hurst index to the abnormal condition characteristic value is further used as an inclination characteristic value, the inclination change degree is limited by the inclination characteristic value, the autocorrelation of the soil inclination characteristic and the abnormal condition are considered, and the inclination characteristic represented by the ground elasticity significance can be more accurate. The ground elasticity significance calculated by the calculation formula of the ground elasticity significance can accurately reflect the inclination characteristic significance degree of the soil body inclined towards the direction of the soil compactor after the soil body corresponding to the spring soil is rolled by the soil compactor, and when the inclination characteristic significance degree is larger, the ground elasticity significance of the corresponding soil body is larger, namely the probability of the spring soil appearing in the corresponding soil body is larger.
Step S5: and obtaining the spring soil saliency of each soil compacting area according to the molding deformation degree and the ground elasticity saliency of each soil compacting area, and completing the spring soil detection according to the spring soil saliency.
So far, the molding deformation degree and the ground elasticity significance corresponding to all the soil compacting areas are obtained through the step S2, the step S3 and the step S4, and the spring soil significance of each soil compacting area is further obtained according to the molding deformation degree and the ground elasticity significance of each soil compacting area. The invention normalizes the ratio of the ground elasticity significance and the shaping deformation of each soil compacting region to obtain the corresponding spring soil significance. Preferably, the spring significance is obtained by adopting a hyperbolic tangent function to carry out proportional normalization on the ratio of the molding compression degree to the ground elasticity significance in the same soil compacting region. It should be noted that the tanh function is well known in the art, and is not further defined and described herein. The calculation process of the spring soil saliency is expressed as follows in the formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,
spring soil saliency for soil compacting area, < ->
For the ground elasticity significance of the soil compacting region, < +.>
For the shaping deformability of the soil compacting zone, < > >
Representing the hyperbolic tangent function normalization. When (when)The larger the ground elasticity significance of the soil compacting area is, the larger the corresponding spring soil significance is when the molding deformation degree is smaller. The spring soil saliency comprehensively evaluates the salient feature value through the ground elasticity saliency and the shaping deformation degree of the soil compacting area, and when the spring soil saliency is larger, the probability that the spring soil appears in the soil body corresponding to the soil compacting area is more obvious.
When the spring soil saliency of the soil pressing area is smaller than a preset spring soil threshold, the soil corresponding to the current soil pressing area is considered to be normal soil, and the soil is not treated; when the saliency of the spring soil in the soil compacting area is larger than or equal to a preset spring soil threshold value, the spring soil is considered to appear in the soil body in the current soil compacting area, the construction process can be influenced, and the soil of the soil body needs to be treated in time. In the embodiment of the invention, the preset spring soil threshold is 0.8.
The present invention has been completed.
In summary, the original depth image before the soil compacting area is compacted by the soil compacting machine and the load depth image after the compaction are obtained by the depth camera, the pressure change height image is obtained according to the difference between the original depth image and the load depth image, the shaping compressibility is obtained according to the pixel value distribution characteristics in the original depth image and the pressure change height image, the shaping flatness is obtained according to the pixel value change characteristics of the original depth image and the depth image after the load, the shaping deformability is obtained according to the shaping compressibility and the shaping flatness, the ground elasticity significance is obtained according to the load depth image, the spring soil significance is obtained according to the shaping deformability and the ground elasticity significance, and the spring soil detection is completed according to the spring soil significance. The invention improves the spring soil detection accuracy and reduces the detection cost.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (3)
1. The spring soil detection method based on computer vision is characterized by comprising the following steps of:
acquiring an original depth image before loading and a loaded depth image after loading of each soil compacting area, and obtaining a pressure change height image according to the difference between the original depth image and the loaded depth image of each soil compacting area;
obtaining a concave region and a convex region according to pixel values in the original depth image; obtaining the shaping compressibility of each soil compacting region according to the pixel value distribution characteristics of the pixel points in the concave region and the convex region in the pressure change height map;
Obtaining shaping flatness according to the pixel value change characteristic difference between the original depth image and the load depth image, and obtaining shaping deformation according to the product of the shaping compression degree and the shaping flatness of each soil compacting area;
obtaining a pixel point characteristic value sequence in the load depth image according to the moving direction of the soil compactor; obtaining the ground elasticity significance of each soil compacting area according to the element value distribution trend characteristic in the pixel point characteristic value sequence;
obtaining the spring soil saliency of each soil compacting area according to the molding deformation degree and the ground elasticity saliency of each soil compacting area, and completing spring soil detection according to the spring soil saliency;
the method for acquiring the concave area and the convex area of the pressure change height map comprises the following steps:
dividing pixel values of all pixel points in the original depth image by adopting an OTSU maximum inter-class variance method to obtain a division threshold, wherein the division threshold is a depth threshold, pixel points corresponding to pixel values larger than the depth threshold in the original depth image are marked as concave pixel points, pixel points corresponding to pixel values smaller than the depth threshold in the original depth image are marked as convex pixel points, an area formed by all the concave pixel points is marked as a concave area, and an area formed by all the convex pixel points is marked as a convex area;
The method for obtaining the molding compression degree comprises the following steps:
in the pressure change height map, calculating the average value of pixel values of all pixel points of the concave area and marking the average value as a characteristic value of the concave area, calculating the average value of pixel values of all pixel points of the convex area and marking the characteristic value of the convex area, calculating the difference value between the depth threshold value and the characteristic value of the convex area and marking the difference value as a convex difference value, calculating the difference value between the characteristic value of the concave area and the depth threshold value and marking the difference value as a concave difference value, and taking the ratio of the convex difference value and the concave difference value as the weight value of the characteristic value of the convex area; adding the result of multiplying the weight value by the characteristic value of the convex area with the characteristic value of the concave area to obtain the molding compression degree of the corresponding soil compacting area;
the method for obtaining the shaping flatness comprises the following steps:
calculating the difference between the pixel value change characteristics of the pressure change height map and the load depth image in the same soil compacting region, marking the difference as flatness difference, and marking the ratio between the flatness difference and the pixel value change characteristics of the load depth image as the shaping flatness of the corresponding soil compacting region;
the method for acquiring the pixel point characteristic value sequence comprises the following steps:
In the load depth image, the reverse direction of the movement direction of the soil compactor is taken as the stress characteristic direction;
counting the median value of pixel values of each row of pixel points in the load depth image, marking the median value as a pixel point characteristic value, and arranging the pixel point characteristic values in order of the stress characteristic direction to obtain a pixel point characteristic value sequence;
the method for acquiring the element value distribution trend characteristics in the pixel point characteristic value sequence comprises the following steps:
obtaining a hurst index by adopting an aggregation variance method for the pixel characteristic value sequence, and recording the hurst index of the pixel characteristic value sequence as an autocorrelation characteristic value of the load depth image;
calculating element difference values between every two adjacent elements in the pixel characteristic value sequence, marking the element difference values as pixel difference characteristic values, forming a sequence by taking the pixel difference characteristic values as elements according to the sequence of the elements in the pixel characteristic value sequence, and marking the sequence as a pixel difference characteristic value sequence;
calculating standard deviation among various elements in the pixel point difference characteristic value sequence, recording the standard deviation as characteristic value difference standard deviation of the load depth image, detecting abnormal data of the pixel point difference characteristic value sequence, and counting the number of abnormal values;
Recording the autocorrelation characteristic value, the pixel point difference characteristic value, the characteristic value difference standard deviation and the abnormal value quantity of the load depth image as the distribution trend characteristic;
the method for acquiring the ground elasticity significance comprises the following steps:
acquiring the load depth image of a target soil compacting region, recording the product of the characteristic value difference standard deviation of the load depth image and the abnormal value quantity as an abnormal condition characteristic value, calculating the ratio of the autocorrelation characteristic value of the load depth image to the abnormal condition characteristic value plus a preset constant coefficient, recording the ratio of the sum of all pixel point difference characteristic values of the load depth image to the element quantity in the pixel point difference characteristic value sequence as an inclination change degree, and recording the product of the inclination characteristic value of the load depth image and the inclination change degree as the ground elasticity significance of the corresponding target soil compacting region;
the method for obtaining the spring soil saliency comprises the following steps:
and carrying out proportional normalization on the ratio of the molding compression degree to the ground elasticity significance in the same soil compacting region by adopting a hyperbolic tangent function to obtain the spring soil significance.
2. The computer vision-based spring soil detection method according to claim 1, wherein the method for acquiring the pixel value change characteristics comprises the following steps:
optionally selecting one of the original depth image and the load depth image as a target image;
and taking each pixel point of the target image as a central pixel point, acquiring a gray level co-occurrence matrix according to the pixel values of the pixel points in a preset neighborhood range of the central pixel point, calculating the contrast corresponding to the gray level co-occurrence matrix, and recording the accumulated sum of the contrast corresponding to all the pixel points in the target image as a pixel value change characteristic.
3. The computer vision-based spring soil detection method according to claim 1, wherein the method for acquiring the pressure change height map comprises the following steps:
obtaining the original depth image and the load depth image which correspond to each soil compacting area and have the same size; and marking the pixel values of the target pixel points in the original depth image and the load depth image in the same soil compacting region as the pixel values of the target pixel points in the pressure change height map, and changing the target pixel points to obtain the pixel value of each pixel point in the pressure change height map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139076.1A CN115830029B (en) | 2023-02-21 | 2023-02-21 | Spring soil detection method based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139076.1A CN115830029B (en) | 2023-02-21 | 2023-02-21 | Spring soil detection method based on computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115830029A CN115830029A (en) | 2023-03-21 |
| CN115830029B true CN115830029B (en) | 2023-04-28 |
Family
ID=85521947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310139076.1A Active CN115830029B (en) | 2023-02-21 | 2023-02-21 | Spring soil detection method based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115830029B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104103082A (en) * | 2014-06-06 | 2014-10-15 | 华南理工大学 | Image saliency detection method based on region description and priori knowledge |
| CN106872472A (en) * | 2017-01-17 | 2017-06-20 | 中交武汉港湾工程设计研究院有限公司 | Surface Quality of Concrete method of determination and evaluation |
| CN114972906A (en) * | 2022-05-05 | 2022-08-30 | 同济大学 | Soil quality type identification method for excavation surface of soil pressure balance shield |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103033456B (en) * | 2012-12-13 | 2015-06-03 | 北京农业信息技术研究中心 | Soil porosity detection method based on SFS (Shape from Shading) algorithm |
| US9299004B2 (en) * | 2013-10-24 | 2016-03-29 | Adobe Systems Incorporated | Image foreground detection |
| US10699151B2 (en) * | 2016-06-03 | 2020-06-30 | Miovision Technologies Incorporated | System and method for performing saliency detection using deep active contours |
| CN111145161B (en) * | 2019-12-28 | 2023-09-19 | 北京工业大学 | Pavement crack digital image processing and identifying method |
| CN111932537B (en) * | 2020-10-09 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Object deformation detection method and device, computer equipment and storage medium |
| CN114782419B (en) * | 2022-06-17 | 2022-08-23 | 山东水利建设集团有限公司 | Water conservancy construction gradient detection method |
-
2023
- 2023-02-21 CN CN202310139076.1A patent/CN115830029B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104103082A (en) * | 2014-06-06 | 2014-10-15 | 华南理工大学 | Image saliency detection method based on region description and priori knowledge |
| CN106872472A (en) * | 2017-01-17 | 2017-06-20 | 中交武汉港湾工程设计研究院有限公司 | Surface Quality of Concrete method of determination and evaluation |
| CN114972906A (en) * | 2022-05-05 | 2022-08-30 | 同济大学 | Soil quality type identification method for excavation surface of soil pressure balance shield |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115830029A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103207987B (en) | A kind of registration recognition methods of pointer instrument | |
| CN110533686B (en) | Method and system for judging whether line frequency of linear array camera is matched with object motion speed | |
| CN110611770B (en) | Method and system for judging whether line frequency of linear array camera is matched with object motion speed | |
| CN113605188B (en) | Pavement structure testing method | |
| CN106978774A (en) | A kind of road surface pit automatic testing method | |
| CN110346151B (en) | Apparatus and computer-implemented method for determining the mass of a tire | |
| CN104766335A (en) | Geotechnical material deformation digital image correlation analysis and optimization method | |
| CN113240735B (en) | Slope displacement activity monitoring method | |
| CN116399302B (en) | Method for monitoring dynamic compaction settlement in real time based on binocular vision and neural network model | |
| CN116580032B (en) | Quality monitoring method for road construction | |
| CN111473776A (en) | Landslide crack monitoring method based on single-image close-range photogrammetry | |
| CN106778683A (en) | Based on the quick Multi-angle face detection method for improving LBP features | |
| CN116309557B (en) | Method for detecting fracture of track shoe of excavator | |
| CN103500453A (en) | SAR(synthetic aperture radar) image significance region detection method based on Gamma distribution and neighborhood information | |
| CN115830029B (en) | Spring soil detection method based on computer vision | |
| CN108153979A (en) | Deformation information extraction method based on InSAR, terminal and storage medium | |
| CN112284980A (en) | Reagent asphalt static contact angle testing method, device and system | |
| CN115797338B (en) | Panoramic pavement multi-performance index calculation method and system based on binocular vision | |
| CN111612734B (en) | Background clutter characterization method based on image structure complexity | |
| US20070008491A1 (en) | Online wavefront measurement and display | |
| CN116429295A (en) | Method for evaluating contact stress distribution of rock mass structural plane | |
| CN116363617A (en) | Ultra-small curvature lane line detection method | |
| CN110689537B (en) | Method and system for judging whether line-scan camera is used for acquiring images at constant speed | |
| Hu et al. | Three-dimensional characterization method of pile–rock interface roughness based on fractal geometry | |
| CN109862349A (en) | Quality determining method, device and the automated driving system of disparity map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |