An integrated slope monitoring system and method based on laser radar

Abstract

The present invention discloses an integrated slope monitoring system and method based on laser radar, which relates to the field of slope monitoring technology. The method includes the following steps: installing a laser radar and a high-definition camera on each slope within the current area, performing a three-dimensional scan of the slope using the laser radar to obtain slope surface point cloud data, grouping the slopes based on the soil characteristics of the current area, and recording the collected slope data; determining the slope abnormality location based on the density and elevation of the abnormal point cloud in the point cloud data of the slope, obtaining the coordinates of the abnormal location through position coordinate conversion, and performing main and side view image acquisition of the coordinate location using the high-definition camera; extracting lines from the main and side views of the abnormal location, and performing parameter analysis on the curvature and distance of the lines in the main and side views. By combining the advantages of laser radar and image analysis, the present invention reduces the amount of data processing during slope monitoring and improves the accuracy of abnormality identification and monitoring efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of slope monitoring, and in particular to an integrated slope monitoring system and method based on laser radar. Background Art

[0002] Slope stability monitoring is a critical safety guarantee in fields such as geological engineering, transportation construction, and mining. Traditional slope monitoring methods, such as manual inspections and total station measurements, suffer from low efficiency, strong subjectivity, and low monitoring frequency. These methods make it difficult to capture subtle slope changes in real time, and thus fail to meet the timeliness and accuracy requirements of modern engineering safety monitoring.

[0003] With the development of technology, although monitoring technology based on image recognition can intuitively reflect the surface condition of the slope, it needs to process massive amounts of image data when facing large-area slopes, which results in heavy computational load and low analysis efficiency, leading to high misjudgment and missed judgment rates in abnormality identification. Existing lidar monitoring technology, although it can quickly obtain three-dimensional point cloud data of the slope, lacks in-depth analysis and accurate judgment of abnormal data. It is difficult to accurately distinguish real dangerous abnormal situations from complex point cloud data, and it is also impossible to effectively predict potential slope abnormal areas. It has problems of low practicality and functionality.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in the related art, the present invention proposes an integrated slope monitoring system and method based on laser radar to overcome the above-mentioned technical problems existing in the existing related art.

[0006] To this end, the specific technical solutions adopted in the present invention are as follows:

[0007] An integrated slope monitoring method based on laser radar comprises the following steps:

[0008] S1. Install laser radar and high-definition cameras on the slopes within the current area. Use the laser radar to perform three-dimensional scanning of the slopes to obtain slope surface point cloud data. Based on the soil characteristics of the current area, the slopes under the jurisdiction are grouped and divided, and the collected slope data is recorded.

[0009] S2. Determine the abnormal location of the slope based on the density and elevation of the abnormal point cloud in the point cloud data of the slope, obtain the coordinates of the abnormal location through position coordinate conversion, and capture the main and side view images of the coordinate location using a high-definition camera;

[0010] S3. Extract lines from the main and side views of the abnormal location, perform parameter analysis on the curvature and distance of the lines in the main and side views, determine the type of slope abnormal point, including depression, protrusion, and crack, and combine other identical abnormal parameters under the same soil characteristics within the same group to determine the slope abnormality;

[0011] S4. Capture images of the slope using a high-definition camera, manually mark potential abnormal locations, extract data on potential abnormal locations and reconcile them with the lidar point cloud data, and monitor and identify potential abnormalities on the slope based on the data upload results of potential abnormal locations.

[0012] As a preferred embodiment, the S1 includes the following steps: S11, based on the area of ​​the subordinate slope and the parameters of the laser radar, setting a laser radar on the slope, and scanning the slope by the laser radar to obtain surface point cloud data;

[0013] S12. Collect geological survey reports and soil samples of different slopes in the current area, including soil type, density, water content, and particle size distribution. Determine the slopes with the same soil type and density, water content, and particle size distribution within a similar error range as similar slopes. A slope monitoring database is established, and slopes of the same type are divided into the same group. At the same time, according to the rock structure of the slope, the group is further subdivided into layered structure slopes, block structure slopes, and mesh structure slopes. The slope numbers and point cloud data are recorded at the same time.

[0014] As a preferred embodiment, the S2 includes the following steps: S21, dividing the subordinate slopes into different areas, and marking abnormal areas according to the point cloud density and elevation value in each area, combined with the current slope point cloud density and elevation value normal values;

[0015] S22. For each point cloud data obtained by scanning the slope, a three-dimensional spatial coordinate system is established and the three-dimensional center coordinates of each divided area are marked to obtain the characteristic coordinates of the marked abnormal area. Based on the characteristic coordinates of the abnormal area, the main view image and side view image of the abnormal site of the abnormal area under the corresponding characteristic coordinates are collected by a high-definition camera and uploaded to the slope monitoring database.

[0016] As a preferred embodiment, the S21 includes the following steps:

[0017] S211, for the point cloud data obtained on the slope, the point cloud data on the slope is divided into grids according to a fixed spacing to obtain The number of point clouds in each area is counted as the point cloud density feature of the current area. The area without abnormal deformation or damage signs on the current slope is selected as the normal sample area to calculate the mean and standard deviation of the point cloud density feature. The range from mean -2 standard deviations to mean +2 standard deviations is taken as the normal interval. The area outside the normal interval is determined as the abnormal point cloud density area.

[0018] S212, at the same time Point cloud data points for each area in the , based on the radius Determine the neighborhood of the current point cloud data, and calculate the average elevation value of all points in the neighborhood of the point. ,in represents the points in the neighborhood, Representing the first The elevation value of the point, calculate the current point Elevation value and the neighborhood average elevation The difference ,when When , it means that there is an abnormal elevation value in the current area, and the current area is judged as an abnormal elevation value area. Represents the elevation value threshold.

[0019] As a preferred embodiment, S3 includes the following steps:

[0020] S31, performing two-dimensional conversion and line extraction on the images based on the obtained front view image and side view image of the abnormal area, and performing parameter analysis on the curvature and spacing of the lines in the front view image and the side view image to determine the slope abnormality type of the current abnormal area;

[0021] S32. By grouping the slopes under the jurisdiction of the slope monitoring database, statistics are collected on the slope anomalies under the sub-items in the same group by type, and the serious anomalies of the slopes are analyzed and determined.

[0022] As a preferred embodiment, the S31 includes the following steps:

[0023] S311, for the main view image and side view image of the abnormal area obtained, the formula Perform grayscale processing on the image, where R, G, and B represent the pixel values ​​of the red, green, and blue channels respectively. At the same time, perform histogram equalization on the image to enhance the contrast of the image;

[0024] S312, using an edge detection algorithm to extract abnormal edge information from the abnormal area image, using a Gaussian filter to smooth the image to reduce the influence of noise, calculating the gradient of the image in the horizontal and vertical directions to obtain the gradient amplitude and gradient direction, performing non-maximum suppression in the gradient direction to retain the point with the maximum local gradient amplitude to refine the edge, and marking the edge points through dual threshold detection, the steps are as follows:

[0025] Setting the threshold 、 ,in < , the gradient amplitude is greater than The points with gradient amplitude less than The points with a gradient between 、 The points between are marked as pending points. When the pending points are connected to strong edge points, they are determined to be strong edge points. When the pending points are connected to non-edge points, they are determined to be non-edge points.

[0026] S313, perform line fitting on the obtained strong edge points, use the polynomial fitting method to determine the line parameters by minimizing the sum of squared errors, calculate the curvature of the line to obtain the curvature of the line, discretize the line to calculate the discrete curvature, select three points in the curve and calculate the discrete curvature by the inverse of the radius of the circumscribed circle of the triangle , and choose to calculate the vertical distance between the corresponding points of two adjacent lines at multiple points at the same time , take the average value as the current line spacing distance ;

[0027] S314, through the obtained discrete curvature and line spacing of the lines in different abnormal areas, through the interval distance threshold and curvature threshold , determine the exception type:

[0028] When the lines obtained in the abnormal area and When , it means that the lines in the current area tend to sink toward the inside of the slope, which is judged as a concave anomaly;

[0029] When the lines obtained in the abnormal area only meet When , it means that there is abnormal crack in the current area;

[0030] When the lines obtained in the abnormal area and When , it means that when the curvature of the line shows a tendency to bulge outwards towards the slope, and the interval between the lines in the bulge area does not change significantly, it is judged as a bulge anomaly;

[0031] When the above three conditions are not met, the current area is marked as normal.

[0032] As a preferred embodiment, the S32 includes the following steps:

[0033] S321. Based on the slope numbers of the subdivided items in the same group in the slope monitoring database, extract the abnormal data of depressions, protrusions, and cracks, including curvature and interval distance, and determine the severe outliers of the curvature and interval distance in the subdivided items by using the interquartile range method. The specific steps are as follows:

[0034] For the abnormal data of depression, bulge and crack, obtain the curvature and interval distance values ​​of the slope in the same subdivision project under the corresponding abnormality, sort the data from small to large, and calculate the first quartile and the third quartile , calculate the interquartile range ,in represents the interquartile range;

[0035] Get the lower limit and upper limit , judge the curvature and interval distance values ​​of the slope in the same subdivision project under the same anomaly, and and greater than The exception is marked as a serious exception.

[0036] As a preferred embodiment, the S4 comprises the following steps:

[0037] S41. Capturing images of the slope at fixed intervals using a high-definition camera, manually identifying and marking potential abnormal locations, and determining the position coordinates of the manually marked potential abnormal locations using the point cloud data of the laser radar;

[0038] S42, comparing the potential abnormal position coordinates with the characteristic coordinates of the marked abnormal area uploaded in the slope monitoring database, and ignoring the current potential abnormal position when the potential abnormal position coordinates match the existing characteristic coordinates of the marked abnormal area;

[0039] S43. When the coordinates of the potential abnormality position do not match the characteristic coordinates of the existing marked abnormal area, repeat S3 to analyze and determine the potential abnormality.

[0040] As a preferred embodiment, the S43 further includes the following steps:

[0041] S431. When the coordinates of the potential abnormal position do not match the characteristic coordinates of the existing marked abnormal area, the point cloud data within the current potential abnormal position coordinate area is extracted at the same time, and the similarity between the point cloud data of other areas and the current abnormal position coordinate area is calculated by Euclidean distance. For areas with similarity less than 0.3, similar abnormality marking is performed, and S3 is repeated to perform abnormality analysis and judgment on similar abnormal areas.

[0042] An integrated slope monitoring system based on laser radar includes a data acquisition module, a parameter conversion and anomaly recognition module, and a potential anomaly determination module:

[0043] The data acquisition module includes a laser radar and a high-definition camera. The laser radar performs a three-dimensional scan of the slope to obtain the slope surface point cloud data, and the high-definition camera collects the image data of the slope abnormal position. At the same time, based on the soil characteristics of the current area, Establish a slope monitoring database to group and divide the slopes under its jurisdiction, and record the collected slope data;

[0044] The parameter conversion and anomaly identification module determines the slope anomaly location through the density and elevation of the abnormal point cloud in the point cloud data of the slope, obtains the coordinates of the anomaly location through position coordinate conversion, collects the main and side view images of the coordinate location using a high-definition camera, extracts lines from the main and side views of the anomaly location, performs parameter analysis on the curvature and distance of the lines in the main and side views, determines the type of the slope anomaly location, including depression, protrusion, and crack, and combines other identical anomaly parameters under the same soil characteristics within the same group to determine the slope anomaly.

[0045] The potential anomaly determination module manually marks the potential anomaly locations through the slope images captured by the high-definition camera, extracts the potential anomaly location data and reconciles it with the lidar point cloud data, and monitors and identifies potential anomalies and similar anomalies on the slope based on the data uploaded results of the potential anomaly locations.

[0046] The beneficial effects of the present invention are:

[0047] 1. The present invention uses laser radar to collect slope point cloud data to determine the abnormal location, further obtains images of the abnormal location, and extracts lines from the image to highlight the abnormal structural features, reducing the computational complexity of abnormality identification during the monitoring process. At the same time, based on the same abnormal data under the same geological characteristics, the present invention determines the most serious abnormalities in the slope during the slope monitoring process, making it easier for managers to maintain the slope in a timely manner.

[0048] 2. The present invention first uses lidar to collect point cloud data to determine the abnormal location, then specifically obtains images of the abnormal location and performs line extraction, which can focus on key areas and features. Compared with long-term comprehensive monitoring and analysis of the entire slope image, this method greatly reduces the amount of data that needs to be processed, thereby significantly shortening the calculation time, improving operating efficiency, and obtaining monitoring results more quickly, enhancing practicality. At the same time, line extraction of the abnormal location image can highlight the abnormal structural features, such as cracks, depressions, and protrusions. These key abnormal features are clearer after line extraction, reducing the probability of misjudgment and missed judgment during the monitoring process;

[0049] 3. The present invention obtains an overall image of the monitored slope on a regular basis, manually marks potential anomalies, combines the potential anomaly coordinates with the characteristic coordinates of the existing abnormal area, performs potential anomaly analysis on the unrecorded area, and simultaneously performs similarity judgment on the point cloud data of the potential abnormal area. Similar anomaly analysis is simultaneously performed on the remaining areas of the slope that meet the similarity judgment, thereby further improving the accuracy of slope monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 is a flow chart of an integrated slope monitoring method based on laser radar according to an embodiment of the present invention;

[0052] Figure 2 4 is a block diagram of an integrated slope monitoring system based on laser radar according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0054] According to an embodiment of the present invention, a laser radar-based integrated slope monitoring system and method are provided.

[0055] The present invention will now be further described with reference to the accompanying drawings and specific embodiments:

[0056] Example 1: Figure 1 As shown, according to an embodiment of the present invention, an integrated slope monitoring method based on laser radar includes the following steps:

[0057] S1. Install laser radar and high-definition cameras on the slopes within the current area. Use the laser radar to perform three-dimensional scanning of the slopes to obtain slope surface point cloud data. Based on the soil characteristics of the current area, the slopes under the jurisdiction are grouped and divided, and the collected slope data is recorded.

[0058] S11. Based on the area of ​​the subordinate slope and the parameters of the laser radar, a laser radar is set on the slope, and the slope is scanned by the laser radar to obtain surface point cloud data;

[0059] S12. Collect geological survey reports and soil samples of different slopes in the current area, including soil type, density, water content, and particle size distribution. Determine the slopes with the same soil type and density, water content, and particle size distribution within a similar error range as similar slopes. A slope monitoring database is established, and slopes of the same type are divided into the same group. At the same time, according to the rock structure of the slope, the group is further subdivided into layered structure slopes, block structure slopes, and mesh structure slopes. The slope numbers and point cloud data are recorded at the same time.

[0060] It should be noted that in the process of determining soil type consistency, the type of soil on each slope was clarified according to the commonly used domestic soil classification standard. If the soils on two slopes belonged to the same classification unit, such as silty clay, they were considered to have the same soil type. The density of the soil on each slope was measured using the ring knife method and wax seal method. The difference in soil density between different slopes was calculated and determined using the error range. The error range of soil density was ±0.5 g / cm³. The water content of the soil on each slope was measured using the oven drying method. The mean water content of the soil on different slopes was compared. If the difference was within ±3%, it indicated that the water content of the current slopes was similar. The effective particle size, average particle size, and limiting particle size of the soil on different slopes were selected, and the ratio of the characteristic particle size of the soil on different slopes was calculated. When the ratio of the characteristic particle size was between 0.9 and 1.1, it indicated that the particle gradation of the current slopes was similar.

[0061] S2. Determine the abnormal location of the slope based on the density and elevation of the abnormal point cloud in the point cloud data of the slope, obtain the coordinates of the abnormal location through position coordinate conversion, and capture the main and side view images of the coordinate location using a high-definition camera;

[0062] S21. Divide the subordinate slopes into different areas, and mark abnormal areas based on the point cloud density and elevation value in each area, combined with the current normal values ​​of the slope point cloud density and elevation value;

[0063] S211, for the point cloud data obtained on the slope, the point cloud data on the slope is divided into grids according to a fixed spacing to obtain The number of point clouds in each area is counted as the point cloud density feature of the current area. The area without abnormal deformation or damage signs on the current slope is selected as the normal sample area to calculate the mean and standard deviation of the point cloud density feature. The range from mean -2 standard deviations to mean +2 standard deviations is taken as the normal interval. The area outside the normal interval is determined as the abnormal point cloud density area.

[0064] It should be noted that when determining areas on the current slope that have no signs of abnormal deformation or damage, it is necessary to combine field photos of the slope, consult current experts in the field, and rely on empirical methods to determine.

[0065] S212, at the same time Point cloud data points for each area in the , based on the radius Determine the neighborhood of the current point cloud data, and calculate the average elevation value of all points in the neighborhood of the point. ,in represents the points in the neighborhood, Representing the first The elevation value of the point, calculate the current point Elevation value and the neighborhood average elevation The difference ,when When , it means that there is an abnormal elevation value in the current area, and the current area is judged as an abnormal elevation value area. Represents the elevation value threshold.

[0066] It should be noted that the radius The threshold value needs to be determined based on the empirical method according to the density of the point cloud data in the current area. By considering factors such as the complexity of the current regional terrain and data accuracy, and consulting with current field experts, the appropriate threshold is determined.

[0067] S22. For each point cloud data obtained by scanning the slope, a three-dimensional spatial coordinate system is established and the three-dimensional center coordinates of each divided area are marked to obtain the characteristic coordinates of the marked abnormal area. Based on the characteristic coordinates of the abnormal area, the main view image and side view image of the abnormal site of the abnormal area under the corresponding characteristic coordinates are collected by a high-definition camera and uploaded to the slope monitoring database.

[0068] Example 2: S3, extracting lines from the main and side views of the abnormal location, performing parameter analysis on the curvature and distance of the lines in the main and side views, determining the type of the slope abnormal point, including depression, protrusion, and crack, and combining other identical abnormal parameters under the same soil characteristics within the same group to determine the slope abnormality;

[0069] S31, performing two-dimensional conversion and line extraction on the images based on the obtained front view image and side view image of the abnormal area, and performing parameter analysis on the curvature and spacing of the lines in the front view image and the side view image to determine the slope abnormality type of the current abnormal area;

[0070] S311, for the main view image and side view image of the abnormal area obtained, the formula Perform grayscale processing on the image, where R, G, and B represent the pixel values ​​of the red, green, and blue channels respectively. At the same time, perform histogram equalization on the image to enhance the contrast of the image;

[0071] It should be noted that when adjusting the histogram of an image, it is assumed that the grayscale value of the original image is , the gray value after transformation is , then the transformation function of histogram equalization is:

[0072] ;

[0073] in, is the total number of gray levels, Represents grayscale The probability density function of .

[0074] S312, using an edge detection algorithm to extract abnormal edge information from the abnormal area image, using a Gaussian filter to smooth the image to reduce the influence of noise, calculating the gradient of the image in the horizontal and vertical directions to obtain the gradient amplitude and gradient direction, performing non-maximum suppression in the gradient direction to retain the point with the maximum local gradient amplitude to refine the edge, and marking the edge points through dual threshold detection, the steps are as follows:

[0075] Setting the threshold 、 ,in < , the gradient amplitude is greater than The points with gradient amplitude less than The points with a gradient between 、 The points between are marked as pending points. When the pending points are connected to strong edge points, they are determined to be strong edge points. When the pending points are connected to non-edge points, they are determined to be non-edge points.

[0076] It should be noted that dual threshold processing can effectively remove false edges caused by noise while retaining the real abnormal edges in the image. The settings of high and low thresholds can be set by consulting experts in related fields and combining actual usage with empirical methods.

[0077] S313, perform line fitting on the obtained strong edge points, use the polynomial fitting method to determine the line parameters by minimizing the sum of squared errors, calculate the curvature of the line to obtain the curvature of the line, discretize the line to calculate the discrete curvature, select three points in the curve and calculate the discrete curvature by the inverse of the radius of the circumscribed circle of the triangle , and choose to calculate the vertical distance between the corresponding points of two adjacent lines at multiple points at the same time , take the average value as the current line spacing distance ;

[0078] S314, through the obtained discrete curvature and line spacing of the lines in different abnormal areas, through the interval distance threshold and curvature threshold , determine the exception type:

[0079] When the lines obtained in the abnormal area and When , it means that the lines in the current area tend to sink toward the inside of the slope, which is judged as a concave anomaly;

[0080] When the lines obtained in the abnormal area only meet When , it means that there is abnormal crack in the current area;

[0081] When the lines obtained in the abnormal area and When , it means that when the curvature of the line shows a tendency to bulge outwards towards the slope, and the interval between the lines in the bulge area does not change significantly, it is judged as a bulge anomaly;

[0082] When the above three conditions are not met, the current area is marked as normal.

[0083] It should be noted that the interval distance threshold and curvature threshold , it is necessary to collect a large amount of slope monitoring image data that are similar to the current slope geological conditions, environmental factors, and data collection methods, and mark the normal areas and known abnormal areas in these data, calculate the curvature and interval distance of the lines in the normal areas and abnormal areas, and obtain a series of curvature values ​​and interval distance values. The training set is constructed according to the label of the abnormal type to build a machine learning model, and the interval distance threshold and curvature threshold are determined by analyzing the decision boundary of the model.

[0084] S32. Based on the slope grouping in the slope monitoring database, statistics are collected on slope anomalies under the sub-items in the same group by type, and the existence of severe slope anomalies is analyzed and determined;

[0085] S321. Based on the slope numbers of the subdivided items in the same group in the slope monitoring database, extract the abnormal data of depressions, protrusions, and cracks, including curvature and interval distance, and determine the severe outliers of the curvature and interval distance in the subdivided items by using the interquartile range method. The specific steps are as follows:

[0086] For the abnormal data of depression, bulge and crack, obtain the curvature and interval distance values ​​of the slope in the same subdivision project under the corresponding abnormality, sort the data from small to large, and calculate the first quartile and the third quartile , calculate the interquartile range ,in represents the interquartile range;

[0087] Get the lower limit and upper limit , judge the curvature and interval distance values ​​of the slope in the same subdivision project under the same anomaly, and and greater than The exception is marked as a serious exception.

[0088] It should be noted that by jointly analyzing anomalies of similar geological types and using the quartiles of the data to determine the distribution range of the data, data outside this range in the same sub-project are considered severe anomalies, which facilitates subsequent maintenance of severely abnormal slopes and further observation of anomalies that are not within the range.

[0089] S4. Use high-definition cameras to collect images of the slope, manually mark potential abnormal locations, extract data on potential abnormal locations and reconcile them with the lidar point cloud data. Based on the data upload results of potential abnormal locations, monitor and identify potential abnormalities on the slope;

[0090] S41. Capturing images of the slope at fixed intervals using a high-definition camera, manually identifying and marking potential abnormal locations, and determining the position coordinates of the manually marked potential abnormal locations using the point cloud data of the laser radar;

[0091] S42, comparing the potential abnormal position coordinates with the characteristic coordinates of the marked abnormal area uploaded in the slope monitoring database, and ignoring the current potential abnormal position when the potential abnormal position coordinates match the existing characteristic coordinates of the marked abnormal area;

[0092] S43. When the coordinates of the potential abnormality position do not match the characteristic coordinates of the existing marked abnormal area, repeat S3 to analyze and determine the potential abnormality.

[0093] It should be noted that the slope images are collected at fixed intervals using high-definition cameras, with a cycle of 7 days. The cycle can also be shortened or extended based on actual conditions.

[0094] S431. When the coordinates of the potential abnormal position do not match the characteristic coordinates of the existing marked abnormal area, the point cloud data within the current potential abnormal position coordinate area is extracted at the same time, and the similarity between the point cloud data of other areas and the current abnormal position coordinate area is calculated by Euclidean distance. For areas with similarity less than 0.3, similar abnormality marking is performed, and S3 is repeated to perform abnormality analysis and judgment on similar abnormal areas.

[0095] It should be noted that in the process of identifying some tiny cracks, the point cloud resolution of the lidar may not meet the requirements for identifying these tiny cracks. Tiny cracks may only appear as abnormalities of a few points in the point cloud map, which are difficult to distinguish from the surrounding noise or normal terrain undulations and are easily overlooked. By manually marking potential abnormal areas and combining them with lidar for coordinate determination, potential abnormalities and similar abnormalities can be further identified.

[0096] Example 3: Figure 2 As shown in the figure, an integrated slope monitoring system based on laser radar includes a data acquisition module, a parameter conversion and anomaly recognition module, and a potential anomaly determination module:

[0097] The data acquisition module includes a laser radar and a high-definition camera. The laser radar is used to perform a three-dimensional scan of the slope to obtain the point cloud data of the slope surface. The high-definition camera is used to collect the image data of the abnormal position of the slope. At the same time, based on the soil characteristics of the current area, Establish a slope monitoring database to group and divide the slopes under its jurisdiction, and record the collected slope data;

[0098] The parameter conversion and anomaly identification module determines the slope anomaly location based on the density and elevation of the abnormal point cloud in the slope point cloud data. The coordinates of the anomaly location are obtained through position coordinate conversion. High-definition cameras are used to capture the main and side view images of the coordinate location. Lines are extracted from the main and side views of the anomaly location. Parameter analysis is performed on the curvature and distance of the lines in the main and side views to determine the type of slope anomaly location, including depressions, protrusions, and cracks. The module then combines other identical anomaly parameters within the same group with the same soil characteristics to determine the slope anomaly.

[0099] The potential anomaly determination module manually marks the potential anomaly locations through slope images captured by high-definition cameras, extracts the potential anomaly location data and reconciles it with the lidar point cloud data. Based on the data upload results of the potential anomaly location, the module monitors and identifies potential anomalies and similar anomalies on the slope.

[0100] In summary, the present invention uses laser radar to collect slope point cloud data to determine the abnormal location, further obtains an image of the abnormal location, and extracts lines from the image to highlight the structural characteristics of the abnormality, thereby reducing the computational complexity of abnormality identification during the monitoring process. At the same time, based on the same abnormal data under the same geological characteristics, the present invention determines the serious abnormalities among the slope abnormalities during the slope monitoring process, making it easier for management personnel to maintain the slope in a timely manner.

[0101] By first using lidar to collect point cloud data to determine the abnormal location, and then obtaining images of the abnormal location in a targeted manner and performing line extraction, it is possible to focus on key areas and features. Compared with long-term comprehensive monitoring and analysis of the entire slope image, this method greatly reduces the amount of data that needs to be processed, thereby significantly shortening the calculation time and improving operating efficiency, so as to obtain monitoring results more quickly and enhance practicality. At the same time, line extraction of the abnormal location image can highlight the abnormal structural features, such as cracks, depressions, and protrusions. These key abnormal features are clearer after line extraction, reducing the probability of misjudgment and missed judgment during the monitoring process.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An integrated slope monitoring method based on laser radar, characterized in that: The method comprises the following steps: S1. Install laser radar and high-definition cameras on the slopes within the current area. Use the laser radar to perform three-dimensional scanning of the slopes to obtain slope surface point cloud data. Based on the soil characteristics of the current area, the slopes under the jurisdiction are grouped and divided, and the collected slope data is recorded. S2. Determine the abnormal location of the slope based on the density and elevation of the abnormal point cloud in the point cloud data of the slope, obtain the coordinates of the abnormal location through position coordinate conversion, and capture the main and side view images of the coordinate location using a high-definition camera; S3. Extract lines from the main and side views of the abnormal location, perform parameter analysis on the curvature and distance of the lines in the main and side views, determine the type of slope abnormal point, including depression, protrusion, and crack, and combine other identical abnormal parameters under the same soil characteristics within the same group to determine the slope abnormality; S4. Capture images of the slope using a high-definition camera, manually mark potential abnormal locations, extract data on potential abnormal locations and reconcile them with the lidar point cloud data, and monitor and identify potential abnormalities on the slope based on the data upload results of potential abnormal locations.

2. The integrated slope monitoring method based on laser radar according to claim 1, characterized in that: The S1 comprises the following sub-steps: S11. Based on the area of ​​the subordinate slope and the parameters of the laser radar, a laser radar is set on the slope, and the slope is scanned by the laser radar to obtain surface point cloud data; S12. Collect geological survey reports and soil samples of different slopes in the current area, including soil type, density, water content, and particle size distribution. Determine the slopes with the same soil type and density, water content, and particle size distribution within a similar error range as similar slopes. A slope monitoring database is established, and slopes of the same type are divided into the same group. At the same time, according to the rock structure of the slope, the group is further subdivided into layered structure slopes, block structure slopes, and mesh structure slopes. The slope numbers and point cloud data are recorded at the same time.

3. The integrated slope monitoring method based on laser radar according to claim 2 is characterized in that: The S2 comprises the following steps: S21. Divide the subordinate slopes into different areas, and mark abnormal areas based on the point cloud density and elevation value in each area, combined with the current normal values ​​of the slope point cloud density and elevation value; S22. For each point cloud data obtained by scanning the slope, a three-dimensional spatial coordinate system is established and the three-dimensional center coordinates of each divided area are marked to obtain the characteristic coordinates of the marked abnormal area. Based on the characteristic coordinates of the abnormal area, the main view image and side view image of the abnormal site of the abnormal area under the corresponding characteristic coordinates are collected by a high-definition camera and uploaded to the slope monitoring database.

4. The integrated slope monitoring method based on laser radar according to claim 3 is characterized in that: The S21 includes the following steps: S211, for the point cloud data obtained on the slope, the point cloud data on the slope is divided into grids according to a fixed spacing to obtain The number of point clouds in each area is counted as the point cloud density feature of the current area. The area without abnormal deformation or damage signs on the current slope is selected as the normal sample area to calculate the mean and standard deviation of the point cloud density feature. The range from mean -2 standard deviations to mean +2 standard deviations is taken as the normal interval. The area outside the normal interval is determined as the abnormal point cloud density area. S212, at the same time Point cloud data points for each area in the , based on the radius Determine the neighborhood of the current point cloud data, and calculate the average elevation value of all points in the neighborhood of the point. ,in represents the points in the neighborhood, Representing the field The elevation value of the point, calculate the current point Elevation value Average elevation of the neighborhood The difference ,when When , it means that there is an abnormal elevation value in the current area, and the current area is judged as an abnormal elevation value area. Represents the elevation value threshold.

5. The integrated slope monitoring method based on laser radar according to claim 2, characterized in that: The S3 includes the following steps: S31, performing two-dimensional conversion and line extraction on the images based on the obtained front view image and side view image of the abnormal area, and performing parameter analysis on the curvature and spacing of the lines in the front view image and the side view image to determine the slope abnormality type of the current abnormal area; S32. By grouping the slopes under the jurisdiction of the slope monitoring database, statistics are collected on the slope anomalies under the sub-items in the same group by type, and the serious anomalies of the slopes are analyzed and determined.

6. The integrated slope monitoring method based on laser radar according to claim 5, characterized in that: The S31 includes the following steps: S311, for the main view image and side view image of the abnormal area obtained, the formula Perform grayscale processing on the image, where R, G, and B represent the pixel values ​​of the red, green, and blue channels respectively. At the same time, perform histogram equalization on the image to enhance the contrast of the image; S312, using an edge detection algorithm to extract abnormal edge information from the abnormal area image, using a Gaussian filter to smooth the image to reduce the influence of noise, calculating the gradient of the image in the horizontal and vertical directions to obtain the gradient amplitude and gradient direction, performing non-maximum suppression in the gradient direction to retain the point with the maximum local gradient amplitude to refine the edge, and marking the edge points through dual threshold detection, the steps are as follows: Setting the threshold 、 ,in < , the gradient amplitude is greater than The points with gradient amplitude less than The points with a gradient between 、 The points between are marked as pending points. When the pending points are connected to strong edge points, they are determined to be strong edge points. When the pending points are connected to non-edge points, they are determined to be non-edge points. S313, perform line fitting on the obtained strong edge points, use the polynomial fitting method to determine the line parameters by minimizing the sum of squared errors, calculate the curvature of the line to obtain the curvature of the line, discretize the line to calculate the discrete curvature, select three points in the curve and calculate the discrete curvature by the inverse of the radius of the circumscribed circle of the triangle , and choose to calculate the vertical distance between the corresponding points of two adjacent lines at multiple points at the same time , take the average value as the current line spacing distance ; S314, through the obtained discrete curvature and line spacing of the lines in different abnormal areas, through the interval distance threshold and curvature threshold , determine the exception type: When the lines obtained in the abnormal area and When , it means that the lines in the current area tend to sink toward the inside of the slope, which is judged as a concave anomaly; When the lines obtained in the abnormal area only meet When , it means that there is abnormal crack in the current area; When the lines obtained in the abnormal area and When , it means that when the curvature of the line shows a tendency to bulge outwards towards the slope, and the interval between the lines in the bulge area does not change significantly, it is judged as a bulge anomaly; When the above three conditions are not met, the current area is marked as normal.

7. The integrated slope monitoring method based on laser radar according to claim 6, characterized in that: The S32 includes the following steps: S321. Based on the slope numbers of the subdivided items in the same group in the slope monitoring database, extract the abnormal data of depressions, protrusions, and cracks, including curvature and interval distance, and determine the severe outliers of the curvature and interval distance in the subdivided items by using the interquartile range method. The specific steps are as follows: For the abnormal data of depression, bulge and crack, obtain the curvature and interval distance values ​​of the slope in the same subdivision project under the corresponding abnormality, sort the data from small to large, and calculate the first quartile and the third quartile , calculate the interquartile range ,in represents the interquartile range; Get the lower limit and upper limit , judge the curvature and interval distance values ​​of the slope in the same subdivision project under the same anomaly, and and greater than The exception is marked as a serious exception.

8. The integrated slope monitoring method based on laser radar according to claim 2, characterized in that: The S4 comprises the following steps: S41. Capturing images of the slope at fixed intervals using a high-definition camera, manually identifying and marking potential abnormal locations, and determining the position coordinates of the manually marked potential abnormal locations using the point cloud data of the laser radar; S42, comparing the potential abnormal position coordinates with the characteristic coordinates of the marked abnormal area uploaded in the slope monitoring database, and ignoring the current potential abnormal position when the potential abnormal position coordinates match the existing characteristic coordinates of the marked abnormal area; S43. When the coordinates of the potential abnormality position do not match the characteristic coordinates of the existing marked abnormal area, repeat S3 to analyze and determine the potential abnormality.

9. The integrated slope monitoring method based on laser radar according to claim 8, characterized in that: The S43 further includes the following steps: S431. When the coordinates of the potential abnormal position do not match the characteristic coordinates of the existing marked abnormal area, the point cloud data within the current potential abnormal position coordinate area is extracted at the same time, and the similarity between the point cloud data of other areas and the current abnormal position coordinate area is calculated by Euclidean distance. For areas with similarity less than 0.3, similar abnormality marking is performed, and S3 is repeated to perform abnormality analysis and judgment on similar abnormal areas.

10. An integrated slope monitoring system based on laser radar, characterized in that: The system adopts the integrated slope monitoring method based on laser radar according to any one of claims 1 to 9, including a data acquisition module, a parameter conversion and anomaly recognition module, and a potential anomaly determination module: The data acquisition module includes a laser radar and a high-definition camera. The laser radar performs a three-dimensional scan of the slope to obtain the slope surface point cloud data, and the high-definition camera collects the image data of the slope abnormal position. At the same time, based on the soil characteristics of the current area, Establish a slope monitoring database to group and divide the slopes under its jurisdiction, and record the collected slope data; The parameter conversion and anomaly identification module determines the slope anomaly location through the density and elevation of the abnormal point cloud in the point cloud data of the slope, obtains the coordinates of the anomaly location through position coordinate conversion, collects the main and side view images of the coordinate location using a high-definition camera, extracts lines from the main and side views of the anomaly location, performs parameter analysis on the curvature and distance of the lines in the main and side views, determines the type of the slope anomaly location, including depression, protrusion, and crack, and combines other identical anomaly parameters under the same soil characteristics within the same group to determine the slope anomaly. The potential anomaly determination module manually marks the potential anomaly locations through the slope images captured by the high-definition camera, extracts the potential anomaly location data and reconciles it with the lidar point cloud data, and monitors and identifies potential anomalies and similar anomalies on the slope based on the data uploaded results of the potential anomaly locations.

Images