Slope deformation monitoring and identification method based on 4D imaging millimeter wave radar

Abstract

The application relates to the technical field of intelligent traffic and road safety monitoring, and discloses a slope deformation monitoring and identification method based on 4D imaging millimeter wave radar, which comprises the following steps: acquiring continuous point clouds; modeling voxels of the point clouds in a three-dimensional space; selecting three continuous frames of point clouds, identifying mutant voxels by calculating the point number change of each voxel in adjacent frames; performing spatial clustering on the mutant voxels to obtain an obstacle region; extracting features of the obstacle region, wherein the extracted features include a height difference, an average reflection intensity and a centroid drift of the obstacle region; performing linear weighted fusion on the extracted features to construct a landslide mutation index; determining whether the obstacle region contains an obstacle target according to a preset condition, and performing risk classification identification according to the landslide mutation index. The application realizes all-weather, structured and high-reliability perception of landslide / rockfall traffic major safety hazards, and provides a new basic capability for a traffic safety system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation and road safety monitoring, and particularly relates to a slope deformation monitoring and identification method based on 4D imaging millimeter wave radar. BACKGROUND

[0002] The existing road disaster monitoring methods mainly include manual inspection, video monitoring, laser radar detection, etc. However, these methods have certain limitations: manual inspection has poor real-time performance and is obviously affected by environmental conditions; video monitoring depends on light and sight distance, and its detection capability significantly decreases at night or in bad weather conditions; although laser radar and remote sensing technology have high accuracy, they have high equipment cost and complex deployment, and it is difficult to realize continuous monitoring in a dynamic environment. In recent years, 4D imaging millimeter wave radar has gradually been applied to traffic target detection due to its advantages of all-weather, anti-interference and high frequency output. However, the existing systems mainly focus on vehicle identification, and the three-dimensional contour modeling and risk assessment capability for natural obstacles still have deficiencies, mainly in the following aspects.

[0003] 1. Insufficient obstacle area identification capability: the existing radar processing methods mainly focus on single-point target tracking, lack spatial continuity analysis of regional obstacles, and it is difficult to timely find newly added rockfalls or slowly deformed landslide areas.

[0004] 2. Lack of perfect risk judgment mechanism: the existing methods mainly rely on a single index for judgment, and do not comprehensively consider time and physical characteristics such as obstacle appearance speed, range expansion trend, reflection intensity and stability, so it is difficult to quantify the risk level.

[0005] In summary, the main bottlenecks in risk identification and assessment of landslide / rockfall disasters are: insufficient obstacle area identification capability; lack of perfect risk judgment mechanism; these deficiencies result in that the monitoring system cannot stably operate in all-weather and complex environments, and affect the accuracy and reliability of risk identification and assessment of landslide / rockfall disasters. SUMMARY

[0006] In order to solve the above technical problems, the present application provides a slope deformation monitoring and identification method based on 4D imaging millimeter wave radar, which solves the problem that the existing traffic monitoring system cannot accurately identify sudden natural obstacles on the road slope in bad weather, at night or in low visibility scenes. The present application can realize real-time identification of structural static natural obstacles appearing in the road slope area under different meteorological conditions, and the specific steps include:

[0007] S1. acquiring continuous point clouds;

[0008] S2. modeling voxels in the point clouds in a three-dimensional space;

[0009] S3. Selecting three continuous frames of point clouds, and identifying mutant voxels by calculating the point number change of each voxel in adjacent frames;

[0010] S4. Spatially clustering the mutant voxels to obtain an obstacle region;

[0011] S5. Extracting features of the obstacle region, including height difference, average reflection intensity and centroid drift of the obstacle region;

[0012] S6. Linearly weighting and fusing the extracted features to construct a landslide mutation index;

[0013] S7. Determining whether the obstacle region contains an obstacle target according to a preset condition, and identifying the risk classification according to the landslide mutation index.

[0014] Preferably, the modeling step of the voxel includes: dividing the three-dimensional space where the point cloud is located into a plurality of equal-sized voxels; determining the voxel index based on the spatial position of different discrete points in the point cloud, and assigning the discrete points to the voxel identified by the voxel index.

[0015] Preferably, the step of identifying mutant voxels by calculating the point number change of each voxel in adjacent frames includes: if the maximum value of the point number change of the three continuous frames of point clouds is greater than a preset point number change, the corresponding voxel is a mutant voxel.

[0016] Preferably, the spatial clustering method includes: clustering the mutant voxels in six directions of up and down, front and back, and left and right to obtain at least one obstacle region.

[0017] Preferably, the method of constructing the landslide mutation index includes:

[0018] ;

[0019] wherein, is the maximum value of the point number change of the mutant voxels in the obstacle region, is the maximum value of the height difference change in the obstacle region, is the maximum value of the centroid drift change in the obstacle region, are preset feature weights, respectively.

[0020] Preferably, the preset condition includes simultaneously satisfying the following conditions:

[0021] The landslide mutation index is greater than or equal to a preset landslide mutation index threshold;

[0022] The average reflection intensity is within a preset average reflection intensity range; ​​

[0023] The maximum value of the change amount of the center of mass drift is less than or equal to a preset center of mass drift threshold.

[0024] Compared with the prior art, the present application has the following beneficial effects:

[0025] The present application realizes high-precision positioning of sudden static natural obstacles such as landslides and falling rocks by continuously analyzing and identifying new mutant voxels through multiple frames of point clouds and forming a complete obstacle region by combining spatial clustering; further, multi-dimensional features such as height difference, average reflectivity and center of mass drift are extracted, a landslide mutation index is constructed, the obstacle region is quantitatively classified, automatic early warning and linkage response are supported; the method overcomes the problems of false positives and difficulty in quantification of existing traffic monitoring systems in bad weather, night or low visibility scenes, and improves the accuracy, real-time performance and environmental adaptability of road slope disaster identification. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, a brief introduction will be given below to the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0027] Figure 1 A flowchart of a slope deformation monitoring and identification method based on 4D imaging millimeter wave radar is provided in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0029] Embodiment one

[0030] At present, the road monitoring method based on 4D imaging millimeter wave radar mainly focuses on vehicle detection and moving target tracking. For sudden landslides, falling rocks and other natural obstacles on road slopes, traditional methods mostly rely on cameras or laser radars for identification, but such methods are limited by light, weather conditions and are difficult to maintain stable identification effect in night, rain, fog and other harsh environments. In addition, the risk determination of the existing method for the obstacle region mostly relies on a single feature such as height or reflectivity, which is difficult to effectively distinguish between new obstacles and point cloud changes, resulting in false positives and false negatives.

[0031] As Figure 1 shown, the embodiment provides a slope deformation monitoring and identification method based on 4D imaging millimeter wave radar, comprising the steps of:

[0032] S1. Obtain continuous point clouds.

[0033] In some preferred embodiments, the point cloud refers to a large number of discrete three-dimensional space points generated after scanning the target area by devices such as 4D imaging millimeter wave radar.

[0034] In some preferred embodiments, a certain highway slope is selected, and the rock-soil mass is mainly argillaceous sandstone, which is prone to shallow slip in the rainy season. A 4D imaging millimeter wave radar is used to monitor the target slope area, and point cloud data is collected at a sampling frequency of 10s / frame. Each frame of point cloud contains the three-dimensional coordinates (x, y, z) of each discrete point in the slope area, x is along the direction of the highway, y is perpendicular to the direction of the highway, and z is the vertical protrusion degree of the obstacle. The collection of all discrete points is the point cloud.

[0035] S2. Model the point cloud in three-dimensional space with voxels.

[0036] In some preferred embodiments, a voxel is a basic discrete unit in three-dimensional space, which can be compared to the extension of a pixel in a two-dimensional plane in three dimensions. Its essence is a regular small cube with a fixed size in three-dimensional space. Each frame of point cloud is divided into a regular three-dimensional voxel grid, and the number of points in each voxel is counted.

[0037] S3. Select three consecutive frames of point cloud, and identify the mutant voxel by calculating the point number change of each voxel in adjacent frames.

[0038] In some preferred embodiments, a mutant voxel refers to a voxel in which the number of point clouds or the point number changes significantly and abnormally between consecutive frames of point clouds (adjacent two frames). Three consecutive frames of point cloud are selected, and the point number change in the three frames is compared. If the maximum point number change is greater than the preset point number change, the corresponding voxel is a mutant voxel.

[0039] S4. Spatially cluster the mutant voxel to obtain an obstacle region.

[0040] In some preferred embodiments, the method of spatially clustering the mutant voxel includes: judging the voxel connectivity based on the six-neighborhood, or reasonably designing according to the actual situation or the needs of the site, clustering the mutant voxel in the six directions of up, down, front, back, left and right, and obtaining at least one obstacle region.

[0041] S5. Feature extraction is performed on the obstacle region, and the extracted features include height difference, average reflection intensity, and centroid drift of the obstacle region.

[0042] In some preferred embodiments, the height difference refers to the height difference between the highest point and the lowest point in the z-axis direction of the obstacle region, reflecting the vertical protrusion degree of the obstacle; the average reflection intensity refers to the average radar reflection intensity value of all point clouds in the obstacle region, used to distinguish metal targets from natural objects such as rocks and mudslides; and the centroid drift represents the change in the centroid position of the target in two consecutive frames, reflecting whether it is a stationary body.

[0043] In some preferred embodiments, the volume cluster is extracted, and the volume cluster represents a set of spatially connected mutant voxels. Each volume cluster corresponds to an obstacle region. The calculation formulas of the features are as follows:

[0044] Height difference : Let p be a point in the volume cluster , denote the height of point p in the z-axis direction, then

[0045] ;

[0046] Average reflection intensity R m : Let reflect(p) denote the reflection intensity of point p, and denote the number of mutant voxels, then

[0047] ;

[0048] Centroid drift : Let and be the centroid positions of the obstacle region in the t-th frame and the t-1-th frame, respectively, then

[0049] ;

[0050] Through the above feature extraction, the system converts the obstacle region with mutant voxels into a candidate target with structural description, providing basic data support for the next landslide index calculation and risk assessment.

[0051] S6. Linearly weighted fusion is performed on the extracted features to construct a landslide mutation index.

[0052] In some preferred embodiments, the landslide mutation index is a comprehensive index obtained by linearly weighted fusion of the features such as height difference, average reflection intensity, and centroid drift of the obstacle region, used to represent the risk level of landslides or rockfalls.

[0053] S7. Determine whether the obstacle region contains an obstacle target according to a preset condition, and identify the risk level according to the landslide mutation index.

[0054] When the obstacle region meets the preset determination condition, such as the voxel quantity threshold, the reflection intensity threshold, and the centroid drift threshold, it is determined that the region contains an obstacle target. Meanwhile, according to the size of the landslide mutation index, the risk level is divided into three levels: low, medium, and high.

[0055] The embodiment can detect and identify newly added natural obstacles such as slope landslides and rockfalls in the absence of light and in rainy and foggy weather. The use of mutation voxels combined with feature fusion to construct the landslide mutation index reduces the misjudgment caused by a single feature and improves the accuracy and stability of detection. Experimental results show that the method can maintain a high recognition rate in different environments and effectively classify the risk of obstacles, facilitating timely measures by road safety management departments.

[0056] Embodiment Two

[0057] On the basis of Embodiment One, the embodiment is used for modeling voxels.

[0058] Voxel modeling is a key step in connecting raw point cloud data and deformation analysis. Common voxel modeling methods include regular voxel grid modeling, adaptive voxel modeling, and octree voxel modeling. These methods have high computational cost, complex processes, or over-segmentation or under-segmentation problems in areas with large differences in point cloud density due to improper parameter settings. To solve the above problems, in some preferred embodiments, the three-dimensional space where the point cloud is located is divided into voxels of equal size; the voxel index of each discrete point in the point cloud is determined based on its spatial position, and the discrete point is assigned to the voxel identified by the voxel index. The voxel index (i, j, k) is calculated as follows:

[0059] ;

[0060] where x, y, and z are the spatial coordinates of the discrete point, and Vx, Vy, and Vz represent the size of the voxel in the x, y, and z directions, respectively.

[0061] For example, in some preferred embodiments, the highway slope region is divided into voxels with a size of Vx x Vy x Vz, the number of point clouds in each voxel is counted, and the voxel is modeled. For example, if the voxel size is 0.5m x 0.5m x 0.5m, voxel V(10, 5, 3) contains 8 point clouds, and voxel V(10, 6, 3) contains 0 point clouds.

[0062] In this embodiment, the original point cloud is converted into a voxelized structure, and the number of points corresponding to each voxel is obtained. Compared with conventional technologies, the method in this embodiment is more accurate and reliable in comparison of multiple frames of point cloud data.

[0063] Embodiment three

[0064] On the basis of embodiment one, this embodiment is used to identify mutant voxels.

[0065] Currently, point cloud mutation detection methods often compare the point number difference frame by frame to determine the obstacle region. However, simple two-frame comparison is easily disturbed by instantaneous noise, which may lead to random noise points being identified as mutant targets, thereby reducing the identification accuracy. In order to solve the above problems, in some preferred embodiments, the present application identifies mutant voxels by comparing the point number change in three frames. If the maximum point number change is greater than the preset point number change, the corresponding voxel is a mutant voxel.

[0066] In some preferred embodiments, the specific steps of the mutant voxel identification method of the present application include: using three consecutive frames of point cloud t-2, t-1 and t of the sliding window, counting the number of points in each voxel of the point cloud, and identifying the mutant voxels of shallow slip by calculating the point number change of each voxel in adjacent frames.

[0067] First, the point number change ΔN1 of the same voxel in t-1 and t-2 frames is calculated. Then, the point number change ΔN2 of the same voxel in t and t-1 frames is calculated.

[0068] For example, the voxel V(10, 5, 3) contains 8 points in the t-2 frame and 2 points in the t-1 frame, so ΔN1 = 8-2 = 6.

[0069] The same voxel V(10, 5, 3) contains 2 points in the t-1 frame and 1 point in the t frame, so ΔN2 = 2-1 = 1.

[0070] The larger value is taken as the point number change max(ΔN1, ΔN2) of the voxel. In this case, the point number change of the voxel is 6.

[0071] The threshold is set to 2: the point number change of the voxel is 6, which is greater than the set threshold 2, so the voxel V(10, 5, 3) is determined to be a mutant voxel.

[0072] Embodiment four

[0073] On the basis of embodiment one, this embodiment is used to perform spatial clustering on the mutant voxels.

[0074] Common clustering methods include application space clustering based on Euclidean distance or three-dimensional clustering based on connectivity. However, these methods are computationally intensive, parameter sensitive, and prone to low efficiency in real-time monitoring of large-scale point clouds. In some preferred embodiments, the mutant voxels are clustered in six directions: up, down, front, back, left, and right. The spatial clustering process includes: obtaining a series of mutant voxel sets by the method of Example Three; for each mutant voxel, checking whether there are other mutant voxels in the six directions (up, down, front, back, left, and right). If so, they are considered to belong to the same connected region; recursively traverse all adjacent mutant voxels and aggregate them into an obstacle region; if there is no direct adjacency relationship between the mutant voxels, multiple independent obstacle regions are formed, each region corresponding to a potential landslide or rockfall target.

[0075] This embodiment can accurately identify different obstacle regions while ensuring computational efficiency.

[0076] Example Five

[0077] On the basis of Example One, this embodiment constructs a landslide mutation index.

[0078] Existing road slope monitoring relies on a single feature for judgment, which is prone to missed detection or misjudgment due to environmental interference, making it difficult to accurately assess landslide or rockfall risk. For example, a large height difference but actually a vehicle parking spot, or a high reflectivity but only a metal object, not a real landslide risk point. To solve this problem, in some preferred embodiments, the method for constructing the landslide mutation index includes:

[0079] ;

[0080] wherein, is the maximum value of the point number change amount of the mutant voxels in the obstacle region, is the maximum value of the height difference change amount in the obstacle region, is the maximum value of the centroid drift change amount in the obstacle region, , are the preset feature weights, respectively.

[0081] In some preferred embodiments, The preset feature weights can be 1.0, 1.5, and 2.0, respectively, or can be reasonably designed by those skilled in the art according to actual conditions or field needs. For example, when = 11, = 1.1 m, = 0.015 m, the landslide mutation index is: ​​​

[0082] =1.0x11+1.5x1.1-2.0x0.015=12.62;

[0083] By linearly weighting and fusing the multi-dimensional features, the landslide mutation index proposed in this embodiment can comprehensively reflect the characteristics of the obstacle region and effectively distinguish real landslides / rockfalls from ordinary environmental changes.

[0084] Embodiment six

[0085] On the basis of the first embodiment, the present embodiment provides a method for obstacle target determination and risk grading.

[0086] Traditional slope monitoring methods often rely on a single indicator to determine the presence of obstacles, which is easily affected by environmental interference or abnormal points, leading to false positives or false negatives. At the same time, there is a lack of comprehensive judgment basis, and the risk of obstacles cannot be effectively graded. To solve the above problems, in some preferred embodiments, the present application provides a grading strategy, including the following steps:

[0087] First, for each obstacle region, determine whether the following conditions are met simultaneously:

[0088] The landslide mutation index is greater than or equal to the preset landslide mutation index threshold ;

[0089] The average reflection intensity is within the preset average reflection intensity range;

[0090] The maximum value of the change amount of the centroid drift is less than or equal to the preset centroid drift threshold ;

[0091] In some preferred embodiments, the preset landslide mutation index threshold can be set to =10; the preset average reflection intensity range can be set to ∈(-15,-8)dB, which can effectively exclude non-natural objects such as metal vehicles; the preset centroid drift threshold can be set to =0.1, which is used to distinguish dynamic traffic flow from static obstacles. It can also be a reasonable design according to the field situation or actual needs of those skilled in the art.

[0092] When the above three conditions are met simultaneously, it is determined that the obstacle region contains an obstacle (landslide or rockfall, etc.) target.

[0093] Then, according to the size of the landslide mutation index , the risk level of the determined obstacle region is divided, for example:

[0094] 5≤ <10, low risk;

[0095] 10≤ <20, medium risk;

[0096] 20≤ , high risk;

[0097] In this embodiment, The higher the value, the closer the target is to a sudden large amount of stationary natural obstacles. The point cloud mutation variable, height difference, and centroid drift in the index are respectively derived from the voxel level, cluster body level, and time sequence level data processing modules, which The index is used as a fusion scoring function for landslide events, which can allow the system to comprehensively consider from multiple dimensions and improve the overall judgment accuracy of the target.

[0098] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring and identifying slope deformation based on 4D imaging millimeter-wave radar, characterized in that, include: S1. Obtain continuous point cloud; S2. Perform voxel modeling on the point cloud in three-dimensional space; S3. Select three consecutive frames of point cloud and identify mutant voxels by calculating the change in the number of points of each voxel in adjacent frames; S4. Perform spatial clustering on the mutant voxels to obtain obstacle regions; S5. Extract features from the obstacle region, including the height difference, average reflection intensity, and centroid drift of the obstacle region; S6. Perform linear weighted fusion on the extracted features to construct a landslide mutation index; S7. Determine whether there are obstacle targets in the obstacle area according to preset conditions, and identify risk classification based on the landslide mutation index.

2. The slope deformation monitoring and identification method based on 4D imaging millimeter-wave radar according to claim 1, characterized in that, The modeling steps for the voxels include: dividing the three-dimensional space of the point cloud into several voxels of equal size; determining the voxel index based on the spatial position of different discrete points in the point cloud, and assigning the discrete points to the voxels identified by the voxel indexes.

3. The slope deformation monitoring and identification method based on 4D imaging millimeter-wave radar according to claim 1, characterized in that, The step of identifying mutant voxels by calculating the change in the number of voxels in adjacent frames includes: if the maximum value of the change in the number of voxels in three consecutive frames is greater than a preset change in the number of voxels, then the corresponding voxel is a mutant voxel.

4. The slope deformation monitoring and identification method based on 4D imaging millimeter-wave radar according to claim 1, characterized in that, The spatial clustering method includes: clustering mutant voxels according to six directions: up and down, front and back, left and right, to obtain at least one obstacle region.

5. The slope deformation monitoring and identification method based on 4D imaging millimeter-wave radar according to claim 1, characterized in that, The method for constructing the landslide abrupt change index includes: ； in, This represents the maximum change in the number of mutant points in the obstacle region. This represents the maximum value of the change in height difference within the obstacle region. This represents the maximum value of the change in centroid drift within the obstacle region. , , These are the preset feature weights.

6. The slope deformation monitoring and identification method based on 4D imaging millimeter-wave radar according to claim 1, characterized in that, The preset conditions include the following conditions being met simultaneously: The landslide mutation index is greater than or equal to a preset landslide mutation index threshold. The average reflection intensity is within a preset average reflection intensity range; The maximum value of the change in centroid drift is less than or equal to a preset centroid drift threshold.

Images