Collaborative information guidance-based unmanned aerial vehicle laser radar point cloud individual tree segmentation method

Abstract

The invention discloses an unmanned aerial vehicle laser radar point cloud individual tree segmentation method based on collaborative information guidance. The individual tree segmentation method comprises the steps of obtaining an initial crown class; based on the uniqueness of point cloud distribution of the unmanned aerial vehicle laser radar in the forest region, geometric significance features are constructed, and accurate extraction of trunk candidate points and objectified detection of trunks are realized; dividing the initial crown class into under-segmentation, correct segmentation and over-segmentation; outputting the correctly segmented crown as a single tree segmentation result, and further refining the under-segmented class cluster; and optimizing the under-segmented crown by using the mutual reference information of the crown and the trunk. According to the method, the tree boundary refined segmentation capability is improved, and the extraction precision and reliability of the unmanned aerial vehicle laser radar point cloud single tree are effectively improved.

Description

Technical Field

[0001] The present invention relates to a method for segmenting a single tree in a UAV laser radar point cloud, specifically a method for extracting a single tree by comprehensively considering crown features, trunk features, and coordinated mutual reference features of crowns and trunks, and belongs to the technical field of laser radar point cloud data processing and forest resource survey. Background Art

[0002] Forests are the largest ecosystems on land and play an important role in maintaining the global ecological balance. Efficient and accurate acquisition of forest resource information is the premise and basis for forest resource protection and management. UAV LiDAR technology can quickly obtain three-dimensional spatial information of forest structure. It has the advantages of high efficiency, flexibility, high spatiotemporal resolution, no cloud cover, and low cost. It is an important means of forest resource survey. The extraction of single trees from UAV LiDAR point cloud is the basic step to obtain single tree structural parameters. Accurate single tree structural parameters can provide basic data for forest resource survey and forest management decision-making, and also provide support for forestry applications such as forest growth simulation, forest carbon storage assessment, and forest ecosystem function assessment. However, the large amount of UAV LiDAR data, the diverse changes in forest site conditions, the diverse tree structure and morphology, and mutual occlusion have affected the accuracy of UAV LiDAR point cloud single tree extraction, which seriously restricts the application and promotion of UAV LiDAR technology in forest resource survey and forest protection and management.

[0003] At present, the existing single wood splitting methods in the prior art may have the following problems:

[0004] 1) Top-down single tree segmentation method. Due to the bird's-eye view of observation by satellite / aviation manned airborne platforms, the obtained forest area lidar point cloud or image data can better characterize and cover the forest canopy structure. The single tree extraction method based on satellite and manned airborne point cloud or image starts from the crown characteristics and follows the top-down single tree extraction mode. This type of method first identifies and locates the crown vertices, and then uses a series of different segmentation methods to gradually distribute the crown to each tree top. Common segmentation methods include watershed segmentation, regional growth, mean shift, morphological reconstruction, etc. However, the performance of this type of method is completely dependent on the characterization and description capabilities of the crown characteristics, and is easily affected by the heterogeneous canopy structure.

[0005] 2) Bottom-up single tree segmentation method. Terrestrial Laser Scanning (TLS) can obtain detailed understory vegetation information. The single tree extraction method based on TLS makes full use of the trunk features and follows a bottom-up approach. This type of method first locates the base or trunk of the tree, and then uses segmentation methods such as the k-nearest neighbor algorithm, morphological methods, and graph theory to gradually assign crown points to their respective trunks. However, this type of method relies on the effect of trunk detection. When trunk recognition fails, these methods will be hindered or even terminated prematurely.

[0006] 3) Existing single tree extraction methods based on UAV point clouds usually treat UAV point clouds as data similar to manned point clouds, and adopt the same top-down single tree segmentation strategy as manned point clouds; however, UAV point clouds can provide more comprehensive and higher-density tree trunk structure information than manned point clouds. In addition, compared with manned point clouds and ground-based point clouds, UAV point clouds can simultaneously obtain more complete and detailed crown and trunk structure information. The uniqueness and advantages of these UAV laser point cloud data have not been fully explored and applied;

[0007] 4) Although the single tree extraction method based on deep learning can obtain better single tree extraction results for the data of a given scene, it requires the collection and labeling of a large amount of sample data for the training of the deep learning model, which has a high implementation cost and poor transplantability and robustness to different types of forest structures under different site conditions. Summary of the invention

[0008] In response to the problems raised in the above background technology, the purpose of the present invention is to make full use of and explore the characteristics of UAV lidar point cloud, and propose a UAV lidar point cloud single tree segmentation method based on collaborative information guidance. The single tree segmentation method is based on the collaborative information guidance of the trunk and the crown to improve the accuracy and robustness of the single tree segmentation, thereby solving the problems existing in the prior art.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: a method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance, the method comprising the following steps:

[0010] S1: The UAV laser radar scans the forest area to obtain the crown point cloud. The mean shift algorithm with 3D asymmetric kernel is used to preliminarily divide the crown point cloud to obtain a rough crown segmentation result, i.e., the initial crown cluster.

[0011] S2: Based on the point density distribution characteristics of tree crowns and trunks in the UAV LiDAR point cloud in the forest area, the height histogram is used to preliminarily separate the trunk points and the crown points to obtain the trunk candidate points. Based on the uniqueness of the UAV LiDAR point cloud distribution in the forest area, geometric saliency features are constructed, and the trunk candidate points are further subdivided to achieve accurate extraction of trunk candidate points and object detection of trunks;

[0012] S3: Construct crown and trunk collaborative features and mean shift modulus variance features, use random forest to divide the initial crown class into under-segmentation, correct segmentation and over-segmentation, and retain the correct segmentation as the single tree segmentation result;

[0013] S4: Refine the over-segmented crown by using the mutual coordination and reference information of the crown and trunk; perform vertical region growth on the trunk, sort all crown clusters from high to low, match them with the trunk respectively, output the correctly segmented crown as the single tree segmentation result, and further refine the under-segmented clusters;

[0014] S5: For the under-segmented crown clusters after matching, a graph cut segmentation method based on the optimization of the tree center vector deviation angle is constructed, and the under-segmented crown is optimized by using the mutual reference information between the crown and the trunk.

[0015] As a further technical solution of the present invention, S1 specifically includes:

[0016] S11: Normalize the tree crown point cloud obtained by scanning the forest area with UAV lidar, and eliminate the low-lying vegetation points in the forest area according to the height threshold;

[0017] S12: The tree crown point cloud is preliminarily segmented using the mean shift algorithm of the 3D asymmetric kernel. The three-dimensional space of the drone lidar point cloud is divided into two parts: the horizontal domain and the vertical domain. The horizontal domain uses a symmetric Gaussian kernel function to find the local maximum of density, and the vertical domain uses an asymmetric kernel function to find the local maximum of height. For any point X in the drone lidar point cloud, A , and its mean shift vector is expressed as:

[0018]

[0019] Among them, the vertical kernel function g r It is an asymmetric function. The specific expression is as follows:

[0020]

[0021]

[0022] Where: superscript s and r represent horizontal domain and vertical domain respectively; gs and g r Represent the horizontal kernel function and the vertical kernel function respectively; h s and h r Represent the horizontal core bandwidth and vertical core bandwidth respectively; and Respectively represent X A and X i The horizontal component of the coordinate; and Respectively represent X A and X i The vertical component of the coordinates; each point X i X A The weight of the mean shift vector is related to the point and X A The distance is related to the kernel function; Used to filter X within a fixed bandwidth i ; Calculate X A and X i The horizontal coordinate distance.

[0023] As a further technical solution of the present invention, S2 specifically includes:

[0024] S21: Divide the clusters obtained by mean shift clustering of each asymmetric kernel into twelve intervals according to the elevation, count the frequency of points appearing in each interval, analyze the continuous height intervals with lower frequency in the height histogram, perform preliminary separation of crown points and trunk points, and obtain candidate trunk points;

[0025] S22: Calculate linear difference significance features, plane difference significance features and scattered difference significance features for each of the trunk candidate points, and use random forest to further subdivide the trunk candidate points into trunk points and non-trunk points, wherein, in the calculation of the plane difference significance feature SoDP and the scattered difference significance feature SoDS, P, L, S are calculated based on the eigenvalues ​​of the covariance matrix of the point cloud segmentation part, representing the plane feature, linear feature and scattered point feature, respectively, and the formula is as follows:

[0026] SoDP = P + (1-P) × [P-max (L, S)]

[0027] SoDS=S+(1-S)×[S-max(L,P)]

[0028] S23: Clustering the identified tree trunk points using a 2D mean shift algorithm to obtain tree trunk clusters.

[0029] As a further technical solution of the present invention, S3 specifically includes:

[0030] S31: Based on the initial crown clusters obtained in S1, the crown and trunk collaborative features and the mean shift modulus point variance features are constructed, and the incorrect segmentation in the initial crown clusters is identified based on the crown and trunk collaborative features and the mean shift modulus point variance features;

[0031] The crown and trunk synergistic features include the number of trunks under the initial crown cluster, the crown width predicted by the allometric model according to the tree height, and the difference between the crown width predicted by the crown height and the actual crown width of the crown cluster.

[0032] S32: The crown and trunk collaborative features and mean shift modulus variance features are used in random forests to divide the initial crown clusters into under-segmentation, over-segmentation and correct segmentation.

[0033] As a further technical solution of the present invention, S4 specifically includes:

[0034] S41: using the mutual coordination and reference information between the crown and the trunk, i.e. the allometric relationship between the trunk and the crown, the crown cluster identified as over-segmented is merged with the nearest under-segmented cluster;

[0035] S42: performing vertical region growth on the tree trunk detected in S3 to obtain a complete tree trunk;

[0036] S43: Sort the under-segmented and correctly segmented crowns from high to low, and use the allometric growth relationship between the trunk and the crown to match them with the vertically grown trunks. The correctly segmented crowns are output as single tree segmentation results, while the under-segmented results need further refinement.

[0037] As a further technical solution of the present invention, S5 specifically includes:

[0038] S51: Using the mutual reference information between the crown and the trunk, i.e. the two-dimensional vector angle consistency between the mean shift modulus of the crown and the centroid of the trunk, as well as the allometric relationship between the size of the trunk and the crown, the graph cut optimization is performed on the under-segmented clusters after matching:

[0039] First, the crown width was estimated according to the crown height in each cluster through an allometric growth model.

[0040] Secondly, the trunk points to be segmented are used as the foreground seed points of the graph cut, the remaining trunks are used as the background seed points of the graph cut, and the crown width estimated according to the allometric growth model is used as the radius of the graph cut;

[0041] The radius calculation formula is as follows:

[0042] radius=0.446×H 0.854

[0043] Where: H is the normalized height of the tree trunk;

[0044] S52: Calculate the two-dimensional vector D from each point to the mode point through the mode point of the mean shift algorithm n , D n as the prediction vector for each point pointing to the center of the tree;

[0045] S53: Calculate the centroid of the foreground point, use the centroid as the tree center, and calculate the vector D of each point pointing to the tree center (n,K) , D (n,K) as the true vector for each point pointing to the center of the tree;

[0046] S54: Based on the prediction vector D n With the real vector D (n,K) , calculate the tree center vector angle weight w θ :

[0047]

[0048] S55: Deviate the tree center from the angle weight w θ and the original background penalty w in the graph cut back_penalty Add them together to get the mixed weight sink_weight as the new background penalty input into the graph cut algorithm. The new background penalty formula is as follows:

[0049]

[0050] sink_weight=0.5*w back_penalty +0.5*w θ

[0051] Where: dist 2d Indicates the two-dimensional plane distance from the foreground point to the input point cloud;

[0052] S56: Remove the segmented point cloud from the input point cloud, and repeat the above operation until all under-segmentation is segmented.

[0053] The beneficial effects of the present invention are:

[0054] 1) The present invention fully utilizes and mines the UAV laser radar point cloud to obtain the uniqueness of high-density crown and trunk point clouds, and ensures the high accuracy and robustness of single tree extraction through the clues and guidance of mutual reference between trunks and crowns. The present invention is also applicable to different forest conditions and forest types, including coniferous forests, broad-leaved forests, and mixed coniferous and broad-leaved forests;

[0055] 2) According to the spatial distribution characteristics of the UAV laser radar point cloud, the present invention designs a UAV laser radar point cloud tree trunk detection method based on the plane difference significance and scattering difference significance features, thereby improving the accuracy of tree trunk detection;

[0056] 3) The present invention utilizes the two-dimensional vector angle consistency between the mean drift modulus point of the crown and the trunk centroid, as well as the allometric growth relationship between the trunk and crown sizes, to enhance the fault tolerance and refinement processing capabilities for over-segmentation and under-segmentation of the crown, improves the accuracy and robustness of single tree extraction under different forest types, diverse tree structures and morphology, and mutual occlusion, improves the accuracy and reliability of UAV lidar technology in forest resource surveys, and promotes the popularization and application of UAV lidar technology in forestry surveys. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the overall technical process of the present invention;

[0058] Figure 2a is a schematic diagram of a tree crown before rough segmentation in an embodiment of the present invention;

[0059] Figure 2b is a schematic diagram of a roughly segmented tree crown in an embodiment of the present invention;

[0060] Figure 3 A tree crown cluster height histogram constructed in an embodiment of the present invention;

[0061] Figure 4a This is a schematic diagram of a tree trunk before extraction in an embodiment of the present invention;

[0062] Figure 4b This is a schematic diagram of a tree trunk after extraction in an embodiment of the present invention;

[0063] Figure 5 Schematic diagram of a segmentation method based on tree center vector deviation angle optimization in an embodiment of the present invention;

[0064] Figure 6a This is a schematic diagram of the segmentation result before the tree center vector deviation angle optimization is adopted in an embodiment of the present invention;

[0065] Figure 6b Schematic diagram of segmentation results after tree center vector deviation angle optimization in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Embodiment 1, as Figure 1As shown, this embodiment provides a method for segmenting a single tree in a UAV laser radar point cloud based on collaborative information guidance, and the method for segmenting a single tree includes the following steps:

[0068] S1: The crown point cloud (crown distribution characteristics) is obtained by scanning the forest area with UAV lidar. The crown point cloud is preliminarily divided using the mean shift algorithm with a 3D asymmetric kernel to obtain a rough crown segmentation result (initial crown cluster).

[0069] S1 specifically includes:

[0070] S11: Normalize the tree crown point cloud obtained by UAV lidar scanning, and eliminate the low-lying vegetation points in the forest area according to the height threshold;

[0071] S12: Use the mean shift algorithm with 3D asymmetric kernel to perform preliminary segmentation of the tree crown point cloud;

[0072] The three-dimensional space of the UAV lidar point cloud is divided into two parts: the horizontal domain and the vertical domain. The horizontal domain uses a symmetric Gaussian kernel function to find the local maximum of density; the vertical domain uses an asymmetric kernel function to find the local maximum of height.

[0073] For any point X in the UAV lidar point cloud A , its mean shift vector can be expressed as:

[0074]

[0075] Among them, the vertical kernel function g r It is a specially designed asymmetric function, the purpose of which is to give higher points greater weights. The specific expression is as follows:

[0076]

[0077] Where: superscript s and r represent horizontal domain and vertical domain respectively; g s and g r Represent the horizontal kernel function and the vertical kernel function respectively; h s and h r Represent the horizontal core bandwidth and vertical core bandwidth respectively; and Respectively represent X A and X i The horizontal component of the coordinate; and Respectively represent X A and X i The vertical component of the coordinates; each point X i X A The weight of the mean shift vector is related to the point and X AThe distance is related to the kernel function; Used to filter X within a fixed bandwidth i ; Calculate X A and X i The horizontal coordinate distance.

[0078] S2: According to the point density distribution characteristics of tree crowns and trunks in the UAV LiDAR point cloud in the forest area, the height histogram is used to preliminarily separate the trunk points and crown points to obtain the trunk candidate points. According to the uniqueness of the UAV LiDAR point cloud distribution in the forest area, geometric significance features such as plane difference significance and discrete difference significance are constructed to further subdivide the trunk candidate points to achieve accurate extraction of trunk points and object detection of trunks.

[0079] S2 specifically includes:

[0080] S21: According to the point density distribution characteristics of tree crowns and trunks in the UAV LiDAR point cloud in the forest area, the clusters obtained by mean shift clustering of each asymmetric kernel are divided into twelve intervals according to the elevation. The frequency of points appearing in each interval is counted, and the continuous height intervals with lower frequency in the height histogram are analyzed. The crown points and trunk points are preliminarily separated to obtain candidate trunk points.

[0081] S22: Calculate linear difference significance features, plane difference significance features and scattering difference significance features for each trunk candidate point, and use random forest to further subdivide the trunk candidate points into trunk points and non-trunk points;

[0082] Among them, in the calculation of the plane difference significance feature SoDP and the scattered difference significance feature SoDS, P, L, and S are calculated according to the eigenvalues ​​of the covariance matrix of the point cloud segmentation part, representing the plane feature, linear feature, and scattered point feature, respectively, and the formula is as follows:

[0083] SoDP = P + (1-P) × [P-max (L, S)]

[0084] SoDS=S+(1-S)×[S-max(L,P)]

[0085] S23: Clustering the identified tree trunk points using a 2D mean shift algorithm to obtain tree trunk clusters, thereby achieving object-oriented detection of tree trunks.

[0086] S3: Construct the crown and trunk collaborative features and mean shift modulus variance features, use random forest to divide the crown preliminary segmentation clusters into under-segmentation, correct segmentation and over-segmentation, and retain the correct segmentation as the single tree segmentation result;

[0087] S3 specifically includes:

[0088] S31: constructing crown and trunk collaborative features and mean shift modulus point variance features for the initial crown clusters obtained in S1, and identifying incorrect segmentation situations in the clusters based on these features;

[0089] The crown and trunk synergistic features include the number of trunks, the crown width predicted by the allometric model based on the tree height, and the difference between the crown width predicted by the crown height and the actual crown width of the crown cluster.

[0090] S32: Based on the crown and trunk collaborative features and mean shift modulus variance features in S31, random forest is used to divide the crown clusters into under-segmentation, over-segmentation and correct segmentation.

[0091] S4: Refine the over-segmented crown by using the mutual coordination and reference information of the crown and trunk; perform vertical regional growth on the trunk, sort all crown clusters from high to low, match them with the trunks respectively, output the correctly segmented crown as the single tree segmentation result, and further refine the under-segmented clusters.

[0092] S4 specifically includes:

[0093] S41: using the mutual coordination and reference information between the crown and the trunk, i.e. the allometric relationship between the trunk and the crown, the crown cluster identified as over-segmented is merged with the nearest under-segmented cluster;

[0094] S42: performing vertical region growth on the tree trunk detected in S3 to obtain a tree trunk that is as complete as possible;

[0095] S43: Sort the under-segmented and correctly segmented crowns from high to low, and use the allometric growth relationship between the trunk and the crown to match them with the vertically grown trunks. The correctly segmented crowns are output as single tree segmentation results, while the under-segmented results need further refinement.

[0096] S5: For the under-segmented crown clusters after matching, a graph cut segmentation method based on the optimization of the tree center vector deviation angle is constructed, and the under-segmented crown is optimized by using the mutual reference information between the crown and the trunk.

[0097] S5 specifically includes:

[0098] S51: Using the mutual reference information between the crown and the trunk, i.e. the two-dimensional vector angle consistency between the mean shift modulus point of the crown and the centroid of the trunk, and the allometric relationship between the size of the trunk and the crown, the graph cut optimization is performed on the under-segmented clusters after matching;

[0099] Firstly, the crown width is estimated according to the crown height in each cluster through the allometric growth model;

[0100] Secondly, the trunk points to be segmented are used as the foreground seed points of the graph cut, the remaining trunks are used as the background seed points of the graph cut, and the crown width estimated by the allometric growth model is used as the radius of the graph cut;

[0101] The radius calculation formula is as follows:

[0102] radius=0.446×H 0.854

[0103] Where: H is the normalized height of the tree trunk;

[0104] S52: Calculate the two-dimensional vector D from each point to the mode point through the mode point of the mean shift algorithm n , D n as the prediction vector for each point pointing to the center of the tree;

[0105] S53: Calculate the centroid of the foreground point, use the centroid as the tree center, and calculate the vector D of each point pointing to the tree center (n,k) , D (n,k) as the true vector for each point pointing to the center of the tree;

[0106] S54: Based on the prediction vector D n With the real vector D (n,k) , calculate the tree center vector angle weight w θ :

[0107]

[0108] S55: Deviate the tree center from the angle weight w θ and the original background penalty w in the graph cut back_penalty Add them together to get the mixed weight sink_weight as the new background penalty input into the graph cut algorithm. The new background penalty formula is as follows:

[0109]

[0110] sink_weight=0.5*w back_penalty +0.5*w θ

[0111] Where: dist 2d Indicates the two-dimensional plane distance from the foreground point to the input point cloud;

[0112] S56: Remove the segmented point cloud from the input point cloud, and repeat the above operation until all under-segmentation is segmented.

[0113] Embodiment 2: This embodiment provides a method for segmenting a single tree from a UAV laser radar point cloud based on collaborative information guidance. The method comprises the following steps:

[0114] First, the UAV laser radar scans the forest area to obtain the forest area point cloud (crown point cloud), and preprocesses the forest area point cloud and roughly segments the crown, including: filtering the ground points and normalizing the height of non-ground points; using the mean shift algorithm with a 3D asymmetric kernel to achieve rough single tree segmentation and obtain the initial crown clusters, such as Figure 2a and Figure 2b shown.

[0115] Second: Extract the trunk points of the initial single tree clusters, including: calculating the height histogram of the clusters to obtain potential trunk points, such as Figure 3 ; Calculate the plane difference significance, scattering difference significance and other features, use random forest to further screen potential trunk points (trunk candidate points); use 2D mean shift algorithm to cluster the trunk points, the trunk point extraction results are as follows Figure 4a and Figure 4b shown.

[0116] Third: segment the initial crown clusters in the first step, including: constructing the collaborative features of the crown and trunk and the mean shift modulus variance features; using random forest to divide the clusters into three segmentation results: over-segmentation, under-segmentation and correct segmentation.

[0117] Fourth: refine the over-segmented and under-segmented clusters, including: merging the over-segmented clusters into the under-segmented clusters; growing the vertical regions of the trunks extracted in the second step, and then matching the trunks and crowns according to the relationship of the allometric growth model.

[0118] Fifth: Optimize the crown segmentation results, including: foreground and background segmentation; calculate the modulus vector of the mean shift algorithm; calculate the true vector of each point pointing to the center of the tree, as shown in the vector diagram Figure 5 As shown in the figure; the tree center vector deflection weight is calculated according to the model point vector and the true vector, and the tree center vector deflection weight and the background penalty weight are mixed to obtain the mixed weight; the above process is repeated, and the graph cut method is iterated until all under-segmented clusters are segmented. The results of using the tree center vector deflection optimization and not using the tree center vector deflection optimization are shown in the figure below. Figure 6a and Figure 6b shown.

[0119] Working principle and process: The crown point cloud is obtained by scanning the forest area with UAV lidar, and the crown point cloud is preliminarily segmented into single trees; based on the preliminary segmentation results, on the basis of the preliminary separation of the crown and trunk, the difference significance features are designed to realize trunk detection; the collaborative features of the crown and trunk are constructed, the preliminary single tree segmentation results are classified, and the erroneous segmentation is identified; using the mutual coordination and reference information of the crown and trunk, a segmentation method based on the optimization of the tree center vector deflection angle is constructed to optimize the erroneous segmentation and finally realize the single tree segmentation.

[0120] The present invention aims at the characteristics of UAV laser point cloud and the single tree extraction method for different forest types, strengthens the recognition ability of incorrect crown segmentation, reduces the interference of the understory, improves the ability of tree boundary refinement segmentation, and effectively improves the accuracy and reliability of single tree extraction from UAV laser point cloud.

[0121] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0122] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance, characterized in that: The single wood segmentation method comprises the following steps: S1: The UAV laser radar scans the forest area to obtain the crown point cloud, and uses the mean shift algorithm of the 3D asymmetric kernel to preliminarily divide the crown point cloud to obtain a rough crown segmentation result, that is, the initial crown cluster; S2: Based on the point density distribution characteristics of tree crowns and trunks in the UAV LiDAR point cloud in the forest area, the height histogram is used to preliminarily separate the trunk points and the crown points to obtain the trunk candidate points. Based on the uniqueness of the UAV LiDAR point cloud distribution in the forest area, geometric saliency features are constructed, and the trunk candidate points are further subdivided to achieve accurate extraction of trunk candidate points and object detection of trunks; S3: constructing crown and trunk collaborative features and mean shift modulus variance features, using random forest to divide the initial crown class into under-segmentation, correct segmentation and over-segmentation, and retaining the correct segmentation as the single tree segmentation result; S4: Refine the over-segmented crown by using the mutual coordination and reference information of the crown and trunk; perform vertical region growth on the trunk, sort all crown clusters from high to low, match them with the trunk respectively, output the correctly segmented crown as the single tree segmentation result, and further refine the under-segmented clusters; S5: For the under-segmented crown clusters after matching, a graph cut segmentation method based on the optimization of the tree center vector deviation angle is constructed, and the under-segmented crown is optimized by using the mutual reference information between the crown and the trunk.

2. The method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance according to claim 1 is characterized in that: The S1 specifically includes: S11: Normalize the tree crown point cloud obtained by scanning the forest area with UAV lidar, and eliminate the low-lying vegetation points in the forest area according to the height threshold; S12: The tree crown point cloud is preliminarily segmented using the mean shift algorithm of the 3D asymmetric kernel. The three-dimensional space of the drone lidar point cloud is divided into two parts: the horizontal domain and the vertical domain. The horizontal domain uses a symmetric Gaussian kernel function to find the local maximum of density, and the vertical domain uses an asymmetric kernel function to find the local maximum of height. For any point X in the drone lidar point cloud, A , and its mean shift vector is expressed as: Among them, the vertical kernel function g r It is an asymmetric function. The specific expression is as follows: Where: superscript s and r represent horizontal domain and vertical domain respectively; g s and g r Represent the horizontal kernel function and the vertical kernel function respectively; h s and h r Represent the horizontal core bandwidth and vertical core bandwidth respectively; and Respectively represent X A and X i The horizontal component of the coordinate; and Respectively represent X A and X i The vertical component of the coordinates; each point X i X A The weight of the mean shift vector is related to the point and X A The distance is related to the kernel function; Used to filter X within a fixed bandwidth i ; Calculate X A and X i The horizontal coordinate distance.

3. The method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance according to claim 1 is characterized in that: The S2 specifically includes: S21: Divide the clusters obtained by mean shift clustering of each asymmetric kernel into twelve intervals according to the elevation, count the frequency of points appearing in each interval, analyze the continuous height intervals with lower frequency in the height histogram, perform preliminary separation of crown points and trunk points, and obtain candidate trunk points; S22: Calculate linear difference significance features, plane difference significance features and scattered difference significance features for each of the trunk candidate points, and use random forest to further subdivide the trunk candidate points into trunk points and non-trunk points, wherein in the calculation of the plane difference significance feature SoDP and the scattered difference significance feature SoDS, P, L, S are calculated based on the eigenvalues ​​of the covariance matrix of the point cloud segmentation part, representing the plane feature, linear feature and scattered point feature, respectively, and the formula is as follows: SoDP = P + (1-P) × [P-max (L, S)] SoDS=S+(1-S)×[S-max(L,P)] S23: Clustering the identified tree trunk points using a 2D mean shift algorithm to obtain tree trunk clusters.

4. The method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance according to claim 1 is characterized in that: The S3 specifically includes: S31: Based on the initial crown clusters obtained in S1, construct crown and trunk collaborative features and mean shift model point variance features, and identify incorrect segmentation in the initial crown clusters based on the crown and trunk collaborative features and the mean shift model point variance features; The crown and trunk synergistic features include the number of trunks under the initial crown cluster, the crown width predicted by the allometric model according to the tree height, and the difference between the crown width predicted by the crown height and the actual crown width of the crown cluster. S32: The crown and trunk collaborative features and the mean shift modulus variance features are used by random forest to divide the initial crown clusters into under-segmentation, over-segmentation and correct segmentation.

5. The method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance according to claim 4 is characterized in that: The S4 specifically includes: S41: using the mutual coordination and reference information between the crown and the trunk, i.e. the allometric relationship between the trunk and the crown, the crown cluster identified as over-segmented is merged with the nearest under-segmented cluster; S42: performing vertical region growth on the tree trunk detected in S3 to obtain a complete tree trunk; S43: Sort the under-segmented and correctly segmented crowns from high to low, and use the allometric growth relationship between the trunk and the crown to match them with the vertically grown trunks. The correctly segmented crowns are output as single tree segmentation results, while the under-segmented results need further refinement.

6. The method for segmenting single trees from UAV laser radar point cloud based on collaborative information guidance according to claim 5 is characterized in that: The S5 specifically includes: S51: Using the mutual reference information between the crown and the trunk, i.e. the two-dimensional vector angle consistency between the mean shift modulus of the crown and the centroid of the trunk, as well as the allometric relationship between the size of the trunk and the crown, the graph cut optimization is performed on the under-segmented clusters after matching: First, the crown width was estimated according to the crown height in each cluster through an allometric growth model. Secondly, the trunk points to be segmented are used as the foreground seed points of the graph cut, the remaining trunks are used as the background seed points of the graph cut, and the crown width estimated according to the allometric growth model is used as the radius of the graph cut; The radius calculation formula is as follows: radius=0.446×H 0.854 Where: H is the normalized height of the trunk; S52: Calculate the two-dimensional vector D from each point to the mode point through the mode point of the mean shift algorithm n , D n as the prediction vector for each point pointing to the center of the tree; S53: Calculate the centroid of the foreground point, use the centroid as the tree center, and calculate the vector D of each point pointing to the tree center (n,k) , D (n,k) as the true vector for each point pointing to the center of the tree; S54: Based on the prediction vector D n With the real vector D (n,k) , calculate the tree center vector angle weight w θ : S55: Deviate the tree center from the angle weight w θ and the original background penalty w in the graph cut back_penalty Add them together to get the mixed weight sink_weight as the new background penalty input into the graph cut algorithm. The new background penalty formula is as follows: sink_weight=0.5*w back_penalty +0.5*w θ Where: dist 2b Indicates the two-dimensional plane distance from the foreground point to the input point cloud; S56: Remove the segmented point cloud from the input point cloud, and repeat the above operation until all under-segmentation is segmented.

Images