# US 10,768,303 B2 · Method for identifying individual trees in airborne lidar data and corresponding computer program product > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,768,303 B2 - Document ID: US10768303B2 - Status: Granted - Kind: B2 - Application number: 15/755,100 - Filed: 2016-08-24 - Published: 2020-04-23 - Granted: 2020-09-08 - Earliest claimed: 2015-08-24 - Assignees: YaDo Holding B.V.; Biao Xiong - Applicants: YaDo Holding B.V.; Biao Xiong - Inventors: Biao Xiong; Dong Yang - Web page: https://patentgrep.com/patent/US10768303B2 ## CPC - G01S 17/89: for mapping or imaging - G01S 7/4802: {using analysis of echo signal for target characterisation; Target signature; Target cross-section} - G06T 3/067: Reshaping or unfolding three-dimensional [3D] tree structures onto two-dimensional [2D] planes - G06T 7/11: Region-based segmentation - G06V 20/188: {Vegetation} - G06T 2207/10032: Satellite or aerial image; Remote sensing - G06T 2207/20152: Watershed segmentation - G06T 2207/30188: Vegetation; Agriculture - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract The invention relates to a method for identifying individual trees in airborne lidar data and a corresponding computer program product. The method comprises: a. obtaining lidar data points of a group of one or more trees; b. define voxels in a regular 3D grid on the basis of the data points; c. applying an image segmentation algorithm to obtain at least one segment; and, if at least two segments are obtained: d. find the root voxel and branch voxels of a first segment and a second neighbouring segment; and e. merging the first and second segment if the distance between the first and second root voxel is less than a first threshold, the distance between the first root voxel and the closest second branch voxel is less than a second threshold; and the distance between the first branch voxels and the second branch voxels is less than a third threshold. ## Claims ### Claim 1 A method for identifying individual trees in airborne lidar data, comprising the steps of: a. obtaining lidar data of a group of one or more trees to be separated into individual trees, the lidar data comprising a plurality of lidar data points; b. define voxels in a regular 3D grid on the basis of the lidar data points; c. applying an image segmentation algorithm to obtain at least one segment comprising a subset of the 3D voxels; wherein the following steps are performed if at least two segments are obtained in step c: d. for each of a first segment and a second neighbouring segment of said at least two segments: I. find the root voxel of said segment, the root voxel being a voxel having the lowest height of the voxels of said segment; II. find the branch voxels of said segment, wherein a branch voxel is a voxel connected directly or indirectly to the root voxel; e. merging the first segment and the neighbouring second segment if: I. the distance between the root voxel of the first segment and the root voxel of the second segment is less than a first threshold; and II. the distance between the root voxel of the first segment and the closest branch voxel of the second segment is less than a second threshold; and III. the distance between each of the branch voxels of the first segment and the corresponding closest branch voxels of the second segment is less than a third threshold. ### Claim 2 (depends on 1) The method according to claim 1, wherein step c. comprises applying watershed segmentation to obtain the at least one segment. ### Claim 3 (depends on 2) The method according to claim 2, comprising projecting the 3D voxels on a 2D grid corresponding to the horizontal plane, wherein each grid cell is assigned a value on the basis of the height coordinates of the 3D voxels projected onto said grid cell. ### Claim 4 (depends on 3) The method according to claim 3, wherein each grid cell is assigned a value corresponding to an average, a mode, a median or a maximum of the height coordinates of the 3D voxels projected onto said grid cell. ### Claim 5 (depends on 1) The method according to claim 1, wherein steps d. and e. are iterated over all segments. ### Claim 6 (depends on 1) The method according to claim 1, wherein step a. comprises obtaining lidar data, separating lidar data in ground data and non-ground data and separating non-ground data in said lidar data of a group of one or more trees and non-tree data. ### Claim 7 (depends on 1) The method according to claim 1, further comprising modelling the individual trees on the basis of the obtained individual tree segments to produce a set of 3D models for each individual tree. ### Claim 8 (depends on 1) The method according to claim 1, further comprising extracting parameters from the segments corresponding to individual trees. ### Claim 9 (depends on 8) The method according to claim 8, the parameters comprising at least one of: height of the tree, volume of the tree and canopy area of the tree. ### Claim 10 (depends on 1) A computer program product comprising non-transitory computer-executable instructions configured to, when executed, perform the steps of the method of claim 1.