LiDAR point cloud data individual tree extraction method based on spectral clustering algorithm

A spectral clustering algorithm and point cloud data technology, which is applied in the field of LiDAR point cloud data single-tree extraction based on spectral clustering algorithm, can solve the problem that the segmentation accuracy cannot be guaranteed, and achieve strong practical value, good surface and high-efficiency single-tree recognition effect

Active Publication Date: 2019-11-08
RES INST OF FOREST RESOURCE INFORMATION TECHN CHINESE ACADEMY OF FORESTRY
View PDF16 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these algorithms need to make assumptions about the number of individual trees, and at the same tim

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • LiDAR point cloud data individual tree extraction method based on spectral clustering algorithm
  • LiDAR point cloud data individual tree extraction method based on spectral clustering algorithm
  • LiDAR point cloud data individual tree extraction method based on spectral clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] A single tree extraction method of LiDAR point cloud data based on spectral clustering algorithm, the implementation method is as follows figure 1 As shown, including the following operations:

[0025] Step 1. Normalize the height information of the airborne LiDAR point cloud data and establish CHM;

[0026] Step 2, voxelize the normalized point cloud in step 1 using the mean shift algorithm;

[0027] Mean shift is a clustering algorithm that groups points by iteratively shifting each point towards a point shifted from the mean. It does not require assumptions about the data distribution or the number of clusters, and is a fast and efficient classifier. The present invention uses the mean shift method to complete the voxelization process, each voxel is represented by the clustering result of the mean shift, the position of the voxel is determined by the coordinate center of the cluster point, and the weight of the voxel is equal to the number of points therein.

[00...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention aims to provide an LiDAR point cloud data individual tree extraction method based on a spectral clustering algorithm, which specifically comprises the steps of normalizing height information of LiDAR point cloud data, and performing voxelization by using a mean shift clustering algorithm; constructing a similarity graph in the voxel space based on a Gaussian similarity function; calculating feature values and feature vectors of the similarity graph by using a method, and determining a segmentation individual tree number k by using a feature value interval; and taking the featurevectors corresponding to the first k minimum feature values as columns to construct a feature vector matrix, performing k-means clustering on normalized row elements of the feature vector matrix in afeature space, and mapping a segmentation result back to the LiDAR point cloud to obtain single-tree clustering, thereby realizing single-tree segmentation of the point cloud. The method provided by the invention not only can carry out effective individual tree segmentation on the sample plot scale, but also can provide a stable segmentation result for the regional scale, and has a very high practical value.

Description

technical field [0001] The invention relates to a laser radar point cloud data processing technology, in particular to a method for single tree extraction of LiDAR point cloud data based on a spectral clustering algorithm. Background technique [0002] LiDAR (Light Detecting and Ranging, LiDAR) technology is one of the most revolutionary achievements in the field of remote sensing in the past 20 years. As an active remote sensing technology, airborne lidar can obtain the spatial structure characteristics of forests in a large range, and has outstanding advantages in high-precision extraction of key forest parameters. [0003] At present, there are many algorithms for extracting single trees from airborne LiDAR point cloud data, which can be mainly divided into surface model methods based on Canopy Height Models (CHM) and 3D methods using point cloud information. 3D methods can further Divided into clustering methods and voxel-based methods. The clustering method is an effe...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62
CPCG06F18/23213G06F18/2411
Inventor 庞勇王伟伟
Owner RES INST OF FOREST RESOURCE INFORMATION TECHN CHINESE ACADEMY OF FORESTRY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap