Laser point cloud-oriented single tree segmentation method based on Faster R-CNN

A laser point cloud and point cloud technology, applied in image analysis, image data processing, image enhancement, etc., can solve problems such as irregular tree crown height and deformation of wood components, and achieve high accuracy.

Active Publication Date: 2019-10-25
NANJING FORESTRY UNIV
View PDF1 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, accurate individual canopy segmentation using ground-moving lidar is still challenging, especially for ecological forests with irregular canopy heights and severe crossings.
Although some pioneering studies have been reported on the detection of tree trunk locations from ground-moving lidar data for tre

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
  • Laser point cloud-oriented single tree segmentation method based on Faster R-CNN
  • Laser point cloud-oriented single tree segmentation method based on Faster R-CNN
  • Laser point cloud-oriented single tree segmentation method based on Faster R-CNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The following is based on Figure 1 to Figure 10 The specific embodiment of the present invention is further described:

[0048] A single tree segmentation method based on Faster R-CNN for laser point cloud, the process is as follows figure 1 shown, including:

[0049] Step 1: Obtain forest segment point cloud data based on ground mobile LiDAR.

[0050] Specifically: figure 2 In order to study the general map of the site, the experimenters carried the Velodyne HDL-32E scanner on their backs, and walked back and forth in the three rubber forest segments at a speed of 0.5 m / s according to the established measurement route to obtain point cloud data of the target rubber forest segment. The data splicing of the whole system adopts the simultaneous localization and mapping (SLAM) algorithm.

[0051] In this embodiment, a subset of forest segments is created for three rubber forest segments (rubber forest segment 1, rubber forest segment 2, and rubber forest segment 3), ...

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 discloses a Laser point cloud-oriented single tree segmentation method based on Faster R-CNN. The method comprises the steps of obtaining forest stand point cloud data; calculating pointcloud features of the scanned forest segments to realize branch and leaf separation of forest segment point cloud data; performing adaptive voxelization operation on the main point cloud data of theforest stand, and performing multi-angle projection on the main point cloud data to generate a corresponding depth image; detecting a trunk in the generated depth image by adopting a deep learning method; and obtaining the spatial three-dimensional point cloud of the corresponding trunk through back projection by utilizing the position information of the trunk in the detected depth image; and taking the obtained point cloud of the trunk part as a seed point, and combining a region growing algorithm to realize individual tree separation. According to the method, a deep learning method is adopted, learning is carried out by means of big data samples, the accuracy of individual tree segmentation is higher, and possibility is provided for accurately solving the problem of individual rubber tree segmentation based on LiDAR data of the ground by using deep learning.

Description

technical field [0001] The invention relates to the technical field of individual plant separation, in particular to a laser point cloud-based single tree segmentation method based on Faster R-CNN. Background technique [0002] As an important industrial raw material and strategic material, natural rubber widely planted in tropical areas plays an increasingly prominent role in national economic construction. However, rubber trees are wild species in the Amazon River Basin in South America, and there are no wild resources in our country, so most of the rubber forests in our country are pure artificial forests. As the largest rubber production base in my country, Hainan has nearly 8 million acres of rubber forests, forming the largest artificial ecosystem. However, due to its geographical location, it is often disturbed by typhoons. According to statistics, in the past 60 years, Hainan Island has been hit by more than 100 typhoons. Typhoons occur in a short period of time a...

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): G06T7/11G06N3/04
CPCG06T7/11G06T2207/10028G06T2207/20081G06T2207/30188G06N3/045Y02A90/10
Inventor 云挺陈鑫鑫王佳敏曹林
Owner NANJING FORESTRY UNIV
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