GS1-3 Development of Autonomous Robot for Laborsaving of the Forestry Discrimination between trees and weeds using RGB-D

Title:	GS1-3 Development of Autonomous Robot for Laborsaving of the Forestry Discrimination between trees and weeds using RGB-D
Publication:	ICAROB2018
Volume:	23
Pages:	51-54
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2018.GS1-3
Author(s):	Shingo Yamaguchi, Eiji Hayashi, Ayumu Tominaga
Publication Date:	February 2, 2018
Keywords:	Autonomous Self-Moving, Depth Sensor, Forest, Image processing
Abstract:	In traditional forestry, the weeding task places a large burden on workers. Therefore, it has been expected that such the problem will be solved by a robot. We have been developing an autonomous robot that eliminates the weed plants without damaging trees (these are resources). The robot should recognize trees exists in the environment. In this research, we have been focused on distinguishing between trees and other them. The system computes the RGB histogram of pixels corresponding point-cloud data of the ground extracted by plane detection. The threshold values are determined to discriminate between trees and weeds by this histogram automatically.
PDF File:	https://alife-robotics.co.jp/members2018/icarob/data/html/data/GS_pdf/GS1/GS1-3.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/