ORBi: Piron Alexis - Determination of plant height for weed detection in stereoscopic images

Reference : Determination of plant height for weed detection in stereoscopic images


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Life sciences : Agriculture & agronomy
	To cite this reference:	http://hdl.handle.net/2268/17767

Title :	Determination of plant height for weed detection in stereoscopic images
Language :	English
Author, co-author :	Piron, Alexis [Université de Liège - ULg > Gembloux Agro-Bio Tech > Gembloux Agro-Bio Tech >]
	Leemans, Vincent [Université de Liège - ULg > Gembloux Agro-Bio Tech > Gembloux Agro-Bio Tech >]
	Kleynen, Olivier [ > > ]
	Destain, Marie-France [Université de Liège - ULg > Gembloux Agro-Bio Tech > Gembloux Agro-Bio Tech >]
Publication date :	2008
Main document title :	AGENG 2008 Conference - Agricultural & Biosystems Engineering for a Sustainable World
On invitation :	No
Audience :	International
Event name :	Ag-Eng 2008 (International Conference on Agricultural Engineering)
Event place (city) :	Hersonissos
Event country :	Greece
Keywords :	[en] machine vision ; weeds ; organic farming
Abstract :	[en] The aim of this study was twofold. The first goal was to acquire high accuracy stereoscopic images of small-scale field scenes, the second to examine the potential of plant height as a discriminant factor between crop and weed, within carrot rows. Emphasis was put on how to determine actual plant height taking into account the variable distance from camera to ground and ground irregularities for in-field measurements. Multispectral stereoscopic images were taken over a period of 19 days starting one week after crop emergence and seven weed species were considered. Images were acquired with a mobile vision system consisting in a filter wheel based multispectral camera and a video projector. The stereoscopy technique used belonged to the coded structured light family. The stereoscopic acquisition method yielded good results despite the numerous stereoscopic difficulties exhibited by the scenes. A plant height parameter as opposed to distance from camera to plant pixels gave better results for classification (classification accuracy of up
Research units :	Gembloux Agro-Bio Tech
Funders :	SPW
Name of the research project :	RECADVEN
Target :	Researchers
Permalink :	http://hdl.handle.net/2268/17767

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	Ageng2008.pdf		Publisher postprint	2.44 MB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5