Share Email Print

Proceedings Paper

Image classification approach for automatic identification of grassland weeds
Author(s): Steffen Gebhardt; Walter Kühbauch
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The potential of digital image processing for weed mapping in arable crops has widely been investigated in the last decades. In grassland farming these techniques are rarely applied so far. The project presented here focuses on the automatic identification of one of the most invasive and persistent grassland weed species, the broad-leaved dock (Rumex obtusifolius L.) in complex mixtures of grass and herbs. A total of 108 RGB-images were acquired in near range from a field experiment under constant illumination conditions using a commercial digital camera. The objects of interest were separated from the background by transforming the 24 bit RGB-images into 8 bit intensities and then calculating the local homogeneity images. These images were binarised by applying a dynamic grey value threshold. Finally, morphological opening was applied to the binary images. The remaining contiguous regions were considered to be objects. In order to classify these objects into 3 different weed species, a soil and a residue class, a total of 17 object-features related to shape, color and texture of the weeds were extracted. Using MANOVA, 12 of them were identified which contribute to classification. Maximum-likelihood classification was conducted to discriminate the weed species. The total classification rate across all classes ranged from 76 % to 83 %. The classification of Rumex obtusifolius achieved detection rates between 85 % and 93 % by misclassifications below 10 %. Further, Rumex obtusifolius distribution and the density maps were generated based on classification results and transformation of image coordinates into Gauss-Krueger system. These promising results show the high potential of image analysis for weed mapping in grassland and the implementation of site-specific herbicide spraying.

Paper Details

Date Published: 27 September 2006
PDF: 8 pages
Proc. SPIE 6298, Remote Sensing and Modeling of Ecosystems for Sustainability III, 629806 (27 September 2006); doi: 10.1117/12.678752
Show Author Affiliations
Steffen Gebhardt, Univ. Bonn (Germany)
Walter Kühbauch, Univ. Bonn (Germany)

Published in SPIE Proceedings Vol. 6298:
Remote Sensing and Modeling of Ecosystems for Sustainability III
Wei Gao; Susan L. Ustin, Editor(s)

© SPIE. Terms of Use
Back to Top