Weed Detection Using Textural Image Analysis

G. Polder, F.K. van Evert, A. Lamaker, A. de Jong, G.W.A.M. van der Heijden, L.A.P. Lotz, A.J.A. van der Zalm, C. Kempenaar

Research output: Contribution to conferenceConference paper

Abstract

The objective of the work described here was to detect broad-leaved weeds in grassland. We used textural image analysis to detect weeds in grass. In the textural analysis, images were divided in square tiles, which were subjected to a 2-D FFT. The power of the resulting spectrum was found to be a measure of the presence of coarse elements (weeds). Application of a threshold made it possible to classify tiles as containing only grass or as containing a weed. A weed was assumed to be detected when a sufficient number of adjacent tiles were classified as containing weed material. The algorithm has a success rate of 94%.
Original languageEnglish
Publication statusPublished - 2007
EventEFITA/ WCCA conference -
Duration: 2 Jul 20075 Jul 2007

Conference

ConferenceEFITA/ WCCA conference
Period2/07/075/07/07

Keywords

  • weed control
  • grassland management
  • detection
  • integrated control

Fingerprint Dive into the research topics of 'Weed Detection Using Textural Image Analysis'. Together they form a unique fingerprint.

  • Cite this

    Polder, G., van Evert, F. K., Lamaker, A., de Jong, A., van der Heijden, G. W. A. M., Lotz, L. A. P., van der Zalm, A. J. A., & Kempenaar, C. (2007). Weed Detection Using Textural Image Analysis. Paper presented at EFITA/ WCCA conference, . https://edepot.wur.nl/28203