Article,

Automated Crop and Weed Monitoring in Widely Spaced Cereals

, , and .
Precision Agriculture, 7 (1): 21--32 (March 2006)

Abstract

Abstract  An approach is described for automatic assessment of crop and weed area in images of widely spaced (0.25 m) cereal crops, captured from a tractor mounted camera. A form of vegetative index, which is invariant over the range of natural daylightillumination, was computed from the red, green and blue channels of a conventional CCD camera. The transformed image can besegmented into soil and vegetative components using a single fixed threshold. A previously reported algorithm was appliedto robustly locate the crop rows. Assessment zones were automatically positioned; for crop growth directly over the crop rows,and for weed growth between the rows. The proportion of crop and weed pixels counted was compared with a manual assessmentof area density on the basis of high resolution plan view photographs of the same area; this was performed for views witha range of crop and weed levels. The correlation of the manual and automatic measures was examined, and used to obtain a calibrationfor the automatic approach. The results of mapping of a small field, at two times, are presented. The results of the automatedmapping appear to be consistent with manual assessment.

Tags

Users

  • @midtiby

Comments and Reviews