Abstract

This paper presents a system for the detection of weed amongst crop based on the extraction of structural field information. Data is gathered online with a sensor built upon an imaging spectrograph optimized for this purpose. The optical sensor splits the light from a line on the ground parallel with the spray boom in its spectral components that are projected on a camera. One of the main advantages of this sensor type is the high spatial resolution (up to a few mm). The weed detection algorithm uses the reflectance differences between the red and the near-infrared bands to make the distinction between plants and soil. Detection of weed amongst crop is based on the detection of weed patches and the extraction of the crop rows. A mathematical model for the herbicide reduction and the hit rate is presented that shows the relations between the different system parameters such as the spray resolution and the performance of the classifier.

Copyright © 1999. . Copyright © 1999 American Society of Agronomy, Inc., Crop Science Society of America, Inc., Soil Science Society of America Inc., 5585 Guilford Rd., Madison, WI 53711 USA