Ultrasonic measurements for weed detection in cereal crops
- Publication Type
- Contribution to conference
- Authors
- Dionisio Andújar and Martin Weis and Roland Gerhards
- Year of publication
- 2012
- Published in
- Proceedings of first RHEA international conference on robotics and associated high-technologies and equipment for agriculture
- Editor
- Andrea Perruzi
- Pubisher
- Pisa University Press srl , Pisa, Italy
- ISBN / ISSN / eISSN
- 9788867410217
- Page (from - to)
- 287--292
- Conference name
- RHEA2012
- Conference location
- Pisa, Italy
- Conference date
- September 19-20-21, 2012
- Keywords
- Unkrautregulierung
An automation of site-specific weed management requires sensing of the actual weed infestation levels in agricultural fields to adapt the management accordingly. In this paper, a sensor based weed detection method is presented and its applicability to cereal crops is evaluated. The sensing unit consists of an ultrasonic distance sensor for the determination of plant heights. It was hypothesised that the weed infested zones have a higher amount of biomass than non-infested areas and that this can be determined by the plant height measurements. Ultrasonic distance measurements were taken in a winter wheat field infested by grass weeds and broad-leaved weeds. A total of 120 samples of different weed densities and compositions were assessed at two different dates. The sensor was pointed directly to the ground for height determination. In the following, weeds were counted and then removed from the sample locations, before a second sensor reading was taken. Differences between weed infested and weed-free measurements were determined. Images were taken simultaneously and the coverage of weeds and crop were determined using image-processing methods. Dry-matter of the weeds and crop was assessed and evaluated together with the sensor measurements. RGB images were taken prior and after weed removal to determine the coverage percentages of weeds and crop per sampling point. The images were transformed and thresholded to separate plants and background. The relationship between ultrasonic readings and the actual values of the crop and weed coverage was assessed using regression analysis. Results revealed a height difference between infested and non-infested sample locations. Density and biomass of weeds present in the sample influenced the ultrasonic readings.