Weed detection and discrimination in maize fields using ultrasonic and lidar sensors
- Publikations-Art
- Kongressbeitrag
- Autoren
- Escolà, Alexandre and Andújar, D. and Dorado, J. and Fernández-Quintanilla, C. and Rosell-Polo, Joan R.
- Erscheinungsjahr
- 2012
- Veröffentlicht in
- Proceedings of the 12th International Conference of Agricultural Engineerig CIGR 2012
- Seite (von - bis)
- C2125
- Tagungsname
- CIGR 2012
- Tagungsort
- Valencia, Spain
- Tagungsdatum
- July 8-12, 2012
Optical and ultrasonic sensors have been the most used sensors to detect vegetation. Sensor technologies have rapidly improved and sensors are more reliable and provide much more data. In weed detection, optical sensors have been studied (Andújar et al., 2011) and commercial applications are available for patch spraying. However, these applications cannot distinguish between crop and weeds or between weed species. Other approaches are the ones based on image analysis according to shape, colour and texture but they require longer processing times and powerful microprocessors. We will take advantage on the use of ultrasonic (Escolà et al., 2011; Llorens et al., 2011) and lidar sensors (Rosell et al., 2009; Rosell \& Sanz, 2011) previously used to characterize tree and vine canopies to detect and recognize different weed species groups owing to its simplicity and relatively low cost.