Publications:A vision based row-following system for agricultural field machinery

From ISLAB/CAISR
Revision as of 21:41, 30 September 2016 by Slawek (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Do not edit this section

Keep all hand-made modifications below

Title A vision based row-following system for agricultural field machinery
Author Björn Åstrand and Albert-Jan Baerveldt
Year 2005
PublicationType Journal Paper
Journal Mechatronics (Oxford)
HostPublication
Conference
DOI http://dx.doi.org/10.1016/j.mechatronics.2004.05.005
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:237417
Abstract In the future, mobile robots will most probably navigate through the fields autonomously to perform different kind of agricultural operations. As most crops are cultivated in rows, an important step towards this long-term goal is the development of a row-recognition system, which will allow a robot to accurately follow a row of plants. In this paper we describe a new method for robust recognition of plant rows based on the Hough transform. Our method adapts to the size of plants, is able to fuse information coming from two rows or more and is very robust against the presence of many weeds. The accuracy of the position estimation relative to the row proved to be good with a standard deviation between 0.6 and 1.2 cm depending on the plant size. The system has been tested on both an inter-row cultivator and a mobile robot. Extensive field tests have showed that the system is sufficiently accurate and fast to control the cultivator and the mobile robot in a closed-loop fashion with a standard deviation of the position of 2.7 and 2.3 cm, respectively. The vision system is also able to detect exceptional situations by itself, for example the occurrence of the end of a row.