Position Estimation Method Using Artificial Landmarks and Omnidirectional Vision

Abstract

The development of autonomous navigation systems for agricultural vehicles is an important endeavor. We propose a position estimation method based on artificial landmarks and omnidirectional vision for agricultural vehicle navigation to augment GPS-based solutions. The method sets four red artificial landmarks as a rectangle in the corners of an operating area and estimates an absolute position relative to the landmark-based coordinate system on the ground. This article introduces an algorithm to extract the landmarks and estimate the directional angles of the landmarks using only one omnidirectional image. Camera location was estimated based on the directional angles of the landmarks. Experiments were conducted under natural sunlight in a 50 m 50 m square area to verify the method. Experimental results showed that the maximum and mean position errors were about 46.96 cm and 31.99 cm, respectively. Camera tilt experiments showed that the tilt angle had some effect on errors, but not significantly, and it was not necessary to compensate for the errors caused by camera tilt on uneven ground. In conclusion, this method is feasible to augment GPS-based solutions for agricultural vehicle navigation.