Localization System Based on Artificial Landmark and Omnidirectional Vision

Abstract

We propose a localization system based on artificial landmarks and omnidirectional vision for agricultural vehicle navigation. The system sets four red artificial landmarks as a rectangle in the corners of an operating spot and estimates an absolute position. This paper introduces an algorithm in which red landmark pixels beyond the threshold were extracted as a small area and the center of gravity was calculated for the extracted small area representing the position of one landmark in order to obtain the positions of four representative landmarks and then estimate the four directional angles of the landmarks using only one omnidirectional image. Camera location was estimated using the center of gravity of the four intersections formed by four arcs according to geometric transformation based on the four directional angles of the landmarks. The experiments were conducted under natural sunlight in a 50 × 50-m square area to verify the system. Experimental results showed that the maximum and mean position errors were about 46.96 and 31.99 cm, respectively; camera tilt experiments showed that the tilt angle had some effect on errors, but not to an obvious level, and it was not necessary to compensate for the errors caused by camera tilt. In conclusion, this system is an effective selection for agricultural vehicle navigation in future.