ARTIFICIAL LANDMARK SELF-LOCALIZATION FOR AGRICULUTRAL VEHICLE FIELD ROAD NAVIGATION USING OMNIDIRECTIONAL VISION
This paper introduces an artificial landmark self-localization method using omnidirectional vision for agricultural vehicles field road navigation. We propose a landmark model and 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 landmark position candidate and blue 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 landmark position another candidate, then distance between the center of gravity of the red patch and the center of gravity of the blue patch was calculated to judge whether or not it was an appropriate landmark representation in order to obtain the positions of landmarks and estimated the distance between landmark and camera in the image, then transformed the image distance to spatial distance and calculated the absolute location of camera. Outdoor experiments were conducted on a flat asphalt road in the field under natural sunlight. Experimental results showed that the RMS and mean distance errors are less than 24 cm in a 20 m distance. In conclusion, the self-localization method is a feasible and potential selection for agricultural vehicles field road navigation.
Agricultural vehicle Localization Omnidirectional vision Navigation.
MING LI KENJI IMOU KATSUHIRO WAKABAYASHI SHINYA YOKOYAMA
Graduate School of Agricultural and Life Sciences,the University of Tokyo,Japan
国际会议
北京
英文
1-10
2009-10-14（万方平台首次上网日期，不代表论文的发表时间）