Road Plane Detection using Differential Homography Estimated by Pair Feature Matching of Local Regions
Kenji Nishida, Jun Fujiki, Chikao Tsuchiya, Shinya Tanaka, Takio Kurita · 2011
This paper presents a novel algorithm for road plane de-tection from an on-board camera. The algorithm employs the temporal difference of homography matrix, which is termed differential homography, caused by camera motion. Differential homography is estimated from optical flows of road plane regions, while using RANSAC algorithm to ex-tract the majority optical flows. Since differential homog-raphy is estimated using the relationship between the image coordinate (location in an image) and the flows at the loca-tions in an image. The proposed algorithm does not require the estimation of the homography matrix itself. Therefore, the proposed algorithm can be applied without calibration. The proposed algorithm effectively detect the optical flows from road region with using the pixel-pair feature match-ing. The algorithm is applied to the city traffic images distributed by UCL, and its average road detection ratio is found to be 75.6%. It is also applied to the previously col-lected suburban traffic images. A suitable detection result is obtained.