ROBUST-DETECTION OF STRAIGHT AND CIRCULAR ROAD SEGMENTS IN NOISY AERIAL IMAGES

This paper treats the problem of detecting straight or circular pieces of road in noisy low-resolution aerial images. it first uses a local operator to detect pixels whose neighborhoods are line-like, and then applies (robust) estimation techniques to find sets of such pixels tha t lie on or near straight or circular loci. An (unbiased) ordinary lea st squares estimator cannot handle outlying data even for straight loc i; on the other hand, conventional robust techniques for fitting circu lar arcs are severely affected by digitization effects and the fact th at circular road segments are typically short and shallow. We therefor e introduce an estimator that is both robust and statistically efficie nt. We also present a simple ad hoc technique that achieves comparable results and can handle road segments that are either straight or circ ular. (C) 1997 Pattern Recognition Society. Published by Elsevier Scie nce Ltd.