Directional scale imaging for extracting maneuvering affordance
Koji KAMEJIMA · 2003
A scheme is presented for detecting maneuvering affordance in noisy imagery. Under the assumption that roadway texture can be identified with noisy observation of fractal attractors, image features are represented in directional scale images. For eliminating background noise, pixelwise filter is designed based on probabilistic complexity analysis. The detectability of affordance patterns has been verified through experimental studies.