Sets of local features that are invariant to common image transformations are an effective representation to use when comparing images; current methods typically judge feature set...
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...
Bottom-up segmentation tends to rely on local features. Yet, many natural and man-made objects contain repeating elements. Such structural and more spread-out features are importa...
See Through The Wall (STTW) applications have become of high importance to law enforcement, homeland security and defense needs. In this work surface penetrating radar is simulate...
The paper presents a novel coding technique based on approximate geometry for images taken from arbitrary recording positions around a 3-D scene. Such data structures occur in ima...