Illumination inconsistencies cause serious problems for classical computer vision applications such as tracking and stereo matching. We present a new approach to model illuminatio...
Contours and junctions are important cues for perceptual organization and shape recognition. Detecting junctions locally has proved problematic because the image intensity surface...
Michael Maire, Pablo Arbelaez, Charless Fowlkes, J...
Feature points for image correspondence are often selected according to subjective criteria (e.g. edge density, nostrils). In this paper, we present a general, non-subjective crit...
Existing sequential feature-based registration algorithms involving search typically either select features randomly (eg. the RANSAC[8] approach) or assume a predefined, intuitive...
In moving object environments, it is infeasible for the database tracking the movement of objects to store the exact locations of objects at all times. Typically, the location of a...
Reynold Cheng, Sunil Prabhakar, Dmitri V. Kalashni...