Bilateral symmetry is a salient visual feature of many man-made objects. In this paper, we present research that use bilateral symmetry to identify, segment and track objects in re...
Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called...
—Optical flow algorithms are difficult to apply to robotic vision applications in practice because of their extremely high computational and frame rate requirements. In most case...
Abstract-- This paper presents an efficient implementation for correlation based stereo. Research in this area can roughly be divided in two classes: improving accuracy regardless ...
In this paper, we present a method to represent achromatic and chromatic image signals independently for content-based image indexing and retrieval for image database applications...