This paper presents a new method for segmentation of images into large regions that reflect the real world objects present in a scene. It explores the feasibility of utilizing sp...
We propose a region-based foreground object segmentation method capable of dealing with image sequences containing noise, illumination variations and dynamic backgrounds (as often...
Current image enhancement in televisions can be improved if the image is analyzed, objects of interest are segmented, and each segment is processed with specifically optimized alg...
Real world computer vision systems highly depend on reliable, robust retrieval of motion cues to make accurate decisions about their surroundings. In this paper, we present a simp...
We propose a method to identify and localize object
classes in images. Instead of operating at the pixel level,
we advocate the use of superpixels as the basic unit of a
class s...