— This paper makes new contributions in motion detection, object segmentation and trajectory estimation to create a successful object tracking system. A new efficient motion det...
We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key ...
We use cluster analysis as a unifying principle for problems from low, middle and high level vision. The clustering problem is viewed as graph partitioning, where nodes represent ...
—In partitioning, clustering, and grouping problems, a typical goal is to group together similar objects, or pixels in the case of image processing. At the same time, another goa...
This paper proposes a new evolutionary region merging method in order to efficiently improve segmentation quality results. Our approach starts from an oversegmented image, which is...