Fast Segmentation via Randomized Hashing
Segmentation, the problem of breaking an image into coherent regions is, of course, a fundamental problem in Computer Vision. In this work we propose a new approach to the segmentation problem that leverages ideas developed in the Theoretical Computer Science literature to derive a new feature space based clustering algorithm that is amenable to real time implementation. Our current implementation runs at 10Hz on VGA resolution images on a MacBook Pro. We expect to be able to speed the scheme up by an order of magnitude on a GPU.
