October 10th, 2012 @ 11:30am Daniel Glasner (Weizmann)

Clustering Segmentations and Viewpoint-Aware Detection

Abstract: In this talk I will present an unsupervised, shape-based method for joint clustering of multiple image segmentations. Given two or more closely related images, along with an initial over-segmentation, our method computes a joint clustering of segments in the two frames. The clustering is computed as an approximate minimizer of a functional which gives preference to selections whose shape matches across frames and which are internally coherent within each frame. We introduce a novel contour-based representation that allows us to compute the shape similarity of a subset of segments in one frame to the other. The comparison looks only at the exterior bounding contours, receiving no contribution from segment boundaries which fall inside the union. Combining this contour-based score with region information gives rise to a quadratic semi-assignment problem whose solution we approximate by applying an efficient linear programming relaxation. This is joint work with Shiv N. Vitaladevuni and Ronen Basri.

In the second part of the talk I will describe a simple technique for generating models of object classes, which relates 3D shape and 2D appearance. I will demonstrate its application to viewpoint-invariant detection and pose estimation of a rigid object from a single 2D image. This is joint work with Meirav Galun, Sharon Alpert, Ronen Basri and Gregory Shakhnarovich.

Bio: Daniel Glasner is a Ph.D. candidate at The Weizmann Institute of Science advised by Prof. Ronen Basri. He has worked on various problems in computer vision including super-resolution from a single image, image and video segmentation and viewpoint-invariant object detection. Daniel received his M.Sc. from Tel-Aviv University where he worked on online algorithm theory with Prof. Yossi Azar. http://www.wisdom.weizmann.ac.il/~glasner/

seminars/seminaritems/2012-10-10.txt · Last modified: 2012/10/02 21:07 by silberman