From bounces@ai.mit.edu Fri Mar 16 11:12:37 MST 2001 MIME-Version: 1.0 X-Sender: coates@life.ai.mit.edu Date: Fri, 16 Mar 2001 11:09:26 -0500 To: tech-sq-faculty@ai.mit.edu, Seminars@lcs.mit.edu, GRADS@hq.lcs.mit.edu, UGRADS@hq.lcs.mit.edu, ai-students@ai.mit.edu, ai-seminar-announce@ai.mit.edu, help-teach@hq.lcs.mit.edu, assistants@ai.mit.edu, tech-sq-staff@ai.mit.edu From: Teresa Coates Cataldo Subject: Frank Dellaert Seminar, April 2, Mon, NE43-518 Cc: coates@ai.mit.edu, annika@ai.mit.edu, wailes@hq.lcs.mit.edu, sally@ai.mit.edu Content-Type: text/plain; charset="us-ascii"; format=flowed DATE: Monday, April 2, 2001 TIME: Refreshments at 4:00pm TALK at 4:15pm LOCATION: NE43-518 Structure from Motion without Correspondence Frank Dellaert Carnegie Mellon University "Structure from motion" is the problem of recovering the 3D structure of a scene from a set of 2D views. Its applications range from building models of small objects to constructing large scale environment models. I will address the hard continuous-discrete optimization problem that arises when the correspondence between 2D measurements in the different views is unknown. To attack this problem, I combine tools from optimal estimation with Monte Carlo approximation methods designed to speed up the combinatorial data-association problem. In the talk, I will also discuss an efficient Markov chain sampler, developed by generalizing graph-theoretic algorithms for bipartite graph matching. The final algorithm is intuitive, fast, and works well in practice, as will be demonstrated using results on several real image sequences. While developed within the context of a computer vision, I conjecture that the methods I describe are more broadly applicable, i.e., whenever a large optimization problem is paired with a hard data-association problem. Such problems can arise in such diverse fields as target tracking, computational biology, and data mining. HOST: Prof. E. Grimson & Prof. T. Darrell