Multiple View Object Cosegmentation using Appearance and Stereo Cues
chairman: Aude Oliva, Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, MIT
chairman: Silvio Savarese, Department of Electrical Engineering and Computer Science, University of Michigan
published: Nov. 12, 2012, recorded: October 2012, views: 4859
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
We present an automatic approach to segment an object in calibrated images acquired from multiple viewpoints. Our system starts with a new piecewise planar layer-based stereo algorithm that estimates a dense depth map that consists of a set of 3D planar surfaces. The algorithm is formulated using an energy minimization framework that combines stereo and appearance cues, where for each surface, an appearance model is learnt using an unsupervised approach. By treating the planar surfaces as structural elements of the scene and reasoning about their visibility in multiple views, we segment the object in each image independently. Finally, these segmentations are refined by probabilistically fusing information across multiple views. We demonstrate that our approach can segment challenging objects with complex shapes and topologies, which may have thin structures and non-Lambertian surfaces. It can also handle scenarios where the object and background color distributions overlap significantly.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !