Lehigh University - CSE:HaibinLing

Dr. Haibin Ling

"Sparse Representation of Shadow Modeling and Visual Tracking"

Friday, October 23, 2:00 PM

Packard Lab room 416

Reception prior to talk in Packard Lobby

Abstract: Sparse representation recently attracts a large amount of research attention and becomes a popular tool for many tasks in computer vision. In this talk, I will present our recent work applying sparse representation for shadow modeling and visual tracking.

Scenes with cast shadows can produce complex sets of images. These images cannot be well approximated by low-dimensional linear subspaces. However, in this talk we show that the set of images produced by a Lambertian scene with cast shadows can be efficiently represented by a sparse set of images generated by directional light sources. We first model an image with cast shadows as composed of a diffusive part (without cast shadows) and a residual part that captures cast shadows. Then, we express the problem in an L1-regularized least squares formulation, with nonnegativity constraints. This sparse representation enjoys an effective and fast solution, thanks to recent advances in compressive sensing. In experiments on both synthetic and real data, our approach performs favorably in comparison to several previously proposed methods.

Robust visual tracking is an important problem with many applications. We propose a robust visual tracking method by casting tracking as a sparse approximation problem in a particle filter framework. Specifically, to find the tracking target at a new frame, each target candidate is sparsely represented in the space spanned by target templates and trivial templates. The sparsity is achieved by solving an L1-regularized least squares problem. Then the candidate with the smallest projection error is taken as the tracking target. After that, tracking is continued using a Bayesian state inference framework in which a particle filter is used for propagating sample distributions over time. Two additional components further improve the robustness of our approach: 1) the nonnegativity constraints that help filter out clutter that is similar to tracked targets in reversed intensity patterns, and 2) a dynamic template update scheme that keeps track of the most representative templates throughout the tracking procedure. We test the proposed approach on five challenging sequences involving heavy occlusions, drastic illumination changes, and large pose variations.

Bio: Haibin Ling received the B.S. degree in mathematics and the MS degree in computer science from Peking University, China, in 1997 and 2000, respectively, and the PhD degree from the University of Maryland, College Park, in Computer Science in 2006. From 2000 to 2001, he was an assistant researcher in the Multi-Model User Interface Group at Microsoft Research Asia. From 2006 to 2007, he worked as a postdoctoral scientist at the University of California Los Angeles. After that, he joined Siemens Corporate Research as a research scientist. Since fall 2008, he has been an Assistant Professor at Temple University. Dr. Ling's research interests include computer vision, medical image analysis, human computer interaction, and machine learning. He received the Best Student Paper Award at the ACM Symposium on User Interface Software and Technology (UIST) in 2003.

		Dr. Haibin Ling "Sparse Representation of Shadow Modeling and Visual Tracking" Friday, October 23, 2:00 PM Packard Lab room 416 Reception prior to talk in Packard Lobby Abstract: Sparse representation recently attracts a large amount of research attention and becomes a popular tool for many tasks in computer vision. In this talk, I will present our recent work applying sparse representation for shadow modeling and visual tracking. Scenes with cast shadows can produce complex sets of images. These images cannot be well approximated by low-dimensional linear subspaces. However, in this talk we show that the set of images produced by a Lambertian scene with cast shadows can be efficiently represented by a sparse set of images generated by directional light sources. We first model an image with cast shadows as composed of a diffusive part (without cast shadows) and a residual part that captures cast shadows. Then, we express the problem in an L1-regularized least squares formulation, with nonnegativity constraints. This sparse representation enjoys an effective and fast solution, thanks to recent advances in compressive sensing. In experiments on both synthetic and real data, our approach performs favorably in comparison to several previously proposed methods. Robust visual tracking is an important problem with many applications. We propose a robust visual tracking method by casting tracking as a sparse approximation problem in a particle filter framework. Specifically, to find the tracking target at a new frame, each target candidate is sparsely represented in the space spanned by target templates and trivial templates. The sparsity is achieved by solving an L1-regularized least squares problem. Then the candidate with the smallest projection error is taken as the tracking target. After that, tracking is continued using a Bayesian state inference framework in which a particle filter is used for propagating sample distributions over time. Two additional components further improve the robustness of our approach: 1) the nonnegativity constraints that help filter out clutter that is similar to tracked targets in reversed intensity patterns, and 2) a dynamic template update scheme that keeps track of the most representative templates throughout the tracking procedure. We test the proposed approach on five challenging sequences involving heavy occlusions, drastic illumination changes, and large pose variations. Bio: Haibin Ling received the B.S. degree in mathematics and the MS degree in computer science from Peking University, China, in 1997 and 2000, respectively, and the PhD degree from the University of Maryland, College Park, in Computer Science in 2006. From 2000 to 2001, he was an assistant researcher in the Multi-Model User Interface Group at Microsoft Research Asia. From 2006 to 2007, he worked as a postdoctoral scientist at the University of California Los Angeles. After that, he joined Siemens Corporate Research as a research scientist. Since fall 2008, he has been an Assistant Professor at Temple University. Dr. Ling's research interests include computer vision, medical image analysis, human computer interaction, and machine learning. He received the Best Student Paper Award at the ACM Symposium on User Interface Software and Technology (UIST) in 2003.