Sciweavers

Share
TCSV
2010

Action Detection in Cluttered Video With Successive Convex Matching

10 years 6 months ago
Action Detection in Cluttered Video With Successive Convex Matching
We propose a novel successive convex matching method for human action detection in cluttered video. Human actions are represented as sequences of poses, and specific actions are detected by matching pose sequences. Since we represent actions as the evolution of poses and shapes, the proposed method can detect actions in videos that involve fast camera motions. Template sequence to video registration is nonlinear and highly non-convex. Instead of directly solving the hard problem, our method convexifies it into a sequence of linear programs and refines the matching by successive trust region shrinkage. The proposed scheme further simplifies the linear programs by representing the target point space with a small set of basis points. The low complexity of the proposed method enables it to search efficiently in a large range. Experiments show that successive convex matching can robustly match a sequence of coupled shape templates simultaneously to target sequences and effectively detect sp...
Hao Jiang, Mark S. Drew, Ze-Nian Li
Added 21 May 2011
Updated 21 May 2011
Type Journal
Year 2010
Where TCSV
Authors Hao Jiang, Mark S. Drew, Ze-Nian Li
Comments (0)
books