Probabilistic subspace-based learning of shape dynamics modes for multi-view action recognition


We propose a human action recognition algorithm by capturing a compact signature of shape dynamics from multi-view videos. First, we compute R transforms and its temporal velocity on action silhouettes from multiple views to generate a robust low level representation of shape. The spatio-temporal shape dynamics across all the views is then captured by fusion of eigen and multiset partial least squares modes. This provides us a lightweight signature which is classified using a probabilistic subspace similarity technique by learning inter-action and intra-action models. Quantitative and qualitative results of our algorithm are reported on MuHAVi a publicly available multi-camera multi action dataset.
[PDF] [BibTex]
S. Karthikeyan, Utkarsh Gaur, B.S. Manjunath, and Scott Grafton,
International Conference on Computer Vision (ICCV) Workshop PERHAPS 2011, Barcelona, Spain, Nov. 2011.
Node ID: 569 , DB ID: 378 , Lab: VRL , Target: Workshop
Subject: [IPL] « Look up more