Fast realistic multi-action recognition using mined dense spatio-temporal features

Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it is not necessarily optimal in terms of class separability and classification. This paper proposes a novel approach that uses very dense corner features that are spatially and temporally grouped in a hierarchical process to produce an overcomplete compound feature set. Frequently reoccurring patterns of features are then found through data mining, designed for use with large data sets. The novel use of the hierarchical classifier allows real time operation while the approach is demonstrated to handle camera motion, scale, human appearance variations, occlusions and background clutter. The performance of classification, outperforms other state-of-the-art action recognition algorithms on the three datasets; KTH, multi-KTH, and realworld movie sequences containing broad actions. Multiple action localisation is pe...

• Type: Journal
• Year: 2009
• Where: ICCV
• Authors: Andrew Gilbert, John Illingworth, Richard Bowden
• Keywords: Computer Vision, Groundtruth Localisation Data, ICCV 2009, Overcomplete Compound Feature, Real Time