Bag of Optical Flow Volumes for Image Sequence Recognition

Proceedings of British Machine Vision Conference (BMVC)

This paper introduces a novel 3D interest point detector and feature representation for describing image sequences. The approach considers image sequences as spatio-temporal volumes and detect Maximally Stable Volumes (MSVs) in efficiently calculated optical flow fields. This provides a set of binary optical flow volumes highlighting the dominant motions in the sequences. On the detected binary volumes a feature representation in a 3D shape context description method with 3D interest points sampled on the surface of the volumes is calculated. A standard bag-of-words approach then allows building discriminant optical flow volume signatures, which enables the prediction of class labels of previously unseen image sequences by machine learning algorithms. We evaluate the proposed method for the task of action recognition on the well-known Weizmann dataset, and show that we outperform recently proposed state-of-the-art 3D interest point detection and description
methods.

PDF (Abstract)

PDF