Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients

Abstract

In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.

References in corpus (2)

• Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition
• Improved Foreground Detection via Block-based Classifier Cascade with Probabilistic Decision Integration

Cited by in corpus (3)

• Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors
• Towards Miss Universe Automatic Prediction: The Evening Gown Competition
• Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions