Improved Discriminative Model for View- Invariant Human Action Recognition

Recognizing human actions play an important role in applications like video surveillance. The recent past has witnessed an increasing research on view-invariant action recognition. Huang et al. proposed a framework based on discriminative model for human action recognition. This model uses STIP (Space – Time Interest Point) to extract motion features and view invariants. Then a discriminative model is used to model known as hidden Conditional Random Fields (HCRF) for conditional probability estimation for action recognition. They focused on five classes of actions namely climb, jump, run, swing and walk. In this paper we extend the discriminative model proposed by Huang et al. to explore more classes of actions. We built a prototype application to demonstrate human action recognition. The experimental results revealed that the application is capable of accurately recognizing human actions.