Recognition of Long-Term Behaviors by Parsing Sequences of Short-Term Actions with a Stochastic Regular Grammar
Human behavior understanding from visual data has applications such as threat recognition. A lot of approaches are restricted to limited time actions, which we call short-term actions. Long-term behaviors are sequences of short-term actions that are more extended in time. Our hypothesis is that they usually present some structure that can be exploited to improve recognition of short-term actions. We present an approach to model long-term behaviors using a syntactic approach. Behaviors to be recognized are hand-crafted into the model in the form of grammar rules. This is useful for cases when few (or no) training data is available such as in threat recognition. We use a stochastic parser so we handle noisy inputs. The proposed method succeeds in recognizing a set of predefined long-term interactions in the CAVIAR dataset. Additionally, we show how imposing prior knowledge about the structure of the long-term behavior improves the recognition of short-term actions with respect to standard statistical approaches.
Keywordslong-term behavior stochastic context-free grammars human activity analysis visual surveillance
- 3.Brdiczka, O., Yuen, P.C., Zaidenberg, S., Reignier, P., Crowley, J.L.: Automatic acquisition of context models and its application to video surveillance. In: ICPR, pp. 1175–1178 (2006)Google Scholar
- 5.Burghouts, G., Schutte, K.: Correlations between 48 human actions improve their detection. In: ICPR (2012)Google Scholar
- 7.Hays, D.G.: Chomsky hierarchy. In: Encyclopedia of Computer Science, pp. 210–211. John Wiley and Sons Ltd., ChichesterGoogle Scholar
- 10.Kitani, K.M., Sato, Y., Sugimoto, A.: Recovering the basic structure of human activities from a video-based symbol string. In: WMVC, p. 9 (2007)Google Scholar