Detection and Classification of Multiple Person Interaction

Abstract

This thesis investigates the classification of the behaviour of multiple persons when viewed from a video camera. Work upon a constrained case of multiple person interaction in the form of team games is investigated. A comparison between attempting to model individual features using a (hierarchical dynamic model) and modelling the team as a whole (using a support vector machine) is given. It is shown that for team games such as handball it is preferable to model the whole team. In such instances correct classification performance of over 80% are attained. A more general case of interaction is then considered. Classification of interacting people in a surveillance situation over several datasets is then investigated. We introduce a new feature set and compare several methods with the previous best published method (Oliver 2000) and demonstrate an improvement in performance. Classification rates of over 95% on real video data sequences are demonstrated. An investigation into how the length of time a sequence is observed is then performed. This results in an improved classifier (of over 2%) which uses a class dependent window size. The question of detecting pre/post and actual fighting situations is then addressed. A hierarchical AdaBoost classifier is used to demonstrate the ability to classify such situations. It is demonstrated that such an approach can classify 91% of fighting situations correctly.