Crowd behaviour analysis using histograms of motion direction
Hannah Dee, Alice Caplier · 2010
A practical system for the automated analysis of crowded scenes will have to deal with multiple occlusions and tracking failures, in a context in which the cameras may move at any time to point in any direction, at any level of zoom. This paper presents a prototype component of such a system. Much work in crowd modelling assumes that the camera will be static for extended periods of time and that a model of the scene can therefore be learned; we do not make this assumption and instead build a simple representation of motion patterns that is applicable across different views and which learns motion scale rapidly. Our representation is based upon histograms of motion direction alongside an indication of motion speed. These can be used for detecting frames in which behaviour differs from the training set, and also for localisation of where in the image these anomalous events occur. We evaluate this work against five event-detection scenarios from the public PETS2009 crowd behaviour dataset.