Multi-camera detection association for 3D localisation

Jiali Shen, Paul Miller, Huiyu Zhou, Michael Loughlin

Abstract: A multi-camera system is described for 3-D localisation of subjects within a confined space. In particular, we present a novel neighbourhood association algorithm to solve the problem of associating detections in multiple camera views with subjects. To evaluate our approach, experiments were conducted using multiple view video sequences of up to four subjects simulating typical passenger behaviour on a bus. ROC curves were generated for three different versions which showed that for smaller values of the neighbourhood radius parameter, the system tended to over-estimate the number of subjects. However, increasing the radius reduced the over-estimation from 60% to 5%.