Multi-camera detection association for 3D localisation

Jiali Shen, Paul Miller, Huiyu Zhou, Michael Loughlin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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%.

Original languageEnglish
Title of host publication2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2011
Pages480-485
Number of pages6
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2011 - Klagenfurt, Austria
Duration: Aug 30 2011Sep 2 2011

Publication series

Name2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2011

Conference

Conference2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2011
Country/TerritoryAustria
CityKlagenfurt
Period08/30/1109/2/11

Fingerprint

Dive into the research topics of 'Multi-camera detection association for 3D localisation'. Together they form a unique fingerprint.

Cite this