Multi-object tracking using hybrid observation in PHD filter

In this paper, we propose a novel multi-object tracking method to track unknown number of objects with a single camera system. We design the tracking method via probability hypothesis density (PHD) filtering which considers multiple object states and their observations as random finite sets (RFSs)....

Full description

Bibliographic Details
Main Authors: Yoon, J., Yoon, K., Kim, Du Yong
Format: Conference Paper
Published: 2013
Online Access:http://hdl.handle.net/20.500.11937/55155
_version_ 1848759549158227968
author Yoon, J.
Yoon, K.
Kim, Du Yong
author_facet Yoon, J.
Yoon, K.
Kim, Du Yong
author_sort Yoon, J.
building Curtin Institutional Repository
collection Online Access
description In this paper, we propose a novel multi-object tracking method to track unknown number of objects with a single camera system. We design the tracking method via probability hypothesis density (PHD) filtering which considers multiple object states and their observations as random finite sets (RFSs). The PHD filter is capable of rejecting clutters, handling object appearances and disappearances, and estimating the trajectories of multiple objects in a unified framework. Although the PHD filter is robust to cluttered environment, it is vulnerable to missed detections. For this reason, we include local observations in an RFS of observation model. Local observations are locally generated near the individual tracks by using on-line trained local detector. The main purpose of the local observation is to handle the missed detections and to provide identity (label information) to each object in filtering procedure. The experimental results show that the proposed method robustly tracks multiple objects under practical situations. © 2013 IEEE.
first_indexed 2025-11-14T10:01:39Z
format Conference Paper
id curtin-20.500.11937-55155
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:01:39Z
publishDate 2013
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-551552017-09-13T16:11:01Z Multi-object tracking using hybrid observation in PHD filter Yoon, J. Yoon, K. Kim, Du Yong In this paper, we propose a novel multi-object tracking method to track unknown number of objects with a single camera system. We design the tracking method via probability hypothesis density (PHD) filtering which considers multiple object states and their observations as random finite sets (RFSs). The PHD filter is capable of rejecting clutters, handling object appearances and disappearances, and estimating the trajectories of multiple objects in a unified framework. Although the PHD filter is robust to cluttered environment, it is vulnerable to missed detections. For this reason, we include local observations in an RFS of observation model. Local observations are locally generated near the individual tracks by using on-line trained local detector. The main purpose of the local observation is to handle the missed detections and to provide identity (label information) to each object in filtering procedure. The experimental results show that the proposed method robustly tracks multiple objects under practical situations. © 2013 IEEE. 2013 Conference Paper http://hdl.handle.net/20.500.11937/55155 10.1109/ICIP.2013.6738801 restricted
spellingShingle Yoon, J.
Yoon, K.
Kim, Du Yong
Multi-object tracking using hybrid observation in PHD filter
title Multi-object tracking using hybrid observation in PHD filter
title_full Multi-object tracking using hybrid observation in PHD filter
title_fullStr Multi-object tracking using hybrid observation in PHD filter
title_full_unstemmed Multi-object tracking using hybrid observation in PHD filter
title_short Multi-object tracking using hybrid observation in PHD filter
title_sort multi-object tracking using hybrid observation in phd filter
url http://hdl.handle.net/20.500.11937/55155