A labeled random finite set online multi-object tracker for video data

This paper proposes an online multi-object tracking algorithm for image observations using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, handling of false positives, false negatives and occlusion into a single recursion. This is achieved by modeling t...

Full description

Bibliographic Details
Main Authors: Kim, Du Yong, Vo, Ba-Ngu, Vo, Ba Tuong, Jeon, M.
Format: Journal Article
Published: Elsevier 2019
Online Access:http://purl.org/au-research/grants/arc/DP160104662
http://hdl.handle.net/20.500.11937/74333
_version_ 1848763245699006464
author Kim, Du Yong
Vo, Ba-Ngu
Vo, Ba Tuong
Jeon, M.
author_facet Kim, Du Yong
Vo, Ba-Ngu
Vo, Ba Tuong
Jeon, M.
author_sort Kim, Du Yong
building Curtin Institutional Repository
collection Online Access
description This paper proposes an online multi-object tracking algorithm for image observations using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, handling of false positives, false negatives and occlusion into a single recursion. This is achieved by modeling the multi-object state as labeled random finite set and using the Bayes recursion to propagate the multi-object filtering density forward in time. The proposed filter updates tracks with detections but switches to image data when detection loss occurs, thereby exploiting the efficiency of detection data and the accuracy of image data. Furthermore the labeled random finite set framework enables the incorporation of prior knowledge that detection loss in the middle of the scene are likely to be due to occlusions. Such prior knowledge can be exploited to improve occlusion handling, especially long occlusions that can lead to premature track termination in on-line multi-object tracking. Tracking performance is compared to state-of-the-art algorithms on synthetic data and well-known benchmark video datasets.
first_indexed 2025-11-14T11:00:24Z
format Journal Article
id curtin-20.500.11937-74333
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:00:24Z
publishDate 2019
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-743332022-10-27T06:25:37Z A labeled random finite set online multi-object tracker for video data Kim, Du Yong Vo, Ba-Ngu Vo, Ba Tuong Jeon, M. This paper proposes an online multi-object tracking algorithm for image observations using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, handling of false positives, false negatives and occlusion into a single recursion. This is achieved by modeling the multi-object state as labeled random finite set and using the Bayes recursion to propagate the multi-object filtering density forward in time. The proposed filter updates tracks with detections but switches to image data when detection loss occurs, thereby exploiting the efficiency of detection data and the accuracy of image data. Furthermore the labeled random finite set framework enables the incorporation of prior knowledge that detection loss in the middle of the scene are likely to be due to occlusions. Such prior knowledge can be exploited to improve occlusion handling, especially long occlusions that can lead to premature track termination in on-line multi-object tracking. Tracking performance is compared to state-of-the-art algorithms on synthetic data and well-known benchmark video datasets. 2019 Journal Article http://hdl.handle.net/20.500.11937/74333 10.1016/j.patcog.2019.02.004 http://purl.org/au-research/grants/arc/DP160104662 Elsevier restricted
spellingShingle Kim, Du Yong
Vo, Ba-Ngu
Vo, Ba Tuong
Jeon, M.
A labeled random finite set online multi-object tracker for video data
title A labeled random finite set online multi-object tracker for video data
title_full A labeled random finite set online multi-object tracker for video data
title_fullStr A labeled random finite set online multi-object tracker for video data
title_full_unstemmed A labeled random finite set online multi-object tracker for video data
title_short A labeled random finite set online multi-object tracker for video data
title_sort labeled random finite set online multi-object tracker for video data
url http://purl.org/au-research/grants/arc/DP160104662
http://hdl.handle.net/20.500.11937/74333