Online Multi-Object Tracking With Visual and Radar Features
Multi-object tracking (MOT) constructs multiple object trajectories by associating detections between consecutive frames while maintaining object identities. In many autonomous systems equipped with a camera and a radar, an amplitude and visual features can be measured. Therefore, our goal is to sol...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9091141/ |
id |
doaj-7d926228cef34fdaa6a3baf0059b84fa |
---|---|
record_format |
Article |
spelling |
doaj-7d926228cef34fdaa6a3baf0059b84fa2021-03-30T01:55:50ZengIEEEIEEE Access2169-35362020-01-018903249033910.1109/ACCESS.2020.29940009091141Online Multi-Object Tracking With Visual and Radar FeaturesSeung-Hwan Bae0https://orcid.org/0000-0002-9478-2706Department of Computer Engineering, Inha University, Incheon, South KoreaMulti-object tracking (MOT) constructs multiple object trajectories by associating detections between consecutive frames while maintaining object identities. In many autonomous systems equipped with a camera and a radar, an amplitude and visual features can be measured. Therefore, our goal is to solve a MOT problem by associating detections with both features. To achieve it, we propose a unified MOT framework based on object model learning and confidence-based association. For improving discriminability between different objects, we present a method to learn several visual and amplitude object models during online tracking. By applying the learned object models for the affinity evaluation, we improve the confidence-based association further. In addition, we present a practical track management method to initialize and terminate tracks, and eliminate duplicated false tracks. We implement several MOT systems with different object model learning and association methods, and compare our system with them on challenging visual MOT datasets. We further compare our method with the recent deep appearance learning methods. These comparisons verify that our method can achieve the competitive tracking accuracy while maintaining a low MOT complexity.https://ieeexplore.ieee.org/document/9091141/Object trackingsensor fusionvisual/amplitude featuresobject model learningaffinity evaluationconfidence-based data association |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Seung-Hwan Bae |
spellingShingle |
Seung-Hwan Bae Online Multi-Object Tracking With Visual and Radar Features IEEE Access Object tracking sensor fusion visual/amplitude features object model learning affinity evaluation confidence-based data association |
author_facet |
Seung-Hwan Bae |
author_sort |
Seung-Hwan Bae |
title |
Online Multi-Object Tracking With Visual and Radar Features |
title_short |
Online Multi-Object Tracking With Visual and Radar Features |
title_full |
Online Multi-Object Tracking With Visual and Radar Features |
title_fullStr |
Online Multi-Object Tracking With Visual and Radar Features |
title_full_unstemmed |
Online Multi-Object Tracking With Visual and Radar Features |
title_sort |
online multi-object tracking with visual and radar features |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Multi-object tracking (MOT) constructs multiple object trajectories by associating detections between consecutive frames while maintaining object identities. In many autonomous systems equipped with a camera and a radar, an amplitude and visual features can be measured. Therefore, our goal is to solve a MOT problem by associating detections with both features. To achieve it, we propose a unified MOT framework based on object model learning and confidence-based association. For improving discriminability between different objects, we present a method to learn several visual and amplitude object models during online tracking. By applying the learned object models for the affinity evaluation, we improve the confidence-based association further. In addition, we present a practical track management method to initialize and terminate tracks, and eliminate duplicated false tracks. We implement several MOT systems with different object model learning and association methods, and compare our system with them on challenging visual MOT datasets. We further compare our method with the recent deep appearance learning methods. These comparisons verify that our method can achieve the competitive tracking accuracy while maintaining a low MOT complexity. |
topic |
Object tracking sensor fusion visual/amplitude features object model learning affinity evaluation confidence-based data association |
url |
https://ieeexplore.ieee.org/document/9091141/ |
work_keys_str_mv |
AT seunghwanbae onlinemultiobjecttrackingwithvisualandradarfeatures |
_version_ |
1724186122255335424 |