Video Detection and Fusion Tracking for the Targets in Traffic Scenario

In smart transportation systems, obtaining timely and accurate information about the location, speed, category, and shape of traffic targets requires more than what a single sensor can offer. This shortfall has prompted increased attention and rapid development of fusion systems centered around rada...

Full description

Saved in:
Bibliographic Details
Main Authors: Pan Li, Jianing Zhang, Chengxi Han, Luping Xu, Baoguo Feng, Yongjun Zhou, Sen Zhang, Bo Zhang
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/jece/5279061
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846108181280849920
author Pan Li
Jianing Zhang
Chengxi Han
Luping Xu
Baoguo Feng
Yongjun Zhou
Sen Zhang
Bo Zhang
author_facet Pan Li
Jianing Zhang
Chengxi Han
Luping Xu
Baoguo Feng
Yongjun Zhou
Sen Zhang
Bo Zhang
author_sort Pan Li
collection DOAJ
description In smart transportation systems, obtaining timely and accurate information about the location, speed, category, and shape of traffic targets requires more than what a single sensor can offer. This shortfall has prompted increased attention and rapid development of fusion systems centered around radar and video. Radar, while effective at measuring speed, often faces issues such as false tracks, redundant tracks, and low visibility in tracking traffic targets. On the other hand, video provides high visualization but struggles with problems such as target adhesion, low detection confidence, and difficulty in speed measurement. The complementary nature of these technologies underscores the importance of fusion systems in addressing the limitations of individual sensors to improve the accuracy and reliability of smart transportation systems. This paper introduces a fusion tracking method that combines radar and video data for tracking traffic targets. By leveraging the target’s morphological information at various pixel positions, this method supplements the radar data, thereby enhancing the accuracy of data association. The experimental results demonstrate that the association algorithm for optimal data fusion proposed in this paper improves performance by 3.86% and 2.13% compared with the traditional fusion method and the IOU matching fusion, respectively. In addition, it shows greater resilience to complex environments.
format Article
id doaj-art-ee28b76c1109498cb2110d1bfe7d533c
institution Kabale University
issn 2090-0155
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-ee28b76c1109498cb2110d1bfe7d533c2024-12-26T00:00:03ZengWileyJournal of Electrical and Computer Engineering2090-01552024-01-01202410.1155/jece/5279061Video Detection and Fusion Tracking for the Targets in Traffic ScenarioPan Li0Jianing Zhang1Chengxi Han2Luping Xu3Baoguo Feng4Yongjun Zhou5Sen Zhang6Bo Zhang7School of Aerospace Science and TechnologySchool of Aerospace Science and TechnologySchool of Aerospace Science and TechnologySchool of Aerospace Science and TechnologyHebei Deguanlong Technology Co. LtdScience and Technology on Near-Surface Detection LaboratorySchool of Aerospace Science and TechnologySchool of Aerospace Science and TechnologyIn smart transportation systems, obtaining timely and accurate information about the location, speed, category, and shape of traffic targets requires more than what a single sensor can offer. This shortfall has prompted increased attention and rapid development of fusion systems centered around radar and video. Radar, while effective at measuring speed, often faces issues such as false tracks, redundant tracks, and low visibility in tracking traffic targets. On the other hand, video provides high visualization but struggles with problems such as target adhesion, low detection confidence, and difficulty in speed measurement. The complementary nature of these technologies underscores the importance of fusion systems in addressing the limitations of individual sensors to improve the accuracy and reliability of smart transportation systems. This paper introduces a fusion tracking method that combines radar and video data for tracking traffic targets. By leveraging the target’s morphological information at various pixel positions, this method supplements the radar data, thereby enhancing the accuracy of data association. The experimental results demonstrate that the association algorithm for optimal data fusion proposed in this paper improves performance by 3.86% and 2.13% compared with the traditional fusion method and the IOU matching fusion, respectively. In addition, it shows greater resilience to complex environments.http://dx.doi.org/10.1155/jece/5279061
spellingShingle Pan Li
Jianing Zhang
Chengxi Han
Luping Xu
Baoguo Feng
Yongjun Zhou
Sen Zhang
Bo Zhang
Video Detection and Fusion Tracking for the Targets in Traffic Scenario
Journal of Electrical and Computer Engineering
title Video Detection and Fusion Tracking for the Targets in Traffic Scenario
title_full Video Detection and Fusion Tracking for the Targets in Traffic Scenario
title_fullStr Video Detection and Fusion Tracking for the Targets in Traffic Scenario
title_full_unstemmed Video Detection and Fusion Tracking for the Targets in Traffic Scenario
title_short Video Detection and Fusion Tracking for the Targets in Traffic Scenario
title_sort video detection and fusion tracking for the targets in traffic scenario
url http://dx.doi.org/10.1155/jece/5279061
work_keys_str_mv AT panli videodetectionandfusiontrackingforthetargetsintrafficscenario
AT jianingzhang videodetectionandfusiontrackingforthetargetsintrafficscenario
AT chengxihan videodetectionandfusiontrackingforthetargetsintrafficscenario
AT lupingxu videodetectionandfusiontrackingforthetargetsintrafficscenario
AT baoguofeng videodetectionandfusiontrackingforthetargetsintrafficscenario
AT yongjunzhou videodetectionandfusiontrackingforthetargetsintrafficscenario
AT senzhang videodetectionandfusiontrackingforthetargetsintrafficscenario
AT bozhang videodetectionandfusiontrackingforthetargetsintrafficscenario