Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT

In this paper, we address the issues of insufficient accuracy and frequent identity switching in the multi-target tracking algorithm DeepSORT by proposing two improvement strategies. First, we optimize the appearance feature extraction process by training a lightweight appearance extraction network...

Full description

Saved in:
Bibliographic Details
Main Authors: Dudu Guo, Zhuzhou Li, Hongbo Shuai, Fei Zhou
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/21/7014
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173134132084736
author Dudu Guo
Zhuzhou Li
Hongbo Shuai
Fei Zhou
author_facet Dudu Guo
Zhuzhou Li
Hongbo Shuai
Fei Zhou
author_sort Dudu Guo
collection DOAJ
description In this paper, we address the issues of insufficient accuracy and frequent identity switching in the multi-target tracking algorithm DeepSORT by proposing two improvement strategies. First, we optimize the appearance feature extraction process by training a lightweight appearance extraction network (OSNet) on a vehicle re-identification dataset. This makes the appearance features better suited for the vehicle tracking model required in our paper. Second, we improve the metric of motion features by using the original IOU distance metric or GIOU metrics. The optimized tracking algorithm using GIOU achieves effective improvements in tracking precision and accuracy. The experimental results show that the improved vehicle tracking models MOTA and IDF1 are enhanced by 4.6% and 5.9%, respectively. This allows for the stable tracking of vehicles and reduces the occurrence of identity switching phenomenon to a certain extent.
format Article
id doaj-art-df5f649afb494d808033df0b6b14c9b8
institution Kabale University
issn 1424-8220
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-df5f649afb494d808033df0b6b14c9b82024-11-08T14:41:52ZengMDPI AGSensors1424-82202024-10-012421701410.3390/s24217014Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORTDudu Guo0Zhuzhou Li1Hongbo Shuai2Fei Zhou3The School of Transportation Engineering, Xinjiang University, Urumqi 830017, ChinaThe School of Intelligent Manufacturing for Modern Industry, Xinjiang University, Urumqi 830017, ChinaThe School of Intelligent Manufacturing for Modern Industry, Xinjiang University, Urumqi 830017, ChinaThe School of Intelligent Manufacturing for Modern Industry, Xinjiang University, Urumqi 830017, ChinaIn this paper, we address the issues of insufficient accuracy and frequent identity switching in the multi-target tracking algorithm DeepSORT by proposing two improvement strategies. First, we optimize the appearance feature extraction process by training a lightweight appearance extraction network (OSNet) on a vehicle re-identification dataset. This makes the appearance features better suited for the vehicle tracking model required in our paper. Second, we improve the metric of motion features by using the original IOU distance metric or GIOU metrics. The optimized tracking algorithm using GIOU achieves effective improvements in tracking precision and accuracy. The experimental results show that the improved vehicle tracking models MOTA and IDF1 are enhanced by 4.6% and 5.9%, respectively. This allows for the stable tracking of vehicles and reduces the occurrence of identity switching phenomenon to a certain extent.https://www.mdpi.com/1424-8220/24/21/7014optical satellite imagesvehicle detectionYOLOXscale expansionattention mechanismBFPnet
spellingShingle Dudu Guo
Zhuzhou Li
Hongbo Shuai
Fei Zhou
Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT
Sensors
optical satellite images
vehicle detection
YOLOX
scale expansion
attention mechanism
BFPnet
title Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT
title_full Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT
title_fullStr Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT
title_full_unstemmed Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT
title_short Multi-Target Vehicle Tracking Algorithm Based on Improved DeepSORT
title_sort multi target vehicle tracking algorithm based on improved deepsort
topic optical satellite images
vehicle detection
YOLOX
scale expansion
attention mechanism
BFPnet
url https://www.mdpi.com/1424-8220/24/21/7014
work_keys_str_mv AT duduguo multitargetvehicletrackingalgorithmbasedonimproveddeepsort
AT zhuzhouli multitargetvehicletrackingalgorithmbasedonimproveddeepsort
AT hongboshuai multitargetvehicletrackingalgorithmbasedonimproveddeepsort
AT feizhou multitargetvehicletrackingalgorithmbasedonimproveddeepsort