AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands

This study focuses on tracking cranes and storks to aid in wetland ecological protection. Multi-target tracking of these birds presents challenges such as frequent occlusions, sudden appearances, and disappearances. To tackle these issues, we propose a novel multi-target tracking algorithm, AviaryMO...

Full description

Saved in:
Bibliographic Details
Main Authors: Chang Liu, Xuran Ma, Jiahong Zhou, Nini Sun, Hengming Liu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Marine Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmars.2025.1524134/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849702341721194496
author Chang Liu
Xuran Ma
Jiahong Zhou
Nini Sun
Hengming Liu
author_facet Chang Liu
Xuran Ma
Jiahong Zhou
Nini Sun
Hengming Liu
author_sort Chang Liu
collection DOAJ
description This study focuses on tracking cranes and storks to aid in wetland ecological protection. Multi-target tracking of these birds presents challenges such as frequent occlusions, sudden appearances, and disappearances. To tackle these issues, we propose a novel multi-target tracking algorithm, AviaryMOT, which utilizes a fusion technique that combines shallow and deep features to enhance tracking accuracy and effectiveness. We construct a dataset, BirdTrack, for cranes and storks tracking. In the detecting stage, we proposed Aviary Attention to effectively capture the features of birds, by integrating the Coordinate Attention into the YOLOv8 framework and applying Soft-NMS to improve detection in occluded scenarios. In the tracking stage, the BYTE data association method effectively utilizes similarities between low-score detection boxes and tracking trajectories, enabling the identification of true objects and filtering out background noise. Experimental results show that our method outperforms the state-of-art models, maintaining stable target trajectories while ensuring high-quality detection.
format Article
id doaj-art-f0e1031a035446779a2ffdaec9bdee74
institution DOAJ
issn 2296-7745
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Marine Science
spelling doaj-art-f0e1031a035446779a2ffdaec9bdee742025-08-20T03:17:40ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-06-011210.3389/fmars.2025.15241341524134AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlandsChang Liu0Xuran Ma1Jiahong Zhou2Nini Sun3Hengming Liu4Computer School, Beijing Information Science and Technology University, Beijing, ChinaShandong Changdao National Nature Reserve, Shandong, Yantai, ChinaShandong Changdao National Nature Reserve, Shandong, Yantai, ChinaShandong Changdao National Nature Reserve, Shandong, Yantai, ChinaComputer School, Beijing Information Science and Technology University, Beijing, ChinaThis study focuses on tracking cranes and storks to aid in wetland ecological protection. Multi-target tracking of these birds presents challenges such as frequent occlusions, sudden appearances, and disappearances. To tackle these issues, we propose a novel multi-target tracking algorithm, AviaryMOT, which utilizes a fusion technique that combines shallow and deep features to enhance tracking accuracy and effectiveness. We construct a dataset, BirdTrack, for cranes and storks tracking. In the detecting stage, we proposed Aviary Attention to effectively capture the features of birds, by integrating the Coordinate Attention into the YOLOv8 framework and applying Soft-NMS to improve detection in occluded scenarios. In the tracking stage, the BYTE data association method effectively utilizes similarities between low-score detection boxes and tracking trajectories, enabling the identification of true objects and filtering out background noise. Experimental results show that our method outperforms the state-of-art models, maintaining stable target trajectories while ensuring high-quality detection.https://www.frontiersin.org/articles/10.3389/fmars.2025.1524134/fullmultiple object trackingAviary AttentionYOLOv frameworkByteTrackwetlands protection
spellingShingle Chang Liu
Xuran Ma
Jiahong Zhou
Nini Sun
Hengming Liu
AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands
Frontiers in Marine Science
multiple object tracking
Aviary Attention
YOLOv framework
ByteTrack
wetlands protection
title AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands
title_full AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands
title_fullStr AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands
title_full_unstemmed AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands
title_short AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands
title_sort aviarymot aviary attention based adaptive multi object tracking of cranes and storks in wetlands
topic multiple object tracking
Aviary Attention
YOLOv framework
ByteTrack
wetlands protection
url https://www.frontiersin.org/articles/10.3389/fmars.2025.1524134/full
work_keys_str_mv AT changliu aviarymotaviaryattentionbasedadaptivemultiobjecttrackingofcranesandstorksinwetlands
AT xuranma aviarymotaviaryattentionbasedadaptivemultiobjecttrackingofcranesandstorksinwetlands
AT jiahongzhou aviarymotaviaryattentionbasedadaptivemultiobjecttrackingofcranesandstorksinwetlands
AT ninisun aviarymotaviaryattentionbasedadaptivemultiobjecttrackingofcranesandstorksinwetlands
AT hengmingliu aviarymotaviaryattentionbasedadaptivemultiobjecttrackingofcranesandstorksinwetlands