A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection
Small target detection is an important research direction in computer vision, widely applied in scenarios such as drone monitoring, remote sensing image analysis, and autonomous driving. However, as small targets occupy fewer pixels, contain limited feature information, and often appear in complex b...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11005582/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849472000171442176 |
|---|---|
| author | Xu Yan Junliang Du Xuan Li Xiaoye Wang Xiaoxuan Sun Pochun Li Hongye Zheng |
| author_facet | Xu Yan Junliang Du Xuan Li Xiaoye Wang Xiaoxuan Sun Pochun Li Hongye Zheng |
| author_sort | Xu Yan |
| collection | DOAJ |
| description | Small target detection is an important research direction in computer vision, widely applied in scenarios such as drone monitoring, remote sensing image analysis, and autonomous driving. However, as small targets occupy fewer pixels, contain limited feature information, and often appear in complex backgrounds, existing detection algorithms face shortcomings in accuracy and robustness. To address this, this paper proposes a novel small target detection algorithm that integrates hierarchical feature fusion with a spatial dynamic collaboration mechanism. The hierarchical feature fusion module (HFA) effectively combines shallow detail features with deep semantic features, greatly enhancing the feature representation capability for small targets. Meanwhile, the dynamic collaboration mechanism (DCCA) dynamically adjusts feature fusion weights and detection strategies based on target scale and density distribution, thereby further improving detection accuracy and robustness. Extensive experiments are conducted on datasets such as VisDrone, TinyPerson, and NWPU VHR-10. Results demonstrate that, compared to state-of-the-art models like YOLOv8 and YOLOv10, the proposed algorithm achieves significant improvements in precision, recall, and mAP, with mAP increasing by 2.1% to 3.2% and mAP-95 by 1.2% to 1.8%. Ablation studies further validate the complementarity of HFA and DCCA in optimizing model performance, confirming the algorithm’s superiority and robustness in complex scenarios. This research provides a novel technical route for small target detection and offers valuable references for practical applications. |
| format | Article |
| id | doaj-art-b24164f5e5294fe6b051beb562fda7fb |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b24164f5e5294fe6b051beb562fda7fb2025-08-20T03:24:39ZengIEEEIEEE Access2169-35362025-01-0113929539296410.1109/ACCESS.2025.357066911005582A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target DetectionXu Yan0https://orcid.org/0009-0004-6587-1410Junliang Du1https://orcid.org/0000-0002-4306-6339Xuan Li2https://orcid.org/0009-0003-0185-1456Xiaoye Wang3https://orcid.org/0009-0007-0492-5341Xiaoxuan Sun4Pochun Li5https://orcid.org/0009-0003-6462-842XHongye Zheng6https://orcid.org/0009-0004-8337-8857Trine University, Phoenix, AZ, USAShanghai Jiao Tong University, Shanghai, ChinaColumbia University, New York, NY, USAWestern University, London, ON, CanadaUniversity of Southern California, Los Angeles, CA, USANortheastern University, Boston, MA, USAThe Chinese University of Hong Kong, Hong Kong, ChinaSmall target detection is an important research direction in computer vision, widely applied in scenarios such as drone monitoring, remote sensing image analysis, and autonomous driving. However, as small targets occupy fewer pixels, contain limited feature information, and often appear in complex backgrounds, existing detection algorithms face shortcomings in accuracy and robustness. To address this, this paper proposes a novel small target detection algorithm that integrates hierarchical feature fusion with a spatial dynamic collaboration mechanism. The hierarchical feature fusion module (HFA) effectively combines shallow detail features with deep semantic features, greatly enhancing the feature representation capability for small targets. Meanwhile, the dynamic collaboration mechanism (DCCA) dynamically adjusts feature fusion weights and detection strategies based on target scale and density distribution, thereby further improving detection accuracy and robustness. Extensive experiments are conducted on datasets such as VisDrone, TinyPerson, and NWPU VHR-10. Results demonstrate that, compared to state-of-the-art models like YOLOv8 and YOLOv10, the proposed algorithm achieves significant improvements in precision, recall, and mAP, with mAP increasing by 2.1% to 3.2% and mAP-95 by 1.2% to 1.8%. Ablation studies further validate the complementarity of HFA and DCCA in optimizing model performance, confirming the algorithm’s superiority and robustness in complex scenarios. This research provides a novel technical route for small target detection and offers valuable references for practical applications.https://ieeexplore.ieee.org/document/11005582/Small target detectionhierarchical feature fusiondynamic coordination mechanismYOLOv10 |
| spellingShingle | Xu Yan Junliang Du Xuan Li Xiaoye Wang Xiaoxuan Sun Pochun Li Hongye Zheng A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection IEEE Access Small target detection hierarchical feature fusion dynamic coordination mechanism YOLOv10 |
| title | A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection |
| title_full | A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection |
| title_fullStr | A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection |
| title_full_unstemmed | A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection |
| title_short | A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection |
| title_sort | hierarchical feature fusion and dynamic collaboration framework for robust small target detection |
| topic | Small target detection hierarchical feature fusion dynamic coordination mechanism YOLOv10 |
| url | https://ieeexplore.ieee.org/document/11005582/ |
| work_keys_str_mv | AT xuyan ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT junliangdu ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xuanli ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xiaoyewang ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xiaoxuansun ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT pochunli ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT hongyezheng ahierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xuyan hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT junliangdu hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xuanli hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xiaoyewang hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT xiaoxuansun hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT pochunli hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection AT hongyezheng hierarchicalfeaturefusionanddynamiccollaborationframeworkforrobustsmalltargetdetection |