Detail View

DSAB-FPN: Role-Separated High-Resolution Neck Fusion for UAV Small-Object Detection

Citations

WEB OF SCIENCE

Citations

SCOPUS

Metadata Downloads

DC Field Value Language
dc.contributor.author Ahn, Young-Sun -
dc.contributor.author Lee, Chung-Hee -
dc.contributor.author Yang, Jung-Min -
dc.date.accessioned 2026-11-17T15:40:15Z -
dc.date.available 2026-11-17T15:40:15Z -
dc.date.created 2026-11-09 -
dc.date.issued 2026-11 -
dc.identifier.issn 2169-3536 -
dc.identifier.uri https://scholar.dgist.ac.kr/handle/20.500.11750/61180 -
dc.description.abstract Small-object detection in unmanned aerial vehicle (UAV) imagery remains challenging because targets occupy few pixels and often appear in dense, occluded, and cluttered scenes. Adding a stride-4 P2 detection level preserves spatial detail, but a uniform fusion rule along the top–down path does not account for differences in source relationships. This paper proposes the Detail–Semantic Aggregation Bridge Feature Pyramid Network (DSAB-FPN), a compact high-resolution neck for YOLOv8n-P2 that assigns fusion mechanisms according to node role. Detail–Semantic Fusion (DSFuse) uses fixed priors selected for each node when fusing adjacent sources, whereas the Detail–Semantic Bridge (DSB) adaptively balances the sources at the intermediate bridge. Controlled experiments on VisDrone2019-DET show consistent improvements in both overall and small-object detection accuracy. DSAB-FPN achieves an average precision (AP) of 0.2392, improving the direct YOLOv8n-P2 baseline by 0.0199 and standard YOLOv8n by 0.0446. Component ablations support complementary roles for the two fusion mechanisms, and independent evaluation on Berkeley DeepDrive 100K (BDD100K) shows the same improvement trend under a different scene distribution. The final model contains 3.0864 million parameters, requires 14.23 billion floating-point operations, and reaches 121.52 frames/s during TensorRT measurements of network execution on a Jetson Orin Nano Super in its maximum performance mode. These results indicate that role-separated fusion improves small-object detection while quantifying the balance between accuracy and throughput on an edge device. -
dc.publisher Institute of Electrical and Electronics Engineers Inc. -
dc.title DSAB-FPN: Role-Separated High-Resolution Neck Fusion for UAV Small-Object Detection -
dc.type Article -
dc.identifier.doi 10.1109/access.2026.3748090 -
dc.identifier.scopusid 2-s2.0-105055109308 -
dc.identifier.bibliographicCitation IEEE Access, v.14, pp.168985 - 168997 -
dc.description.isOpenAccess FALSE -
dc.subject.keywordAuthor feature pyramid network -
dc.subject.keywordAuthor high-resolution feature fusion -
dc.subject.keywordAuthor small-object detection -
dc.subject.keywordAuthor unmanned aerial vehicle -
dc.subject.keywordAuthor VisDrone2019-DET -
dc.subject.keywordAuthor YOLOv8n -
dc.citation.endPage 168997 -
dc.citation.startPage 168985 -
dc.citation.title IEEE Access -
dc.citation.volume 14 -
dc.description.journalRegisteredClass scie -
dc.description.journalRegisteredClass scopus -
dc.type.docType Article -
Show Simple Item Record

File Downloads

  • There are no files associated with this item.

공유

qrcode
공유하기

Related Researcher

이충희
Lee, Chung-Hee이충희

Division of AI, Big data and Block chain

read more

Total Views & Downloads

???jsp.display-item.statistics.view???: , ???jsp.display-item.statistics.download???: