AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection
文献类型：期刊论文
| 作者 | Huang, Lve1; Yu, Xiaowei1; Yan, Huabiao1; Huang, Libo2; An, Zhulin2; Xu, Yongjun2 |
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2026 |
| 卷号 | 36期号:1页码:63-78 |
| 关键词 | Feature extraction YOLO Head Videos Convolution Accuracy Proposals Hands Fuses Training Aerial image object detection feature extraction asymptotic fusion lightweight model |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2025.3595740 |
| 英文摘要 | Aerial object detection plays a vital role in applications such as natural disaster prevention and urban traffic management, thanks to its ability to handle wide coverage areas and diverse objects. As a leading method for this task, You Only Look Once (YOLO) leverages multi-scale feature extraction to detect objects of various sizes. However, most YOLO-based methods focus on feature extraction and fusion from adjacent scales, neglecting the potential collaboration between non-adjacent scales. This limitation leads to redundant parameters and suboptimal detection performance. To address these issues, this paper proposes AF-YOLO (Asymptotic Feature Extraction and Fusion YOLO), a novel approach tailored for aerial object detection. AF-YOLO introduces two lightweight modules: SCC2f and PAFFN. SCC2f, an optimized version of cross-stage partial bottleneck with spatial and channel reconstruction convolution layers, reduces redundancy and enables efficient multi-scale feature extraction. PAFFN, a parallel asymptotic feature fusion network, facilitates enhanced interaction and fusion of non-adjacent scale features. Additionally, AF-YOLO incorporates a P2 layer to improve small object detection and removes YOLO's P5 layer for a more lightweight design, specifically optimized for aerial detection tasks. Experimental results demonstrate AF-YOLO's significant improvements across multiple benchmarks: on the VisDrone dataset, it achieves a 6.1% higher mAP(0.5) compared to recent baselines while using only 41.8% of their parameters; on the DIOR dataset, it shows a 3.3% accuracy improvement over YOLOv8. These quantitative results are further supported by its superior performance on the DOTA and FAIR1M datasets, with additional validation on HazyDet confirming its robustness in adverse weather conditions. Collectively, these achievements highlight AF-YOLO's exceptional generalization capability and efficient lightweight design, establishing a new state-of-the-art for aerial object detection systems. |
| 资助项目 | Natural Science Foundation of Jiangxi Province[20224BAB202036] ; Key Research Project of Science and Technology by Jiangxi Provincial Department of Education[GJJ2200805] ; National Natural Science Foundation of China[62476264] ; Beijing Natural Science Foundation[4244098] |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001673821800029 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42865]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Huang, Libo |
| 作者单位 | 1.Jiangxi Univ Sci & Technol, Jiangxi Prov Key Lab Multidimens Intelligent Perce, Ganzhou 341000, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Huang, Lve,Yu, Xiaowei,Yan, Huabiao,et al. AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2026,36(1):63-78. |
| APA | Huang, Lve,Yu, Xiaowei,Yan, Huabiao,Huang, Libo,An, Zhulin,&Xu, Yongjun.(2026).AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,36(1),63-78. |
| MLA | Huang, Lve,et al."AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 36.1(2026):63-78. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。