PASR-YOLO: a small object detection algorithm for UAV based on cross-scale feature aggregation

Journal on Advances in Signal Processing

卷:2026

Research

Tien-Wen Sung¹  Yujie Lai¹  Chao-Yang Lee²  Shaopei Wen³ 

[1] Fujian Provincial Key Laboratory of Big Data Mining and Applications, Fujian University of Technology, Xuefu South Road, 350118, Fuzhou, Fujian, China

[2] Fujian Polytechnic of Information Technology, Fufei South Road, 350003, Fuzhou, Fujian, China

[3] Department of Computer Science and Information Engineering, National Yunlin University of Science and Technology, University Road, 640301, Douliu, Yunlin, Taiwan

关键词: UAV detection;    Small target;    Feature extraction;    Lightweight;   

DOI  :  10.1186/s13634-026-01353-9

 received in 2026-01-17, accepted in 2026-06-23,  发布年份 2026

来源: Springer

【 摘 要 】

In recent years, the application of Unmanned Aerial Vehicle (UAV) in production activities involving outdoor operations has gradually become widespread and routine. However, challenges such as the wide size variation of small objects, frequent occlusions, and complex backgrounds have emerged as key difficulties in UAV aerial image object detection. This paper proposes PASR-YOLO, an enhanced YOLO11 algorithm optimized for small objects. To address the issue of insufficient representation of small objects in the detection layer, the High Resolution Detail Injection Unit (HDI) is introduced. Building upon the addition of a high resolution detection branch, it innovatively extracts small object features from low level layers and injects them into higher layers. Furthermore, incorporating the Cross Stage Partial network (CSP) based on three different size branch representations, it aggregates multi-scale and fine-grained information, achieving a lightweight and high precision small object feature pyramid. To further reduce the number of parameters, a low-redundancy mapping named n-Scale Recursive Split-Enhance Fusion Block (NSSE) is proposed that accommodates both large and small models, balancing compactness with equivalent feature extraction and gradient flow capabilities. On the VisDrone dataset, PASR-YOLO achieves 6.6% and 4.5% improvements over the baseline model in mAP 0.5 and mAP 0.5–0.95, respectively.

【 授权许可】

CC BY-NC-ND   
© The Author(s) 2026

【 图 表 】

Fig. 3

1

Fig. 1

Fig. 9

Fig. 1