Paper
9 October 2023 Improved algorithm for small target detection in remote sensing images based on YOLOv5s
Chaoyue Sun, Yajun Chen, Xiangjun Hou
Author Affiliations +
Proceedings Volume 12791, Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023); 127910E (2023) https://doi.org/10.1117/12.3004660
Event: Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023), 2023, Qingdao, SD, China
Abstract
In response to the challenges of small targets and complex backgrounds in remote sensing image detection, this paper proposes an improved algorithm based on Yolov5s, named Yolov5s-RSD. The algorithm replaces the original downsampling method with SPD-Conv to reduce information loss during downsampling, adds a detection head for small targets to fully utilize their features, and introduces Biformer attention to address complex background issues. Testing on the VisDrone datasets shows that the improved algorithm achieves a 10.0% increase in map@0.5 and a 7.0% increase in map@0.5:0.95 compared to the original algorithm.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Chaoyue Sun, Yajun Chen, and Xiangjun Hou "Improved algorithm for small target detection in remote sensing images based on YOLOv5s", Proc. SPIE 12791, Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023), 127910E (9 October 2023); https://doi.org/10.1117/12.3004660
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Object detection

Remote sensing

Small targets

Target detection

Head

Algorithm development

Back to Top