SP-YOLOv8s: An Improved YOLOv8s Model for Remote Sensing Image Tiny Object Detection
Applied Sciences · 13.07.2023 · 13 (14) · 8161
DOI: 10.3390/app13148161 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 13.07.2023. Verfasst von Mingyang Ma und 1 weiteren Autor:innen. Die Arbeit wurde bisher 85-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Department of Jilin Province.
Abstract (Originalsprache)
An improved YOLOv8s-based method is proposed to address the challenge of accurately recognizing tiny objects in remote sensing images during practical human-computer interaction. In detecting tiny targets, the accuracy of YOLOv8s is low because the downsampling module of the original YOLOv8s algorithm causes the network to lose fine-grained feature information, and the neck network feature information needs to be sufficiently fused. In this method, the strided convolution module in YOLOv8s is replaced with the SPD-Conv module. By doing so, the feature map undergoes downsampling while preserving fine-grained feature information, thereby improving the learning and expressive capabilities of the network and enhancing recognition accuracy. Meanwhile, the path aggregation network is substituted with the SPANet structure, which facilitates the acquisition of more prosperous gradient paths. This substitution enhances the fusion of feature maps at various scales, reduces model parameters, and further improves detection accuracy. Additionally, it enhances the network’s robustness to complex backgrounds. Experimental verification is conducted on the following two intricate datasets containing tiny objects: AI-TOD and TinyPerson. A comparative analysis with the original YOLOv8s algorithm reveals notable enhancements in recognition accuracy. Specifically, under real-time performance constraints, the proposed method yields a 4.9% and 9.1% improvement in mAP0.5 recognition accuracy for AI-TOD and TinyPerson datasets, respectively. Moreover, the recognition accuracy for mAP0.5:0.95 is enhanced by 3.4% and 3.2% for the same datasets, respectively. The results indicate that the proposed method enables rapid and accurate recognition of tiny objects in complex backgrounds. Furthermore, it demonstrates better recognition precision and stability than other algorithms, such as YOLOv5s and YOLOv8s.
Förderung
- Science and Technology Department of Jilin Province
Zitieren
APA
Ma, M., & Pang, H. (2023). SP-YOLOv8s: An Improved YOLOv8s Model for Remote Sensing Image Tiny Object Detection. Applied Sciences, 13(14), 8161. https://doi.org/10.3390/app13148161
Vancouver
Ma M, Pang H. SP-YOLOv8s: An Improved YOLOv8s Model for Remote Sensing Image Tiny Object Detection. Applied Sciences. 2023;13(14):8161. doi:10.3390/app13148161
BibTeX
@article{Ma2023,
author = {Ma, Mingyang and Pang, Huanli},
title = {SP-YOLOv8s: An Improved YOLOv8s Model for Remote Sensing Image Tiny Object Detection},
journal = {Applied Sciences},
year = {2023},
volume = {13},
number = {14},
pages = {8161},
doi = {10.3390/app13148161}
}
EUVIMED