Efficient-Lightweight YOLO: Improving Small Object Detection in YOLO for Aerial Images
Sensors · 15.07.2023 · 23 (14) · 6423
DOI: 10.3390/s23146423 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 15.07.2023. Verfasst von Mengzi Hu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Xinjiang University, Urumqi 830091, China. Die Arbeit wurde bisher 89-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key R&D Projects in Xinjiang Uygur Autonomous Region, Natural Science Foundation of Xinjiang Uygur Autonomous Region of China.
Abstract (Originalsprache)
The most significant technical challenges of current aerial image object-detection tasks are the extremely low accuracy for detecting small objects that are densely distributed within a scene and the lack of semantic information. Moreover, existing detectors with large parameter scales are unsuitable for aerial image object-detection scenarios oriented toward low-end GPUs. To address this technical challenge, we propose efficient-lightweight You Only Look Once (EL-YOLO), an innovative model that overcomes the limitations of existing detectors and low-end GPU orientation. EL-YOLO surpasses the baseline models in three key areas. Firstly, we design and scrutinize three model architectures to intensify the model’s focus on small objects and identify the most effective network structure. Secondly, we design efficient spatial pyramid pooling (ESPP) to augment the representation of small-object features in aerial images. Lastly, we introduce the alpha-complete intersection over union (α-CIoU) loss function to tackle the imbalance between positive and negative samples in aerial images. Our proposed EL-YOLO method demonstrates a strong generalization and robustness for the small-object detection problem in aerial images. The experimental results show that, with the model parameters maintained below 10 M while the input image size was unified at 640 × 640 pixels, the APS of the EL-YOLOv5 reached 10.8% and 10.7% and enhanced the APs by 1.9% and 2.2% compared to YOLOv5 on two challenging aerial image datasets, DIOR and VisDrone, respectively.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Software, Xinjiang University, Urumqi 830091, China.
- College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
Förderung
- National Natural Science Foundation of China
- Key R&D Projects in Xinjiang Uygur Autonomous Region
- Natural Science Foundation of Xinjiang Uygur Autonomous Region of China
- Xinjiang University doctoral postgraduate innovation project
- Key R&D projects in the Xinjiang Uygur Autonomous Region
- Natural Science Foundation of the Xinjiang Uygur Autonomous Region of China
Zitieren
APA
Hu, M., Li, Z., Yu, J., Wan, X., Tan, H., & Lin, Z. (2023). Efficient-Lightweight YOLO: Improving Small Object Detection in YOLO for Aerial Images. Sensors, 23(14), 6423. https://doi.org/10.3390/s23146423
Vancouver
Hu M, Li Z, Yu J, Wan X, Tan H, Lin Z. Efficient-Lightweight YOLO: Improving Small Object Detection in YOLO for Aerial Images. Sensors. 2023;23(14):6423. doi:10.3390/s23146423
BibTeX
@article{Hu2023,
author = {Hu, Mengzi and Li, Ziyang and Yu, Jiong and Wan, Xueqiang and Tan, Haotian and Lin, Zeyu},
title = {Efficient-Lightweight YOLO: Improving Small Object Detection in YOLO for Aerial Images},
journal = {Sensors},
year = {2023},
volume = {23},
number = {14},
pages = {6423},
doi = {10.3390/s23146423}
}
EUVIMED