Enhancing Remote Sensing Object Detection with K-CBST YOLO: Integrating CBAM and Swin-Transformer
Remote Sensing · 07.08.2024 · 16 (16) · 2885
DOI: 10.3390/rs16162885 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 07.08.2024. Verfasst von Aonan Cheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Central Guiding Local Technology Development.
Abstract (Originalsprache)
Object detection via remote sensing encounters significant challenges due to factors such as small target sizes, uneven target distribution, and complex backgrounds. This paper introduces the K-CBST YOLO algorithm, which is designed to address these challenges. It features a novel architecture that integrates the Convolutional Block Attention Module (CBAM) and Swin-Transformer to enhance global semantic understanding of feature maps and maximize the utilization of contextual information. Such integration significantly improves the accuracy with which small targets are detected against complex backgrounds. Additionally, we propose an improved detection network that combines the improved K-Means algorithm with a smooth Non-Maximum Suppression (NMS) algorithm. This network employs an adaptive dynamic K-Means clustering algorithm to pinpoint target areas of concentration in remote sensing images that feature varied distributions and uses a smooth NMS algorithm to suppress the confidence of overlapping candidate boxes, thereby minimizing their interference with subsequent detection results. The enhanced algorithm substantially bolsters the model’s robustness in handling multi-scale target distributions, preserves more potentially valid information, and diminishes the likelihood of missed detections. This study involved experiments performed on the publicly available DIOR remote sensing image dataset and the DOTA aerial image dataset. Our experimental results demonstrate that, compared with other advanced detection algorithms, K-CBST YOLO outperforms all its counterparts in handling both datasets. It achieved a 68.3% mean Average Precision (mAP) on the DIOR dataset and a 78.4% mAP on the DOTA dataset.
Förderung
- National Key Research and Development Program of China
- Central Guiding Local Technology Development
Zitieren
APA
Cheng, A., Xiao, J., Li, Y., Sun, Y., Ren, Y., & Liu, J. (2024). Enhancing Remote Sensing Object Detection with K-CBST YOLO: Integrating CBAM and Swin-Transformer. Remote Sensing, 16(16), 2885. https://doi.org/10.3390/rs16162885
Vancouver
Cheng A, Xiao J, Li Y, Sun Y, Ren Y, Liu J. Enhancing Remote Sensing Object Detection with K-CBST YOLO: Integrating CBAM and Swin-Transformer. Remote Sensing. 2024;16(16):2885. doi:10.3390/rs16162885
BibTeX
@article{Cheng2024,
author = {Cheng, Aonan and Xiao, Jincheng and Li, Yingcheng and Sun, Yiming and Ren, Yafeng and Liu, Jianli},
title = {Enhancing Remote Sensing Object Detection with K-CBST YOLO: Integrating CBAM and Swin-Transformer},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {16},
pages = {2885},
doi = {10.3390/rs16162885}
}
EUVIMED