EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SAFF-SSD: Self-Attention Combined Feature Fusion-Based SSD for Small Object Detection in Remote Sensing

Bihan Huo, Chenglong Li, Jianwei Zhang, Yingjian Xue, Zhoujin Lin

Remote Sensing · 09.06.2023 · 15 (12) · 3027

DOI: 10.3390/rs15123027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 09.06.2023. Verfasst von Bihan Huo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 61-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

SSD is a classical single-stage object detection algorithm, which predicts by generating different scales of feature maps on different convolutional layers. However, due to the problems of its insufficient non-linearity and the lack of semantic information in the shallow feature maps, as well as the fact that small objects contain few pixels, the detection accuracy of small objects is significantly worse than that of large- and medium-scale objects. Considering the above problems, we propose a novel object detector, self-attention combined feature fusion-based SSD for small object detection (SAFF-SSD), to boost the precision of small object detection. In this work, a novel self-attention module called the Local Lighted Transformer block (2L-Transformer) is proposed and is coupled with EfficientNetV2-S as our backbone for improved feature extraction. CSP-PAN topology is adopted as the detection neck to equip feature maps with both low-level object detail features and high-level semantic features, improving the accuracy of object detection and having a clear, noticeable and definitive effect on the detection of small targets. Simultaneously, we substitute the normalized Wasserstein distance (NWD) for the commonly used Intersection over Union (IoU), which alleviates the problem wherein the extensions of IoU-based metrics are very sensitive to the positional deviation of the small objects. The experiments illustrate the promising performance of our detector on many datasets, such as Pascal VOC 2007, TGRS-HRRSD and AI-TOD.

Förderung

  • National Natural Science Foundation

Zitieren

APA

Huo, B., Li, C., Zhang, J., Xue, Y., & Lin, Z. (2023). SAFF-SSD: Self-Attention Combined Feature Fusion-Based SSD for Small Object Detection in Remote Sensing. Remote Sensing, 15(12), 3027. https://doi.org/10.3390/rs15123027

Vancouver

Huo B, Li C, Zhang J, Xue Y, Lin Z. SAFF-SSD: Self-Attention Combined Feature Fusion-Based SSD for Small Object Detection in Remote Sensing. Remote Sensing. 2023;15(12):3027. doi:10.3390/rs15123027

BibTeX
@article{Huo2023,
  author = {Huo, Bihan and Li, Chenglong and Zhang, Jianwei and Xue, Yingjian and Lin, Zhoujin},
  title = {SAFF-SSD: Self-Attention Combined Feature Fusion-Based SSD for Small Object Detection in Remote Sensing},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {12},
  pages = {3027},
  doi = {10.3390/rs15123027}
}
Kostenlos starten →