EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improved Architecture and Training Strategies of YOLOv7 for Remote Sensing Image Object Detection

Dewei Zhao, Faming Shao, Qiang Liu, Heng Zhang, Zihan Zhang, Li Yang

Remote Sensing · 07.09.2024 · 16 (17) · 3321

DOI: 10.3390/rs16173321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 07.09.2024. Verfasst von Dewei Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The technology for object detection in remote sensing images finds extensive applications in production and people’s lives, and improving the accuracy of image detection is a pressing need. With that goal, this paper proposes a range of improvements, rooted in the widely used YOLOv7 algorithm, after analyzing the requirements and difficulties in the detection of remote sensing images. Specifically, we strategically remove some standard convolution and pooling modules from the bottom of the network, adopting stride-free convolution to minimize the loss of information for small objects in the transmission. Simultaneously, we introduce a new, more efficient attention mechanism module for feature extraction, significantly enhancing the network’s semantic extraction capabilities. Furthermore, by adding multiple cross-layer connections in the network, we more effectively utilize the feature information of each layer in the backbone network, thereby enhancing the network’s overall feature extraction capability. During the training phase, we introduce an auxiliary network to intensify the training of the underlying network and adopt a new activation function and a more efficient loss function to ensure more effective gradient feedback, thereby elevating the network performance. In the experimental results, our improved network achieves impressive mAP scores of 91.2% and 80.8% on the DIOR and DOTA version 1.0 remote sensing datasets, respectively. These represent notable improvements of 4.5% and 7.0% over the original YOLOv7 network, significantly enhancing the efficiency of detecting small objects in particular.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhao, D., Shao, F., Liu, Q., Zhang, H., Zhang, Z., & Yang, L. (2024). Improved Architecture and Training Strategies of YOLOv7 for Remote Sensing Image Object Detection. Remote Sensing, 16(17), 3321. https://doi.org/10.3390/rs16173321

Vancouver

Zhao D, Shao F, Liu Q, Zhang H, Zhang Z, Yang L. Improved Architecture and Training Strategies of YOLOv7 for Remote Sensing Image Object Detection. Remote Sensing. 2024;16(17):3321. doi:10.3390/rs16173321

BibTeX
@article{Zhao2024,
  author = {Zhao, Dewei and Shao, Faming and Liu, Qiang and Zhang, Heng and Zhang, Zihan and Yang, Li},
  title = {Improved Architecture and Training Strategies of YOLOv7 for Remote Sensing Image Object Detection},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {17},
  pages = {3321},
  doi = {10.3390/rs16173321}
}
Kostenlos starten →