EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SMFF-YOLO: A Scale-Adaptive YOLO Algorithm with Multi-Level Feature Fusion for Object Detection in UAV Scenes

Yuming Wang, Hua Zou, Ming Yin, Xining Zhang

Remote Sensing · 18.09.2023 · 15 (18) · 4580

DOI: 10.3390/rs15184580 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 18.09.2023. Verfasst von Yuming Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bingtuan Science and Technology Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection in images captured by unmanned aerial vehicles (UAVs) holds great potential in various domains, including civilian applications, urban planning, and disaster response. However, it faces several challenges, such as multi-scale variations, dense scenes, complex backgrounds, and tiny-sized objects. In this paper, we present a novel scale-adaptive YOLO framework called SMFF-YOLO, which addresses these challenges through a multi-level feature fusion approach. To improve the detection accuracy of small objects, our framework incorporates the ELAN-SW object detection prediction head. This newly designed head effectively utilizes both global contextual information and local features, enhancing the detection accuracy of tiny objects. Additionally, the proposed bidirectional feature fusion pyramid (BFFP) module tackles the issue of scale variations in object sizes by aggregating multi-scale features. To handle complex backgrounds, we introduce the adaptive atrous spatial pyramid pooling (AASPP) module, which enables adaptive feature fusion and alleviates the negative impact of cluttered scenes. Moreover, we adopt the Wise-IoU(WIoU) bounding box regression loss to enhance the competitiveness of different quality anchor boxes, which offers the framework a more informed gradient allocation strategy. We validate the effectiveness of SMFF-YOLO using the VisDrone and UAVDT datasets. Experimental results demonstrate that our model achieves higher detection accuracy, with AP50 reaching 54.3% for VisDrone and 42.4% for UAVDT datasets. Visual comparative experiments with other YOLO-based methods further illustrate the robustness and adaptability of our approach.

Förderung

  • Bingtuan Science and Technology Program
  • National Natural Science Foundation of China

Zitieren

APA

Wang, Y., Zou, H., Yin, M., & Zhang, X. (2023). SMFF-YOLO: A Scale-Adaptive YOLO Algorithm with Multi-Level Feature Fusion for Object Detection in UAV Scenes. Remote Sensing, 15(18), 4580. https://doi.org/10.3390/rs15184580

Vancouver

Wang Y, Zou H, Yin M, Zhang X. SMFF-YOLO: A Scale-Adaptive YOLO Algorithm with Multi-Level Feature Fusion for Object Detection in UAV Scenes. Remote Sensing. 2023;15(18):4580. doi:10.3390/rs15184580

BibTeX
@article{Wang2023,
  author = {Wang, Yuming and Zou, Hua and Yin, Ming and Zhang, Xining},
  title = {SMFF-YOLO: A Scale-Adaptive YOLO Algorithm with Multi-Level Feature Fusion for Object Detection in UAV Scenes},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {18},
  pages = {4580},
  doi = {10.3390/rs15184580}
}
Kostenlos starten →