EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SOD-YOLOv8—Enhancing YOLOv8 for Small Object Detection in Aerial Imagery and Traffic Scenes

Boshra Khalili, Andrew W Smyth

Sensors · 25.09.2024 · 24 (19) · 6209

DOI: 10.3390/s24196209 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.09.2024. Verfasst von Boshra Khalili und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil Engineering and Engineering Mechanics, Columbia University, New York, NY 10027, USA. Die Arbeit wurde bisher 128-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, Center for Smart Streetscapes, an NSF Engineering Research Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection, as a crucial aspect of computer vision, plays a vital role in traffic management, emergency response, autonomous vehicles, and smart cities. Despite the significant advancements in object detection, detecting small objects in images captured by high-altitude cameras remains challenging, due to factors such as object size, distance from the camera, varied shapes, and cluttered backgrounds. To address these challenges, we propose small object detection YOLOv8 (SOD-YOLOv8), a novel model specifically designed for scenarios involving numerous small objects. Inspired by efficient generalized feature pyramid networks (GFPNs), we enhance multi-path fusion within YOLOv8 to integrate features across different levels, preserving details from shallower layers and improving small object detection accuracy. Additionally, we introduce a fourth detection layer to effectively utilize high-resolution spatial information. The efficient multi-scale attention module (EMA) in the C2f-EMA module further enhances feature extraction by redistributing weights and prioritizing relevant features. We introduce powerful-IoU (PIoU) as a replacement for CIoU, focusing on moderate quality anchor boxes and adding a penalty based on differences between predicted and ground truth bounding box corners. This approach simplifies calculations, speeds up convergence, and enhances detection accuracy. SOD-YOLOv8 significantly improves small object detection, surpassing widely used models across various metrics, without substantially increasing the computational cost or latency compared to YOLOv8s. Specifically, it increased recall from 40.1% to 43.9%, precision from 51.2% to 53.9%, mAP0.5 from 40.6% to 45.1%, and mAP0.5:0.95 from 24% to 26.6%. Furthermore, experiments conducted in dynamic real-world traffic scenes illustrated SOD-YOLOv8’s significant enhancements across diverse environmental conditions, highlighting its reliability and effective object detection capabilities in challenging scenarios.

Schlagwörter

Stichwörter der Autor:innen

YOLOv8attention mechanismbounding box regressionfeature pyramid networksmall object detection

Autor:innen und Institutionen

  • Department of Civil Engineering and Engineering Mechanics, Columbia University, New York, NY 10027, USA.

Förderung

  • National Science Foundation
  • Center for Smart Streetscapes, an NSF Engineering Research Center

Zitieren

APA

Khalili, B., & Smyth, A. W. (2024). SOD-YOLOv8—Enhancing YOLOv8 for Small Object Detection in Aerial Imagery and Traffic Scenes. Sensors, 24(19), 6209. https://doi.org/10.3390/s24196209

Vancouver

Khalili B, Smyth AW. SOD-YOLOv8—Enhancing YOLOv8 for Small Object Detection in Aerial Imagery and Traffic Scenes. Sensors. 2024;24(19):6209. doi:10.3390/s24196209

BibTeX
@article{Khalili2024,
  author = {Khalili, Boshra and Smyth, Andrew W},
  title = {SOD-YOLOv8—Enhancing YOLOv8 for Small Object Detection in Aerial Imagery and Traffic Scenes},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {19},
  pages = {6209},
  doi = {10.3390/s24196209}
}
Kostenlos starten →