EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles

Hwapyeong Baek, Seunghyun Yu, Seungwook Son, Jongwoong Seo, Yongwha Chung

Sensors · 2024

DOI: 10.3390/s24072371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Hwapyeong Baek und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Convergence Software, Korea University, Sejong 30019, Republic of Korea. Hauptthemen laut MEDLINE: Pandemics, Agriculture. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RIS, Korea Institute for Advancement of Technology(KIAT) grant funded by the Korea Government (MOTIE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the global population increase and the recovery of agricultural demand after the COVID-19 pandemic, the importance of agricultural automation and autonomous agricultural vehicles is growing. Fallen person detection is critical to preventing fatal accidents during autonomous agricultural vehicle operations. However, there is a challenge due to the relatively limited dataset for fallen persons in off-road environments compared to on-road pedestrian datasets. To enhance the generalization performance of fallen person detection off-road using object detection technology, data augmentation is necessary. This paper proposes a data augmentation technique called Automated Region of Interest Copy-Paste (ARCP) to address the issue of data scarcity. The technique involves copying real fallen person objects obtained from public source datasets and then pasting the objects onto a background off-road dataset. Segmentation annotations for these objects are generated using YOLOv8x-seg and Grounded-Segment-Anything, respectively. The proposed algorithm is then applied to automatically produce augmented data based on the generated segmentation annotations. The technique encompasses segmentation annotation generation, Intersection over Union-based segment setting, and Region of Interest configuration. When the ARCP technique is applied, significant improvements in detection accuracy are observed for two state-of-the-art object detectors: anchor-based YOLOv7x and anchor-free YOLOv8x, showing an increase of 17.8% (from 77.8% to 95.6%) and 12.4% (from 83.8% to 96.2%), respectively. This suggests high applicability for addressing the challenges of limited datasets in off-road environments and is expected to have a significant impact on the advancement of object detection technology in the agricultural industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PandemicsAgricultureHumansTechnologyAlgorithmsAutomation

Stichwörter der Autor:innen

automated region of interestautonomous agricultural vehiclesdata augmentationfallen person detection

Autor:innen und Institutionen

  • Department of Computer Convergence Software, Korea University, Sejong 30019, Republic of Korea.
  • Info Valley Korea Co., Ltd., Anyang 14067, Republic of Korea.

Förderung

  • RIS
  • Korea Institute for Advancement of Technology(KIAT) grant funded by the Korea Government (MOTIE)

Zitieren

APA

Baek, H., Yu, S., Son, S., Seo, J., & Chung, Y. (2024). Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles. Sensors. https://doi.org/10.3390/s24072371

Vancouver

Baek H, Yu S, Son S, Seo J, Chung Y. Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles. Sensors. 2024. doi:10.3390/s24072371

BibTeX
@article{Baek2024,
  author = {Baek, Hwapyeong and Yu, Seunghyun and Son, Seungwook and Seo, Jongwoong and Chung, Yongwha},
  title = {Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24072371}
}
Kostenlos starten →