Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles
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).
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)
Stichwörter der Autor:innen
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}
}
EUVIMED