EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Object Detection for Edge Computing-Based Agricultural Automation: A Case Study Comparing the YOLOX and YOLOv12 Architectures and Their Performance in Potato Harvesting Systems

Joonam Kim iD, Giryeon Kim, Rena Yoshitoshi iD, Kenichi Tokuda

Sensors · 24.07.2025 · 25 (15) · 4586

DOI: 10.3390/s25154586 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.07.2025. Verfasst von Joonam Kim und 3 weiteren Autor:innen. Beteiligte Einrichtung: Research Center for Agricultural Robotics, National Agricultural and Food Research Organization, Tsukuba 3050856, Japan. Hauptthemen laut MEDLINE: Solanum tuberosum, Agriculture, Automation. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agricultural Machinery Technology Cluster Project of The Institute of Agricultural Machinery, National Agriculture and Food Research Organization (IAM/NARO)..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we presents a case study involving the implementation experience and a methodological framework through a comprehensive comparative analysis of the YOLOX and YOLOv12 object detection models for agricultural automation systems deployed in the Jetson AGX Orin edge computing platform. We examined the architectural differences between the models and their impact on detection capabilities in data-imbalanced potato-harvesting environments. Both models were trained on identical datasets with images capturing potatoes, soil clods, and stones, and their performances were evaluated through 30 independent trials under controlled conditions. Statistical analysis confirmed that YOLOX achieved a significantly higher throughput (107 vs. 45 FPS, p < 0.01) and superior energy efficiency (0.58 vs. 0.75 J/frame) than YOLOv12, meeting real-time processing requirements for agricultural automation. Although both models achieved an equivalent overall detection accuracy (F1-score, 0.97), YOLOv12 demonstrated specialized capabilities for challenging classes, achieving 42% higher recall for underrepresented soil clod objects (0.725 vs. 0.512, p < 0.01) and superior precision for small objects (0–3000 pixels). Architectural analysis identified a YOLOv12 residual efficient layer aggregation network backbone and area attention mechanism as key enablers of balanced precision–recall characteristics, which were particularly valuable for addressing agricultural data imbalance. However, NVIDIA Nsight profiling revealed implementation inefficiencies in the YOLOv12 multiprocess architecture, which prevented the theoretical advantages from being fully realized in edge computing environments. These findings provide empirically grounded guidelines for model selection in agricultural automation systems, highlighting the critical interplay between architectural design, implementation efficiency, and application-specific requirements.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Solanum tuberosumAgricultureAutomationAlgorithmsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Jetson AGX OrinYOLOXYOLOv12agricultural automationdata imbalanceedge computingobject detectionpotato harvestingreal-time processing

Autor:innen und Institutionen

  • Research Center for Agricultural Robotics, National Agricultural and Food Research Organization, Tsukuba 3050856, Japan.

ORCID-Profile: Joonam Kim, Rena Yoshitoshi

Förderung

  • Agricultural Machinery Technology Cluster Project of The Institute of Agricultural Machinery, National Agriculture and Food Research Organization (IAM/NARO).

Zitieren

APA

Kim, J., Kim, G., Yoshitoshi, R., & Tokuda, K. (2025). Real-Time Object Detection for Edge Computing-Based Agricultural Automation: A Case Study Comparing the YOLOX and YOLOv12 Architectures and Their Performance in Potato Harvesting Systems. Sensors, 25(15), 4586. https://doi.org/10.3390/s25154586

Vancouver

Kim J, Kim G, Yoshitoshi R, Tokuda K. Real-Time Object Detection for Edge Computing-Based Agricultural Automation: A Case Study Comparing the YOLOX and YOLOv12 Architectures and Their Performance in Potato Harvesting Systems. Sensors. 2025;25(15):4586. doi:10.3390/s25154586

BibTeX
@article{Kim2025,
  author = {Kim, Joonam and Kim, Giryeon and Yoshitoshi, Rena and Tokuda, Kenichi},
  title = {Real-Time Object Detection for Edge Computing-Based Agricultural Automation: A Case Study Comparing the YOLOX and YOLOv12 Architectures and Their Performance in Potato Harvesting Systems},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {4586},
  doi = {10.3390/s25154586}
}
Kostenlos starten →