Digital Fencing for Farms: Enhancing Object Detection through Multi-Dataset Integration

Juliana Quintiliano de Oliveira Ferreira; Lucas Silva; Thiago L. Gomes; Michel Melo Silva

doi:10.22456/2175-2745.143486

Authors

Juliana Quintiliano de Oliveira Ferreira Universidade Federal de Viçosa (UFV) https://orcid.org/0009-0000-2742-9358
Lucas Silva Universidade Federal de Viçosa (UFV) https://orcid.org/0009-0007-7641-1446
Thiago L. Gomes Universidade Federal de Viçosa (UFV) https://orcid.org/0000-0002-7679-8210
Michel Melo Silva Universidade Federal de Viçosa (UFV) https://orcid.org/0000-0002-2499-9619

DOI:

https://doi.org/10.22456/2175-2745.143486

Keywords:

Object Detection, Farm security, Digital Fence, Data Integration

Abstract

Security in farm areas is a critical concern due to the risks posed by wild animal invasions, farm animals straying, and unauthorized human entry. Conventional object detection models, often trained on urban or context-specific datasets, frequently underperform in farm settings. To address this, our study investigates the integration of multi-datasets to enhance object detection for digital fences, thereby improving farm security. We propose a method to effectively utilize multi-datasets, even when they do not have the same classes, ensuring comprehensive coverage of all required categories. The proposed SmartClass methodology achieved more robust and adaptable detection approaches, suitable for agricultural environments, with considerable increases in recall, mAP50, and mAP50-95 metrics compared to models trained without the methodology. The code and data are available at github.com/MaVILab-UFV/Digital-Fencing-WVC-2024.

Downloads

Download data is not yet available.

References

YIONG, Y. T.; KHAIRUDIN, A. R. M.; REDZUWAN, R. M. Real-time substation detection and monitoring security alarm system. In: Conf. on Systems, Process Control (ICSPC). [s.n.], 2023. Disponível em: ⟨https://ieeexplore.ieee.org/document/10419939⟩.

BRINDHA, S. et al. Augmented security system for commercial buildings by manipulating object detection and admin panel. In: Inter. Conf. on Communication, Computing and Internet of Things (IC3IoT). [s.n.], 2022. Disponível em: ⟨https://ieeexplore.ieee.org/document/9767997⟩.

ALZAABI, A. et al. A systematic literature review on machine learning in object detection security. In: Inter. Conf. on Computing Communication and Automation (ICCCA). [s.n.], 2020. Disponível em: ⟨https://ieeexplore.ieee.org/document/9250836⟩.

REDDY, B. R.; CHOKKALINGAM, S. P. Enhancing transportation security: Automated prohibited object detection for baggage inspection leveraging yolo-nas. In: Inter. Conf. on Image Information Processing (ICIIP). [s.n.], 2023. Disponível em: ⟨https://ieeexplore.ieee.org/document/10537641⟩.

XIAO, Y. et al. Real-time object detection for substation security early-warning with deep neural network based on yolo-v5. In: IAS Global Conf. on Emerging Technologies (GlobConET). [s.n.], 2022. Disponível em: ⟨https://ieeexplore.ieee.org/document/9872338⟩.

PRIYANKA, S. et al. Smart farming: Intelligent animal detection framework in agriculture using iot sensors. In: Inter. Conf. on Edge Computing and Applications (ICECAA). [s.n.], 2023. Disponível em: ⟨https://ieeexplore.ieee.org/document/10212297⟩.

SHETTY, A. D.; ASHWATH, S. Animal detection and classification in image & video frames using yolov5 and yolov8. In: Inter. Conf. on Electronics, Communication and Aerospace Technology (ICECA). [s.n.], 2023. Disponível em: ⟨https://ieeexplore.ieee.org/document/10394750⟩.

PEZZEMENTI, Z. et al. Comparing apples and oranges: Off-road pedestrian detection on the nrec agricultural person-detection dataset. Journal of Field Robotics, 2017. Disponível em: ⟨https://doi.org/10.48550/arXiv.1707.07169⟩.

NEIGEL, P. et al. Opedd: Offroad pedestrian detection dataset. Journal of WSCG, 2020. Disponível em: ⟨http://wscg.zcu.cz/wscg2020/journal/F13.pdf⟩.

LIN, T.-Y. et al. Microsoft coco: Common objects in context. In: ECCV. [s.n.], 2014. Disponível em: ⟨https://doi.org/10.48550/arXiv.1405.0312⟩.

ZHOU, X.; KOLTUN, V.; KRÄHENBÜHL, P. Simple multi-dataset detection. In: CVPR. [s.n.], 2022. Disponível em: ⟨https://doi.org/10.48550/arXiv.2102.13086⟩.

GAO, J. et al. Towards self-supervision for video identification of individual holstein-friesian cattle: The cows2021 dataset. arXiv preprint arXiv:2105.01938, 2021. Disponível em: ⟨https://doi.org/10.48550/arXiv.2105.01938⟩.

YANG, Y. et al. Apt-36k: A large-scale benchmark for animal pose estimation and tracking. In: Advances in Neural Information Processing Systems. [s.n.], 2022. Disponível em: ⟨https://doi.org/10.48550/arXiv.2206.05683⟩.

MAMAT, N.; OTHMAN, M. F.; YAKUB, F. Animal intrusion detection in farming area using yolov5 approach. In: Inter. Conf. on Control, Automation and Systems (ICCAS). [s.n.], 2022. Disponível em: ⟨https://ieeexplore.ieee.org/document/10003780⟩.

NAVEENKUMAR, M. et al. Densenet201 for animal detection and repellent system. In: Inter. Conf. on Electronic Systems and Intelligent Computing (ICESIC). [s.n.], 2022. Disponível em: ⟨https://ieeexplore.ieee.org/document/9783582⟩.

AKHIL, V. et al. Virtual fencing to prevent human wild conflict. In: Inter. Conf. on Innovations in Engineering and Technology (ICIET). [s.n.], 2023. Disponível em: ⟨https://ieeexplore.ieee.org/document/10220801⟩.

HSU, C.-K. et al. Design and implementation of image electronic fence with 5g technology for smart farms. In: VTS Asia Pacific Wireless Communications Symposium (APWCS). [s.n.], 2019. Disponível em: ⟨https://ieeexplore.ieee.org/document/8851659⟩.

OYELADE, I. et al. Farmland intrusion detection using internet of things and computer vision techniques. Inter. Journal of Information Technology and Computer Science, 2024. Disponível em: ⟨https://www.mecs-press.org/ijitcs/ijitcs-v16-n2/v16n2-3.html⟩.

TABOR, T. et al. People in the weeds: Pedestrian detection goes off-road. In: Inter. Symposium on Safety, Security, and Rescue Robotics (SSRR). [s.n.], 2015. Disponível em: ⟨https://ieeexplore.ieee.org/document/7442951⟩.