Field Safe: An IoT-Based Camera Monitoring System for Preventing Animal Crop Damage

Crop damage caused by wild and stray animals remains a significant challenge in modern agriculture, resulting in substantial economic losses and increased labor requirements for continuous field monitoring. This paper presents Field Safe, an Internet of Things (IoT)-enabled intelligent farm security system that combines edge-based computer vision with automated deterrent mechanisms to distinguish humans from animals in real time. The proposed system integrates surveillance cameras, motion sensors, IoT relays, and deep learning-based object detection models (YOLOv5/YOLOv8) to accurately identify intrusions. When a human is detected, the system suppresses deterrent actions to avoid unnecessary disturbances. Conversely, upon detecting an animal, it automatically activates deterrent devices such as buzzers or flashing lights and simultaneously sends instant notifications to farmers via SMS or mobile applications for timely awareness and intervention.

Internet of Things (IoT), Smart Agriculture, Smart Farm Security, Animal Detection

1. Kumar, R., Sharma, M., & Jain, R. (2023). YOLOv5 and YOLOv8 for real-time animal detection in smart farming systems. arXiv preprint, arXiv:2308.06614. [Google Scholar] [Crossref]

2. Singh, A., Yadav, V., & Gupta, D. (2022). IoT-enabled real-time surveillance system using Raspberry Pi and PIR sensors for agricultural field monitoring. International Journal of Advanced Computer Science and Applications, 13(5), 442–450. https://doi.org/10.14569/IJACSA.2022.0130557 [Google Scholar] [Crossref]

3. Bavane, V., Shinde, N., Kadam, P., & Wakchaure, S. (2024). IoT-Based Animal Detection and Alert System for Farm Fields. [Google Scholar] [Crossref]

4. Delwar, T. S., Mukhopadhyay, S., Ryu, J.-Y., & Kim, Y.-K. (2025). Real-time farm surveillance using IoT and YOLOv8 for animal intrusion detection. Future Internet, 17(2), 1–43. [Google Scholar] [Crossref]

5. Miao, J., Rajasekhar, D., Mishra, S., Nayak, S. K., & Yadav, R. (2023). A Fog-Based Smart Agriculture System to Detect Animal Intrusion. arXiv preprint, arXiv:2308.06614. (Please verify this arXiv ID.) [Google Scholar] [Crossref]

6. Chauhan, A., & Saini, H. (2023). Smart IoT-based pest and intrusion control system in agricultural fields using AI and camera networks. International Journal of Sensor Networks and Data Communications, 12(1), 1–8. https://doi.org/10.4172/2090-4886.1000205 [Google Scholar] [Crossref]

7. Lee, T. K. M., & Belkhatir, M. (2020). Vision-Based Techniques for Gait Recognition. arXiv preprint, arXiv:2005.02148. [Google Scholar] [Crossref]

8. He, Y., Li, C., & Zhao, X. (2022). Internet of Things sensors application in dairy cattle farming: Body temperature monitoring. Animals, 14(21), Article 3071. https://doi.org/10.3390/ani14213071 [Google Scholar] [Crossref]

9. Narula, H., & Pathak, A. (2022). IoT-based smart agriculture and animal detection system. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 10(8), 1525–1529. [Google Scholar] [Crossref]

10. Kumar, D., & Rani, P. (2023). IoT-based smart monitoring and alert system for animal intrusion in agriculture. Journal of Emerging Technologies and Innovative Research (JETIR), 10(2), 87–93. [Google Scholar] [Crossref]

11. Balakrishna, K., Mohammed, F., Ullas, C., Hema, C., & Sonakshi, S. (2021). Application of IoT and machine learning in crop protection against animal intrusion. Global Transitions Proceedings, 2, 169–174. [Google Scholar] [Crossref]

12. Burghardt, T., Calic, J., & Walter, T. (2014). Automated detection and recognition of wildlife using thermal cameras in agricultural vehicles. Sensors, 14(8), 13778–13795. https://doi.org/10.3390/s140813778 [Google Scholar] [Crossref]

13. Nørremark, M., Griepentrog, H. W., Nielsen, J., & Søgaard, H. T. (2011). Automatic detection of animals in mowing operations using thermal cameras. Sensors, 12(6), 7587–7605. https://doi.org/10.3390/s120607587 [Google Scholar] [Crossref]

14. Shen, C., Yu, S., Wang, J., Huang, G. Q., & Wang, L. (2022). A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges. arXiv preprint, arXiv:2206.13732. [Google Scholar] [Crossref]

15. Alsaaod, M., Buser, M., Beer, G., & Steiner, A. (2023). Artificial intelligence and sensor innovations: Enhancing livestock welfare with a human-centric approach. Human-Centric Intelligent Systems, 3(1), 12–22. https://doi.org/10.1007/s44230-022-00008-6 [Google Scholar] [Crossref]

16. Patel, R., & Sinha, V. (2023). Lightweight edge AI framework for wildlife detection using YOLO. IEEE Internet of Things Journal, 10(4), 2876–2884. https://doi.org/10.1109/JIOT.2022.3214532 [Google Scholar] [Crossref]

17. Liu, Y., & Zhang, H. (2022). Gait recognition on low-power edge devices for human identification. Sensors, 22(14), 5147. https://doi.org/10.3390/s22145147 [Google Scholar] [Crossref]

18. Gomez, A., & Leung, J. (2024). Thermal-imaging-based indoor human detection for smart systems. ACM Transactions on Sensor Networks, 20(1), Article 7. [Google Scholar] [Crossref]

19. Singh, P., & Rao, S. (2021). Designing IoT-enabled warning devices triggered by edge analytics in agriculture. International Journal of Agricultural Technology, 17(5), 1421–1433. [Google Scholar] [Crossref]

20. Garcia, A., Patel, Y., & Lee, S. (2024). Edge-based thermal and vision combined system for wildlife detection in farms. Sensors, 24(3), 1201. https://doi.org/10.3390/s24031201 [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition