The design and development of an Autonomous Drone to detect and alert forest fire and animal intrusion in forest areas is a groundbreaking technology. This system assesses situations and detects animals entering human living areas to alert relevant authorities. The drone structure is made of plastic and designed in a hexagonal shape. The control unit is divided into a flight controller and an intruder detection camera control unit. The flight controller uses a board with Telemetry module, Receiver module and ESC module through Mission Planner control program. The forest fire and animal detection camera utilizes the Python platform for image detection. Automatic operation uses Auto mode to fly by waypoint for animal and fire detection. In testing, the autonomous drone successfully detected and alerted people living around forest areas, with manual flight testing confirming detection of fire and animals in the surveillance area. The system implements a computationally-low-cost detection algorithm using Python ML, acting as a patrolling device that inspects fire accident areas and collects data to prevent fire spread and reduce loss of life and property.

The researchers have successfully developed an au-tonomous drone that can detect human intruders and an- imals, as well as detect objects and fire hazards in order to provide information to the authorities. The system in-cludes safety mechanisms to observe those entering the surveillance area. The autonomous drone can assess situ-ations and notify relevant officers with clear and accurate information for planning, tracking, and responding to in-cidents. This innovation enables officers to develop appro-priate and timely solutions to current problems and events as they arise. The integration of Edge AI with IoT technology has proven to be an effective approach for wildlife intrusion detection. The system’s ability to process data locally on the drone reduces latency, conserves bandwidth, and en-ables operation in areas with limited internet connectivity. The use of a computationally efficient detection algorithm ensures that the system can run on resource-constrained embedded devices without compromising accuracy. Future work will focus on improving battery life, ex-panding the dataset for more animal species, implement-ing swarm intelligence for multiple drone coordination, and integrating thermal imaging for night-time operation. Ad-ditionally, we plan to explore the use of TinyML models to further reduce power consumption and enable even more efficient edge processing.

1.Deepika R., Shalini P., Sona Saran S., et al., ”Agro Guard Edge AI – Development of Sustainable IoT Framework for Wildlife Intrusion Detection,” IEEE In-ternational Conference on IoT and AI, 2024. 2.Jinpeng Miao, Dasari Rajasekhar, Shivakant Mishra, et al., ”A Microservice-Based Smart Agriculture Sys-tem to Detect Animal Intrusion at the Edge,” IEEE Transactions on AgriElectronics, vol. 12, no. 3, pp. 245-258, 2024. 3.Ashish Gawande, ”Smart Farm Animal Intrusion De-tection Using Multi-Modal IoT and Edge AI,” Journal of Edge Computing, vol. 8, no. 2, pp. 112-128, 2025. 4.Mirosl-aw Hajder, Janusz Kolbusz, and Mateusz Liput, ”AI-Based Integrated Multi-Sensor System with Edge Computing for Human-Wildlife Conflict Management,” IEEE Sensors Journal, vol. 25, no. 1, pp. 78-92, 2025. 5.Tsheten Dorji, Pema Lhaden, Tandin Phuentsho, et al., ”AI-Based Animal Intrusion Detection System for Human-Wildlife Conflict in Bhutan,” International Journal of Environmental Research, vol. 19, pp. 45-61, 2025. 6.Subha N., Sanjay K., Nithyaganesh M., et al., ”AI-Driven Ultrasound System for Wildlife Detection and Sustainable Crop Protection,” Computers and Elec-tronics in Agriculture, vol. 218, 2025. 7.Kong Ka Hing and Mehran Behjati, ”Edge Intelligence for Wildlife Conservation Using TinyML,” ACM Trans-actions on Embedded Computing Systems, vol. 24, no. 2, pp. 1-22, 2025. 8.B. Pareek, P. Gupta, G. Singal and R. Kushwaha, ”Per-son Identification using Autonomous Drone through Resource Constraint Devices,” 2019 Sixth International Conference on Internet of Things: Systems, Manage-ment and Security (IOTSMS), Granada, Spain, 2019, pp. 124-129. 9.S. Nair, G. Rodrigues, C. Dsouza, S. Bellary and V. Gonsalves, ”Designing Of Beach Rescue Drone Us-ing GPS And Zigbee Technologies,” 2019 International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, 2019, pp. 1154-1158. 10.H. Fradi, L. Bracco, F. Canino and J.-L. Dugelay, ”Au- tonomous Person Detection and Tracking Framework Using Unmanned Aerial Vehicles (UAVs),” 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy, 2018, pp. 1047-1051. 11.L. A. Szolga, ”On Flight Real Time Image Processing by Drone Equipped with Raspberry Pi4,” 2021 IEEE 27th International Symposium for Design and Technol-ogy in Electronic Packaging (SIITME), Timisoara, Ro-mania, 2021, pp. 334-337. 12.J. Voas, B. Agresti and P. A. Laplante, ”A Closer Look at IoT’s Things,” IT Professional, vol. 20, no. 3, pp. 11-14, May/Jun. 2018. 13.Q. F. Hassan, ”Introduction to the Internet of Things,” in Internet of Things A to Z: Technologies and Appli-cations, IEEE, 2018. 14.S. Singh and N. Singh, ”Internet of Things (IoT): Secu-rity challenges, business opportunities & reference ar-chitecture for E-commerce,” 2015 International Con-ference on Green Computing and Internet of Things (ICGCIoT), Noida, 2015, pp. 1577-1581. Golam Sarowar, Syed Asif Abdullah and Toufiqul Is-lam, ”Enhanced Wireless Control System for Smoke and Fire Detection,” International Journal of Engineer-ing Research, vol. 5, April 2013.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close