AeroVision: Onboard AI for Crisis Monitoring
JAYARAMA PRADEEP(a), RITHESHA S(b)

(a)Department of Electrical and Electronics Engineering,
St. Joseph^s College of Engineering, Chennai, India

(b)Department of Electrical and Electronics Engineering,
St. Joseph^s College of Engineering, Chennai, India

Abstract

In this age of increasing number of natural disasters, the need for quick situational awareness and real-time environmental monitoring has never been more urgent. This research involves creating an autonomous drone-based remote sensing platform that combines deep learning methods with edge computing to provide fast and accurate assessments of disaster areas.

The system uses the NVIDIA Jetson Orin Nano as its onboard AI processor, allowing for real-time analysis of aerial images captured with a mix of RGB and depth sensors, including an Intel RealSense Camera. A Pixhawk 4 flight controller ensures stable navigation and autonomous route planning. Additionally, thermal cameras improve the drone^s ability to find heat signatures, which is crucial for locating survivors in areas affected by disasters.

Unlike traditional remote sensing methods that depend on cloud processing after data collection, this drone system processes information at the edge. This reduces delays and allows for immediate action. The platform applies AI algorithms to detect features such as debris, water bodies and people, which are essential for emergency management and relief efforts.

This research connects remote sensing, edge AI and UAV systems, providing a low-cost, scalable, and effective solution for real-time disaster monitoring. The proposed system advances smart remote sensing and shows how emerging technologies can help tackle important global issues.

Keywords: Edge AI- Autonomous drones- Disaster response- Semantic segmentation- NVIDIA Jetson- UAV

Topic: Topic C: Emerging Technologies in Remote Sensing