Advanced Multi-Modal Sensor Fusion System for Detecting Falling Humans (AFODS) - Source Code Archive v1.0.1

Collisions with fallen pedestrians pose a lethal challenge to current Advanced Driver Assistance Systems (ADAS). Standard monocular architectures yield a True Positive Rate (TPR) as low as 21.4% at night for prone individuals — a critical classification gap. This repository contains the software framework and quantitative evaluation for the Advanced Falling Object Detection System (AFODS). AFODS architecturally integrates LWIR Thermal, NIR Stereo, and Ultrasonic sensors with a custom AI pipeline to achieve 98.2% TPR in daytime conditions and 95.6% TPR at night.