FogSight – Real-Time Vehicle Detection in Foggy Conditions

Key Highlights

• Developing an AI-powered road safety system that detects vehicles in foggy conditions via a mobile app integrated with a forward-facing camera and deep learning models hosted on Hugging Face.
• Designed an image dehazing pre-processing pipeline using OpenCV Dark Channel Prior (DCP) algorithm to enhance visibility before feeding frames into the YOLOv8 detection model, improving inference accuracy in adverse weather.
• Integrating an ultrasonic distance sensor connected via Bluetooth to estimate proximity of detected vehicles and trigger real-time audio alerts through the car's speakers for driver safety.
• Targeting practical affordability and retrofittability — the system requires no vehicle hardware modifications beyond a mounted camera module and a paired smartphone.
• Building a React Native cross-platform mobile app for real-time visualization of detected vehicles, proximity warnings, and configurable alert sensitivity levels.
• Planning Hugging Face Spaces deployment of the dehazing and detection pipeline for low-latency cloud inference as a fallback when on-device processing is insufficient.