Haniny – AI Driver Assistant

Developed Haniny as a real-time perception and risk-scoring system under hackathon constraints. We treated it as a systems-integration challenge: camera ingestion, model inference, event scoring, and mobile feedback had to work as one low-latency loop.

Visual Architecture

Initialize Stream

Unified telemetry and HUD overlay.

Sensor stream visualization and data analysis.

Real-time YOLOv8 and MediaPipe processing.

Dynamic risk scoring based on driver behavior.

Fatigue and attentiveness tracking modules.

Official branding for Lloyd Assurances partnership.

System Architecture

Built a dual-stream processing pipeline where interior (driver) and exterior (road) camera feeds are ingested via OpenCV, processed by deep learning models, and fused in a shared event bus. Results are transmitted to a mobile frontend (Flutter) using high-frequency WebSocket messaging.

Implementation Strategy

Architecture involves integrating YOLOv8 and MediaPipe for simultaneous processing, optimizing model weights for mobile-compatible inference speeds, and building a low-latency state synchronization layer between the backend and hybrid app.

Technical Outcome

Provides a functional prototype for safety-critical driver assistance, focusing on tight model-to-product integration and multi-sensor data fusion.

Key Features

Real-time Fatigue, Drowsiness, and Distraction monitoring via MediaPipe

Object detection for road hazards (Stop signs, Pedestrians, Potholes) using YOLOv8

Dynamic risk scoring algorithm based on fused behavioral telemetry

Automated emergency protocol routing for critical safety incidents

Optimized inference loop for low-latency (<300ms) mobile performance

Continue Exploration

Next Project

Malware Analysis Lab