Person Re-identification System
Developed a system capable of recognizing individuals across multiple camera views using non-intrusive visual features such as clothing color, texture, and patterns.
The Challenge
Security systems with multiple cameras needed the ability to track individuals across different camera views without relying on facial recognition.
Approach & Solution
Developed a feature extraction pipeline using deep learning to encode visual attributes like clothing color, texture, body shape, and gait patterns. The system matches feature vectors across camera views using similarity metrics.
Results & Impact
- Non-intrusive tracking without facial recognition
- Cross-camera matching across multiple simultaneous feeds
- Published as Bachelor's thesis at Air University
- Deployed in prototype security monitoring setup
More Projects
MacVis — Local-First AI Desktop Assistant
A fully-agentic macOS desktop app that gives AI full access to your Mac — bash, filesystem, web search, and MCP integrations. Bring-your-own-key: Anthropic, OpenAI, OpenRouter, Gemini, Groq, and Ollama. No backend, no telemetry, everything stays on your machine.
Full StackClaude-Powered iOS AI Assistant
Full-stack iOS AI assistant with natural-language control over device functions, Gmail/Calendar automation, AI-participated group chat, and hybrid pgvector + Supabase persistent memory system.
Full StackAI Trading Strategy Generator
End-to-end agentic backend generating 200+ trading strategy variants autonomously. Client deployed 3 profitable strategies to production with measurable revenue impact.