Hex Bug Tracking
Multi-model detection and tracking pipeline evaluated for real-time accuracy and inference speed using FPN, Faster R-CNN, U-Net, and YOLO.
Links
No public links available yet.
Problem
Accurate detection and tracking of small 'hex bugs' in complex scenes.
Solution
Benchmarked detection/segmentation architectures: FPN, Faster R-CNN, ResNet-50, U-Net, YOLO on curated datasets.
Impact
- Identified tradeoffs across precision and latency
- Guidance for production trials
Tech Stack
PyTorch, torchvision, OpenCV.
Related projects
Real-time emotion detection pipeline with CNN/DNN models using Python, Flask, and React.
Full-stack AI resume analyzer that scores ATS compatibility, detects skill gaps, matches keywords semantically, and rewrites experience bullets using a local NLP pipeline and cloud LLM.
AI-powered VC pitch simulator that stress-tests startup founders with a dual-role Gemini 2.5 Flash engine — acting as a hostile investor then switching to structured coach — across 5 investor personas and stage-adaptive difficulty levels.