Wingman: Hazard Detection and Warning System for Cyclists
A low-cost hazard detection system for cyclists, designed to improve situational awareness without the cost of lidar-heavy hardware. Uses Kivy for the mobile app GUI, Arduino-based sensing hardware for rearward video acquisition, and a Python edge-computing pipeline for computer vision, classification, and monocular distance estimation using TensorFlow Lite, the MobileNet vision model, the KITTI Vision Dataset, and XGBoost via an implementation from the DisNet 2018 paper.
Real-Time Profanity Filtering in Audio
Low-latency profanity filter using the Google Cloud Speech-to-Text API with PyAudio and Python multiprocessing to manage parallel input and output audio streams.
