David Okosa
Computer Vision & Edge Deployment for Mechanical Systems
New to Contra
David is building their profile!
Detects unwanted human presence in predefined areas, can be deployed on device or over a server with RTSP streaming enabled. Configurable intruder email and SMS alert systems. Different model configurations with varying accuracy and detection FPS.
Optimized machine learning model, works in extremely resource constrained environments while retaining good accuracy and recall. Detects 7 emotions.
Utilizes NCNN (a high perfomance neural network framework), to achieve 79% accuracy @ 90fps.
Multi-modal machine learning service back-end integration with fastapi. Automatically redacts sensitive PII (Personal Identifiable Information) from documents, performs bulk operations. Link to project on github: https://github.com/fw7th/redact
