Case Study — Computer Vision & Privacy
Real-Time Person Redaction — Privacy-First Computer Vision
A real-time computer vision system that keeps the primary subject in sharp focus while automatically redacting (blurring) anyone who enters the frame behind them — privacy-preserving masking applied live to a camera feed.
Demo
The Challenge
Cameras capture more than the intended subject. Bystanders and background people are recorded whether they consented or not — a privacy risk in CCTV, broadcast, and documentation footage. Manually blurring every frame after the fact is impractical for live or long recordings.
What We Built
- Person detection on every frame of the live camera feed using a computer vision model
- Focus-subject selection that identifies the primary person in the frame and keeps them unredacted
- Automatic real-time redaction (blur masking) applied to every non-focus person behind the subject
- Streaming-friendly pipeline that keeps redaction synchronized with video as it is captured
PythonOpenCVObject DetectionVideo ProcessingComputer VisionReal-Time
Results
Redaction mode
Realtime blur masking
Focus handling
Subject kept in focus
Detection
Frame-by-frame CV
More Work
Batch Disclosure — Price-Moving Catalyst Detection
An AI-powered system that scans ASX and SEC filings for forward-looking disclosures — contracts, M&A, guidance — that move micro-cap prices before the market catches on.
WikiGen — Autonomous, Bias-Aware Knowledge Synthesis
A multi-agent GraphRAG system that autonomously writes reliable, bias-aware Wikipedia-style articles with verifiable provenance on every claim.
Let's Work Together
Build Something Like This?
This system solved a real problem. We can build something similar for you.