Real-time object detection and three-dimensional tracking for a government mixed-reality experience
Delivered in 42 days and demonstrated live at the State Legislative Assembly.
A mixed-reality "Selfie Point" desktop application for the Lucknow Vidhan Sabha: live camera feed, real-time object detection and positional tracking compositing visitors into mixed-reality content, delivered in 42 days.
A public mixed-reality installation for the Uttar Pradesh Legislative Assembly, operated as a desktop application in a live government environment.
Role: Computer-vision and application engineering
Delivered in partnership with Live Pixel and Mizzle Codes.
- From start to government demonstration
- 42 daysFrom start to government demonstrationFounder track record
- Detection and compositing, on local hardware
- Real timeDetection and compositing, on local hardwareNo cloud round-trips
- Public installation at the State Legislative Assembly
- LivePublic installation at the State Legislative AssemblyLucknow Vidhan Sabha
The system
What was actually built
- Live camera feed captured and processed in real time
- YOLO-based object detection on every frame
- Spatial and positional tracking of detected subjects
- Mixed-reality composition of live subjects with rendered content
- Desktop application packaging for on-site operation
Why it was hard
Engineering complexity
- Real-time detection and compositing on local hardware, no cloud round-trips
- A fixed 42-day window ending in a live public demonstration
- Operating reliably in an uncontrolled, high-footfall environment
Product experience
From the delivered system
Technology
Verified stack
Only technologies confirmed in source code, project documentation or the live deployment are listed.
- Python
- OpenCV
- YOLO object detection
- Real-time image processing
- Three-dimensional tracking
Delivery
Scope of responsibility
- Detection and tracking pipeline
- Mixed-reality composition
- On-site delivery
Related
Nearby systems
Automatic Crime Detector95.1%
A Django web application that analyses webcam and uploaded video frame by frame with trained YOLO models, captures anomalies with timestamps and sends automated email alerts, with remote web access.
American Way Health$430M+
A production voice-AI operation for American Way Health, built around Bland AI. The engineering contribution here is the production layer that keeps the agent calling, compliant and measurable at 400K+ calls per month.
Build a system with similar complexity
Book a free 30-minute consultation, or write to us — you will always talk directly to the person who builds your product.
Techon Pixel · info@techonpixel.com