Problem
Support rail-yard operations by detecting, identifying, and tracking rail assets across real-world camera views.
Context
The source portfolio describes a multi-camera system with edge and control-center components deployed around NVIDIA AGX Xavier hardware.
My role
Built computer vision analytics, processed datasets, and supported edge deployment.
Constraints
- Outdoor industrial conditions and long camera ranges.
- Multi-camera identity continuity.
- Edge compute and operational reliability.
TODO_REVIEW: Confirm camera count, throughput, deployment footprint, and approved customer details.
Architecture
Detection and tracking ran within an edge-to-control-center design, with re-identification supporting continuity across views.
TODO_REVIEW: Add an approved deployment diagram.
Technical decisions
- Used specialized detection, tracking, and re-identification stages.
- Deployed on NVIDIA edge hardware for field operation.
Trade-offs
TODO_REVIEW: Document model accuracy, latency, power, bandwidth, and maintenance
trade-offs.
Results
TODO_REVIEW: Add verified operational and model-performance outcomes.
Screenshots
TODO_REVIEW: Add approved field or system screenshots.
Related links
TODO_REVIEW: Add related publication and public project links.