A complete edge AI system we engineered for transit operators — custom hardware, on-device inference, and a reporting pipeline that runs 24/7 in extreme conditions.
Transit operators had no reliable way to audit actual ridership against ticket sales. Manual counts are inaccurate. Existing solutions weren't built for the crowding patterns, lighting conditions, and harsh environments of Indian public transit.
Trip-by-trip passenger data for ticket audit reconciliation. Every boarding and alighting captured and logged.
Operators can confidently fill more passengers on-route, knowing exact counts are being tracked independently.
Driving patterns, stop-level ridership data, and peak analysis to optimize routes and scheduling.
Purpose-built camera unit with embedded compute. Ruggedized for heat, dust, and vibration. Day and night operation with IR capability.
Person detection and tracking optimized for overhead camera angles. Handles crowding, dim lighting, and crew filtering — all inference runs on the edge device.
Real-time data upload over cellular. Trip reports with video clips for each boarding/alighting event. Cloud dashboard for fleet-level analytics.
Trained on Indian boarding patterns — crowded doorways, simultaneous entry/exit, non-standard stops. Adapts to global markets.
Anyone can build CV for a clean, controlled environment. We made ours work in the hardest conditions — 50°C heat, dust, vibration, pitch darkness, patchy connectivity, and crowds pushing through a single door simultaneously. That's the engineering challenge we solved.
We've proven we can go from concept to deployed hardware running real-time CV models. Let's talk about your use case.
Start a Conversation