Thoht Delta
HomeServicesOur WorkBlogCareers Get in Touch
Back to Our Work
Hardware + Software Edge AI

Passenger Counting
Camera System

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.

BusNet Edge AI Camera
The Challenge

Counting Passengers in Indian Buses

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.

Passenger Count Reports

Accurate Count Reports

Trip-by-trip passenger data for ticket audit reconciliation. Every boarding and alighting captured and logged.

On Road Ticketing

Revenue Confidence

Operators can confidently fill more passengers on-route, knowing exact counts are being tracked independently.

Driving Pattern

Operational Insights

Driving patterns, stop-level ridership data, and peak analysis to optimize routes and scheduling.

What We Engineered

Full-Stack Edge AI System

Custom Hardware Design

Purpose-built camera unit with embedded compute. Ruggedized for heat, dust, and vibration. Day and night operation with IR capability.

On-Device CV Models

Person detection and tracking optimized for overhead camera angles. Handles crowding, dim lighting, and crew filtering — all inference runs on the edge device.

Live Reporting Pipeline

Real-time data upload over cellular. Trip reports with video clips for each boarding/alighting event. Cloud dashboard for fleet-level analytics.

Made for Indian Transit

Trained on Indian boarding patterns — crowded doorways, simultaneous entry/exit, non-standard stops. Adapts to global markets.

AI Detection in action
Bus with mounted passenger counting system
The Hard Problem

If It Works Here, It Works Anywhere

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.

  • Accurate detection in zero-light and overcrowded doorways
  • On-device inference at 50°C with no active cooling
  • Offline-first architecture — stores and syncs when connectivity returns
  • Proven in the field, adaptable to any transit system globally

Need an edge AI system?

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