Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks

TL;DR

This paper presents a scalable, AI-driven traffic analytics system that processes city-scale CCTV streams in real-time by leveraging edge-cloud computing, advanced neural networks, and adaptive load balancing to ensure high performance and accuracy.

Contribution

It introduces a novel scalable platform combining edge and cloud processing with dynamic load balancing, real-time graph inference, and federated learning for city-scale traffic monitoring.

Findings

Stable ingestion up to 2000 FPS on Jetson Orins

Low-latency traffic flow aggregation

Accurate forecasting for up to 1000 streams

Abstract

Real-time city-scale traffic analytics requires processing 100s-1000s of CCTV streams under strict latency, bandwidth, and compute limits. We present a scalable AI-driven Intelligent Transportation System (AIITS) designed to address multi-dimensional scaling on an edge-cloud fabric. Our platform transforms live multi-camera video feeds into a dynamic traffic graph through a DNN inferencing pipeline, complemented by real-time nowcasting and short-horizon forecasting using Spatio-Temporal GNNs. Using a testbed to validate in a Bengaluru neighborhood, we ingest 100+ RTSP feeds from Raspberry Pis, while Jetson Orin edge accelerators perform high-throughput detection and tracking, producing lightweight flow summaries for cloud-based GNN inference. A capacity-aware scheduler orchestrates load-balancing across heterogeneous devices to sustain real-time performance as stream counts increase. To ensure continuous adaptation, we integrate SAM3 foundation-model assisted labeling and Continuous Federated Learning to update DNN detectors on the edge. Experiments show stable ingestion up to 2000 FPS on Jetson Orins, low-latency aggregation, and accurate and scalable ST-GNN forecasts for up to 1000 streams. A planned live demonstration will scale the full pipeline to 1000 streams, showcasing practical, cross-fabric scalability.