Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918372784996352 |
|---|---|
| author | Sharma, Akash Naman, Pranjal Banerjee, Roopkatha Pansari, Priyanshu Gawali, Sankalp Arya, Mayank Chandra, Sharath Josephraj, Arun Ramesh, Rakshit Rathore, Punit Chakraborty, Anirban Krishnapuram, Raghu Kovvali, Vijay Simmhan, Yogesh |
| author_facet | Sharma, Akash Naman, Pranjal Banerjee, Roopkatha Pansari, Priyanshu Gawali, Sankalp Arya, Mayank Chandra, Sharath Josephraj, Arun Ramesh, Rakshit Rathore, Punit Chakraborty, Anirban Krishnapuram, Raghu Kovvali, Vijay Simmhan, Yogesh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks Sharma, Akash Naman, Pranjal Banerjee, Roopkatha Pansari, Priyanshu Gawali, Sankalp Arya, Mayank Chandra, Sharath Josephraj, Arun Ramesh, Rakshit Rathore, Punit Chakraborty, Anirban Krishnapuram, Raghu Kovvali, Vijay Simmhan, Yogesh Distributed, Parallel, and Cluster Computing 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. |
| title | Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2603.05217 |