Paper
Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks
Authors
Akash Sharma, Pranjal Naman, Roopkatha Banerjee, Priyanshu Pansari, Sankalp Gawali, Mayank Arya, Sharath Chandra, Arun Josephraj, Rakshit Ramesh, Punit Rathore, Anirban Chakraborty, Raghu Krishnapuram, Vijay Kovvali, Yogesh Simmhan
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.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.05217v1</id>\n <title>Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks</title>\n <updated>2026-03-05T14:30:10Z</updated>\n <link href='https://arxiv.org/abs/2603.05217v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.05217v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.DC'/>\n <published>2026-03-05T14:30:10Z</published>\n <arxiv:comment>Accepted at TCSC SCALE Challenge 2026. To appear in the Proceedings of IEEE/ACM CCGRID Workshops, Sydney, 2026</arxiv:comment>\n <arxiv:primary_category term='cs.DC'/>\n <author>\n <name>Akash Sharma</name>\n </author>\n <author>\n <name>Pranjal Naman</name>\n </author>\n <author>\n <name>Roopkatha Banerjee</name>\n </author>\n <author>\n <name>Priyanshu Pansari</name>\n </author>\n <author>\n <name>Sankalp Gawali</name>\n </author>\n <author>\n <name>Mayank Arya</name>\n </author>\n <author>\n <name>Sharath Chandra</name>\n </author>\n <author>\n <name>Arun Josephraj</name>\n </author>\n <author>\n <name>Rakshit Ramesh</name>\n </author>\n <author>\n <name>Punit Rathore</name>\n </author>\n <author>\n <name>Anirban Chakraborty</name>\n </author>\n <author>\n <name>Raghu Krishnapuram</name>\n </author>\n <author>\n <name>Vijay Kovvali</name>\n </author>\n <author>\n <name>Yogesh Simmhan</name>\n </author>\n </entry>"
}