STAC: Leveraging Spatio-Temporal Data Associations For Efficient Cross-Camera Streaming and Analytics
This addresses bandwidth and latency issues in distributed camera networks for surveillance, offering a domain-specific solution with incremental improvements.
The paper tackles the problem of high bandwidth demands and redundant data in real-time multi-camera video analytics for IoT-based surveillance by proposing STAC, a system that uses spatio-temporal associations to improve efficiency. It achieves a 76% improvement in tracking accuracy, an 8.6x reduction in inference latency, and filters 29% of redundant frames on the AICity Challenge dataset.
In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade model performance, and vice versa. We present STAC, a cross-cameras surveillance system that leverages spatio-temporal associations for efficient object tracking under constrained network conditions. STAC integrates multi-resolution feature learning, ensuring robustness under variable networked system level optimizations such as frame filtering, FFmpeg-based compression, and Region-of-Interest (RoI) masking, to eliminate redundant content across distributed video streams while preserving downstream model accuracy for object identification and tracking. Evaluated on NVIDIA's AICity Challenge dataset, STAC achieves a 76\% improvement in tracking accuracy and an 8.6x reduction in inference latency over a standard multi-object multi-camera tracking baseline (using YOLOv4 and DeepSORT). Furthermore, 29\% of redundant frames are filtered, significantly reducing data volume without compromising inference quality.