Big Data Scalability Issues in WAAS

Jan Prokaj, Xuemei Zhao, Jongmoo Choi, Gérard G. Medioni

Abstract: Wide Area Aerial Surveillance (WAAS) produces very large images at 1-2 fps or more. This data needs to be processed in real time to produce semantically meaningful information, then queried efficiently. We have designed and implemented a full system to detect and track vehicles, and infer activities. We address here the scalability issues, and propose solutions to have the tracker run in real time using different parallelism strategies. We also describe methods to efficiently query the data in forensic mode. Our methods are validated on large scale real world data, and have been transferred to a National Laboratory for deployment.