SUNAR: Surveillance Network Augmented by Retrieval

SUNAR, surveillance, retrieval, AVSS, challenge, NIST

The work dealt with an information retrieval based wide area surveillance system Sunar (Surveillance Network Augmented by Queries) being developed as an open source software at FIT BUT. It includes many experimental techniques evaluated by NIST at the Multiple Camera Person Tracking Challenge as a part of the AVSS 2009 Conference.

We used OpenCV Library for tracking in Computer Vision Modules processing the surveillance video. We have improved some methods and added feature extraction capability to the library. Information about objects and the area under surveillance is cleaned, integrated, indexed and stored in Video Retrieval Modules. It is based on the PostgreSQL database extended to be capable of similarity and spatio-temporal information retrieval and some data analysis and mining in the global context.