Intelligent Retrieval of Surveillance Imagery Navy SBIR FY2006.2 Sol No.: Navy SBIR FY2006.2 Topic No.: N06-147 Topic Title: Intelligent Retrieval of Surveillance Imagery Proposal No.: N062-147-0567 Firm: ObjectVideo 11600 Sunrise Valley Drive Suite # 290 Reston, Virginia 20191 Contact: OMAR JAVED Phone: (703) 654-9300 Web Site: www.objectvideo.com Abstract: ObjectVideo (OV) proposes the development of tools and architecture for automatic forensic analysis and retrieval of video data. This effort enables accurate mining of surveillance video data based on target analysis and complex activity recognition. The video analytics solution proposed by ObjectVideo will entail a unified data management framework that integrates video, annotation text, maps and geo-reference data for robust video retrieval. OV's existing Forensics product enables simple event retrieval based on target detection, tracking and classification algorithms. Under Phase I funding, we will develop algorithms to (a) recognize interactions between targets, (b) detect unusual and threatening multi-agent behaviors and (c) recognize targets in un-tagged data from examples. A powerful query/inferencing language will be used to allow users to formulate queries based on logical combination of target features, behavior descriptions and temporal constraints. Intuitive user interfaces will be incorporated for easy query creation and result visualization. Benefits: Much of the review of video data is manual and, while people are very good at recognizing threatening or suspicious behavior, they are not very good at effectively reviewing large (or even moderate) amounts of video. The development of a system capable of automatically recognizing complex behaviors and retrieving video based on that recognition would provide the following benefits: (1) Assist in automated post-event forensic analysis; helping analysts in retrieval of (a) suspicious interactions among targets, (b) perimeter breaches and anomalous events, (c) particular targets in video archives by providing `query by example' search options. (2) Help in threat assessment of sensitive sites, such as naval bases, by providing statistical models of normal target occupancy and motion patterns, and finding atypical patterns. (3) Enable a more efficient use of both human and technical resources in processing and analysis of video data. Return