A Semantic Based Surveillance Video Indexing and Retrieval System

A Semantic Based Surveillance Video Indexing and Retrieval System
Navy SBIR FY2006.2

Sol No.:	Navy SBIR FY2006.2
Topic No.:	N06-147
Topic Title:	A Semantic Based Surveillance Video Indexing and Retrieval System
Proposal No.:	N062-147-0286
Firm:	UtopiaCompression, Corporation 11150 W. Olympic Blvd. Suite 1020 Los Angeles, California 90064-1825
Contact:	Hieu Nguyen
Phone:	(310) 473-1500
Web Site:	www.utopiacompression.com
Abstract:	Beside robust tracking algorithms, a set of efficient and effective tools for video analysis is an important part of security video surveillance systems. The analysis of pre-recorded videos is necessary to discover trends and patterns of threat activities, to evaluate the performance of the security system, and to develop and test new protection rules. The video analysis software should provide security professionals with powerful tools to search and retrieve sophisticated information and knowledge about monitored objects and activities. Currently available content-based video retrieval systems allow for queries on descriptive information, such as target color, location and motion speed/direction, but fall short of searching for high level semantic concepts. Moreover, they lack flexibility as the user has no opportunity to tune the system to achieve best result for a particular query. The objective of this project is the feasibility of an innovative Semantic-Based Video Indexing and Retrieval system (SBVIR) to help security professionals rapidly and effectively search for intelligent information from stored surveillance videos. Our technology is based on a set of powerful statistical classification algorithms that create highly semantic metadata for objects and activities. The system interacts with the user to iteratively increase accuracy and relevance of the retrieved data.
Benefits:	For the Navy, DoD at large, Department of Homeland Security, Department Of Justice, Department of Transportation, the Intelligence Community and the Law Enforcement, there will be immediate benefits upon implementation and deployment of UtopiaCompression Corporation (UC) SBVIR. First, it will dramatically reduce time and effort while increasing effectiveness of security professionals currently searching days even weeks of pre-recorded CCTV videos for security breaches. Secondly, the proposed technology will greatly enhance the capabilities in forensic analysis to identify, predict and prevent threat and violence activities, and to improve the performance of real-time security systems. The commercial potential for UC's novel SBVR is broad and significant. The initial primary application will be for the Military and Department of Homeland Security facilitating a major step in analysis, prediction and prevention of terrorist activities in the (urban) battlefield as well as here at home. In addition to the military and homeland security applications, UC's proposed technology will have significant application for security & surveillance industry. The technology will assist the federal and local law enforcement agencies to better detect, analyze and prevent crime and violence events in urban settings, workplace, schools, financial and other places of business. Consulting firm Frost & Sullivan estimates video surveillance market will grow to a $4.09 billion by 2010. Furthermore, the IMS Research report by Intex Management Services, UK predicts that much of the opportunity lies in software, particularly video content analysis software, a projected $839 million market by 2009. In private commercial markets, the proposer has identified the recreational boating industry as a logical entry point for the proposed technology, given the similar operating environment of the water vehicles. This is a multi-billion dollar industry with projected growth. UC's proposed SBVIR will also assist the mental health professionals to better assess the risk their patients may pose to themselves and to the society. In addition, correction facilities will be able to use UC's technology to better manage risk in prisons. Additionally, automotive industry will be able to use UC's technology for detection of human fatigue and other alarming behavior and prevention of accidents.

Return