— IEEE 2011 Conference on Technology for Homeland Security: Best Papers —

     pdf file Article [pdf]     
Person Attribute Search For Large-Area Video Surveillance


View all comments / Add Comment
CHDS Comment Policy
Jason Thornton

Dr. Jason Thornton is a member of the technical staff in the Homeland Protection Division at MIT Lincoln Laboratory. His work at the Laboratory includes research related to sensor fusion, threat assessment and decision support, and image and video processing. He holds a PhD degree in electrical and computer engineering from Carnegie Mellon University. Dr. Thornton may be contacted at Jason.thornton@ll.mit.edu.

Daniel Butler

Daniel Butler is a graduate student in computer science and engineering at the University of Washington in Seattle. He received his ScB in applied mathematics and computer science from Brown University in 2009. From 2009 to 2010 he was assistant technical staff at MIT Lincoln Laboratory, and from 2010 to 2011 he was a visiting researcher at the Academia Sinica Institute for Mathematics, where he was supported by a Fulbright scholarship.

Jeanette Baran-Gale

Jeanette Baran-Gale received a BS degree in Computer Engineering from The Pennsylvania State University in 2001 and a MS in Mathematics from the University of Massachusetts at Lowell in 2007. Jeanette was an associate staff member of MIT Lincoln Laboratory from 2004 to 2011; she is currently working on her PhD in bioinformatics and computational biology at the University of North Carolina at Chapel Hill.

Michael Chan

Dr. Michael Chan has been a Research Staff Member at MIT Lincoln Laboratory since 2006. His recent work focuses on developing advanced data analytics algorithms and net-centric systems to improve situation awareness and reduce workload for human operators of large surveillance systems. Dr. Chan received his bachelor’s degree in electrical engineering from Oxford University, and his MS and PhD degrees in computer science from the University of Pennsylvania.

Heather Zwahlen

Dr. Heather Zwahlen is a technical staff member at MIT Lincoln Laboratory in the Advanced System Concepts Group. She received a PhD in physics from Michigan State University (MSU) in 2005. She is currently leading a program focusing on technology solutions for homeland protection.


Awarded Best Paper of Conference

This paper describes novel video analytics technology which allows an operator to search through large volumes of surveillance video data to find persons that match a particular attribute profile. Since the proposed technique is geared for surveillance of large areas, this profile consists of attributes that are observable at a distance (including clothing information, hair color, gender, etc.) rather than identifying information at the face level. The purpose of this tool is to allow security staff or investigators to quickly locate a person-of-interest in real time (e.g., based on witness descriptions) or to speed up the process of video-based forensic investigations. The proposed algorithm consists of two main components: a technique for detecting individual moving persons in large and potentially crowded scenes and an algorithm for scoring how well each detection matches a given attribute profile based on a generative probabilistic model. The system described in this paper has been implemented as a proof-of-concept interactive software tool and has been applied to different test video datasets, including collections in an airport terminal and collections in an outdoor environment for law enforcement monitoring. This paper discusses performance statistics measured on these datasets, as well as key algorithmic challenges and useful extensions of this work based on end-user feedback.

Thornton, Jason et al. “Person Attribute Search For Large-Area Video Surveillance.” Homeland Security Affairs, IEEE 2011 Conference on Technology for Homeland Security: Best Papers (May 2012)