Georgia Tech 
GVU Center/College of Computing

Human Identification at a Distance
(Funded by Defense Advanced Research Projects Agency HID Program)

People

Goals

We are developing ways to identify humans at a distance.  One primary focus of our work is on gait recognition. We propose a technique that recovers static body and stride parameters of subjects as they walk. This approach is an example of an activity-specific biometric: a method of extracting some identifying properties of an individual or of an individual's behavior that is only applicable when a person is performing that specific action. We are also analyzing the ability of time-normalized joint angle trajectories in the walking plane as a means of gait recognition. In addition, we are undertaking related work in locating and tracking faces (with expressions and speech), detecting occlusions and doing activity specific background subtraction.

Gait Recognition | Related Work | Links to Others | Sponsor

Gait Recognition

Publications

• Johnson, Sun, Bobick, "Predicting large population data cumulative match characteristic performance from small population data" In 4th International Conference on Audio- and Video Based Biometric Person Authentication (AVBPA 2003), University of Surrey, Guildford, UK, June 2003.[pdf]
• Tanawongsuwan, Bobick, “Performance Analysis of Time-Distance Gait Parameters under Different Speeds” In 4th International Conference on Audio- and Video Based Biometric Person Authentication, Guildford, UK, June 2003. [pdf]
• Tanawongsuwan, Bobick, “Characteristics of Time-Distance Gait Parameters across Speeds”, Graphics, Visualization, and Usability Center, Georgia Institute of Technology, Atlanta, GA, Technical Report GIT-GVU-03-01,  2003. [pdf]
• Johnson, Bobick "Relationship between identification metrics: Expected Confusion and Area Under a ROC curve"  In International Conference on Pattern Recognition (ICPR 2002) Quebec, Canada, August 2002.[pdf]
• Bobick, Johnson "Gait recognition using static activity-specific parameters" In Proceedings of Computer Vision and Pattern Recognition Conference (CVPR 2001), Kauai, Hawaii, December 2001.[pdf]
• Tanawongsuwan, Bobick, "Gait recognition from time-normalized joint-angle trajectories in the walking plane" In Proceedings of IEEE Computer Vision and Pattern Recognition Conference (CVPR 2001), Kauai, Hawaii, December 2001. [pdf]
• Johnson, Bobick, "A Multi-view Method for Gait Recognition Using Static Body Parameters" In 3rd International Conference on Audio- and Video Based Biometric Person Authentication, pages 301-311, Halmstad, Sweden, June 2001.[pdf]

Related Work

Facial Modeling

Animated Speakers

• L. Reveret, I. Essa, Visual Coding and Tracking of Speech Related Facial Motion (PS.gz | PDF) In CUES 2001 Workshop, Held in conjuction with CVPR 2001, Lihue, Hawaii, Dec 2001, also available as Georgia Tech, GVU Center Tech Report No. GIT-GVU-TR-01-16

Activity Specific Occlusion and Background Detection

Motion Based Decompositing of Video

• Brostow, G., and I. Essa, "Motion-based Video Decompositing." In Proceedings of IEEE International Conference on Computer Vision 1999 (ICCV’99), Corfu, Greece, March 1999.Also available as Georga Tech, GVU Center Tech Report No. GIT-GVU-TR-98-31 (Abstract | PS.Z | PDF).

Depth Layers from Occlusions

• Arno Schödl and Irfan A. Essa. Depth layers from occlusions. In IEEE Computer Vision and Pattern Recognition, pages I:339-644, 2001.

Links to Other Similar Projects

• CMU HID Mobo Gait Database
• Columbia University HID in Bad Weather
• University of Maryland HID via Gait and Face
• University of Southampton HID via Gait
• University of Texas, Dallas HID via dynamic face recognition
• Colorado State University Evaluation of Face Recognition Algorithms
• University of South Florida HID Databse and Experimental Evaluation
• MIT AI Lab HID Database and Experimental Evaluation

Sponsor

• Defense Advanced Research Projects Agency HID Program