Vijayakumar Bhagavatula

Interim Dean, College of Engineering
U.A. and Helen Whitaker Professor, Electrical and Computer Engineering
Affiliated Faculty, DSSC

Bio

Vijayakumar Bhagavatula received his B.Tech. and M.Tech. degrees in electrical engineering from Indian Institute of Technology, Kanpur and his Ph.D. in electrical engineering from Carnegie Mellon University. Since 1982, he has been a faculty member in the Department of Electrical and Computer Engineering (ECE) at Carnegie Mellon where he is now the U.A. & Helen Whitaker Professor of Electrical and Computer Engineering.

Bhagavatula’s research interests include computer vision and pattern recognition algorithms and applications and coding and signal processing for data storage systems. His publications include the book Correlation Pattern Recognition, 22 book chapters, more than 410 conference papers, and 210 journal papers. He is also the co-inventor of 15 patents. He served as a topical editor for Applied Optics and as an associate editor for IEEE Transactions on Information Forensics and Security.

Bhagavatula has served on many conference program committees and was a co-chair of the 2008-2010 SPIE conferences on Biometric Technology for Human Identification, a co-program chair of the 2012 IEEE Biometrics: Theory, Applications and Systems (BTAS) conference and a program committee co-chair for the 2015 International Conference on Biometrics (ICB). He has also received numerous awards and honors.

Education

Ph.D., 1980 
Electrical Engineering 
Carnegie Mellon University

MTech, 1977 
Electrical Engineering 
Indian Institute of Technology, Kanpur

BTech, 1975 
Electrical Engineering 
Indian Institute of Technology, Kanpur

Research

Machine Learning for Biometrics

One way of matching live biometric images (e.g., face images, iris images) with stored templates is to perform the cross-correlation of the two images. Professor Kumar and his students have developed several spatial frequency-domain methods to perform these cross-correlations in the presence of significant appearance variability (e.g., due to illumination changes, expression differences, etc.) in the biometric signatures.

Computer Vision for Connected Vehicles

Computer vision is a critical component for detecting objects in autonomous-driving applications. While advanced machine learning algorithms (including deep learning approaches) perform well in detecting larger objects such as cars and trucks, their performance degrades when trying to detect vulnerable road users (VRUs) such as pedestrians and bicyclists. Prof. Kumar’s research is developing methods to improve VRU detection performance through collaborative perception where multiple sensing agents (in vehicles, in roadside units, in traffic lights) can communicate information with each other to detect objects in challenging conditions such as occlusions and poor visibility.

Keywords

• Biometrics
• Computer/storage systems
• Data storage systems
• Mobile systems
• Signal processing
• Computer vision
• Cyberphysical systems
• Machine learning
• Secure systems
• Smart infrastructure 

Past Appointments

Honors and Awards