Correlation filters represent a well-developed class of methods that are ideally suited for matching images. Over the years, advanced correlation filters have been developed to deal with challenges such as image translations, rotations, scale changes and partial occlusions. While initial application focus of correlation filters was on automatic target recognition, correlation filters have recently been found useful for general object detection, object alignment, object tracking and biometric image matching. This talk will provide an overview of correlation filter theory as well as multiple applications of correlation filters.
Vishnu Naresh Boddeti received a PhD in Electrical and Computer Engineering from Carnegie Mellon University in 2012. He is currently a Postdoctoral Fellow in the Robotics Institute at Carnegie Mellon University. His research interests are in Computer Vision, Machine Learning and Pattern Recognition. He received the best paper award at BTAS 2013.
Host: Kris Kitani