Visual Tracking of Large Numbers of Bats

Abstract

We propose statistical data association techniques for visual tracking of enormously large numbers of objects. We do not assume any prior knowledge about the numbers involved, and the objects may appear or disappear anywhere in the image frame and at any time in the sequence. Our approach combines the techniques of multitarget track initiation, recursive Bayesian tracking, and clutter modeling. We propose two cluster-based data association approaches that are linear in the number of detections and tracked objects. We applied the method to track wildlife in infrared video. We have successfully tracked millions of bats that were flying at high speeds and in dense formations.

Bio: Margrit Betke is an Associate Professor of Computer Science at Boston University, where she co-leads the Image and Video Computing Research Group. She conducts research in computer vision, in particular, the development and application of advanced methods for detection, segmentation, registration, and tracking of objects in visible-light, infrared, and x-ray image data. She earned her Ph.D. degree in Computer Science and Electrical Engineering at the Massachusetts Institute of Technology in 1995. Prof. Betke has received the National Science Foundation Faculty Early Career Development Award in 2001 for developing "Video-based Interfaces for People with Severe Disabilities." She was one of two academic honorees of the ``Top 10 Women to Watch in New England Award'' by Mass High Tech in 2005.