Keynote speakers: Ultrafast pattern recognition and tracking in FLIR imagery

Abstract

Pattern recognition and tracking in forward looking infrared (FLIR) imagery is a challenging problem due to various factors such as low resolution, low signal-to-noise ratio, different 3D orientations of the targets, effects of global motion, and close proximity with similar objects. In this keynote, we will review the recent trends and advancements in distortion-invariant pattern recognition followed by the development of a novel data fusion algorithm for single/multiple object detection and tracking in FLIR imagery. Each detection/tracking algorithm utilizes various properties of objects and image frames of a given FLIR sequence. The data fusion algorithm employs complementary features of two or more of the aforementioned algorithms to achieve significantly better detection/tracking accuracy. Test results using real life FLIR image sequences confirm the effectiveness of the proposed technique.