Detection and Tracking of Targets in Forward-Looking InfraRed (FLIR) Imagery

Abstract

Detection and tracking of targets in forward looking infrared (FLIR) imagery are challenging tasks. IR sensors often provide low signal-to-noise ratio and heavy background cluttering images. Non-stationary cameras can introduce further challenges, because detection and tracking might make it necessary to properly deal with sensor ego-motion through suitable estimation and compensation techniques. Moreover, further issues are posed by imagery with multiple and possibly moving target and non-target objects, which can blend into the background, change their signature, size, shape, and even overlap during their motion. Finally, specific applications could introduce cumbersome real-time constraints, thus requiring tracking techniques with a reduced computational footprint. The objective of this Special Issue is to invite high state-of-the-art research contributions, tutorials, and position papers that address the broad challenges faced in analysis and processing of FLIR imagery. Original papers describing completed and unpublished work that are not currently under review by any other journal/magazine/conference/special issue are solicited.