“…Many approaches for person recognition in thermal infrared images are dealing with strong constraints such as considering only one specific dataset, assuming a stationary camera, or detecting only moving persons [5,6,8,9,13,22,23,33,35]. The authors use own datasets for their experiments [21,31,33,36] or the OTCBVS benchmark datasets: the OSU Thermal Pedestrian Database [5,6,8,13,23,26,31,33,35], the thermal IR subset of OSU Color-Thermal Database [13,21,22,33], and the Terravic Motion IR Database [26]. Regions of interest (ROIs) are detected either with background subtraction [5,6,8,9,13,22,33,35], keypoint detectors [21], sliding window [23,26,36], or thresholding methods such as MSER [31].…”