Tracking Human Faces in Infrared Video

摘要

Detecting and tracking face regions in image sequences has applications to important problems such as face recognition, human-computer interaction, and video surveillance. Visible sensors have inherent limitations in solving this task, such as the need for sufficient and specific lighting conditions, as well as sensitivity to variations in skin color. Thermal infrared (IR) imaging sensors image emitted light, not reflected light, and therefore do not have these limitations, providing a 24-hour, 365-day capability while also being more robust to variations in the appearance of individuals. In this paper, we present a system for tracking human heads that has three components. First, a method for modeling thermal emission from human skin that can be used for the purpose of segmenting and detecting faces and other exposed skin regions in IR imagery. Second, the segmentation model is applied to the CONDENSATION algorithm for tracking the head regions over time. This includes a new observation density that is motivated by the segmentation results. Finally, we examine how to use the tracking results to refine the segmentation estimate.