A Physical Approach to Infrared Image Understanding

In this article, we present how it is possible to recover physical parameters of objects such as reflectivity, emissivity and thermal inertia from the analysis of infrared images in outdoor scenes. Our approach is based on the extensive use of the physical laws that are at the origin of the formation of images. First, we derive a physical model that describes how surface patches of objects appear in infrared images. Second, in order to calculate the physical properties of objects, we inverse this model by using a least square fitting method. Because of the non-linearity of the model, we show that it is difficult to obtain accurate results about the physical properties. To overcome this limitation, we demonstrate that, under several assumptions, there exist some physical invariants that are more reliable than physical parameters.