Stereo Reconstruction of Infrared Images Captured in Microwave Reactor

Abstract

During metallurgy and food processing it is always necessary for real-time detection of stereo temperature distribution in reaction cavity of microwave. We focus on the stereo reconstruction of temperature distribution of the microwave reaction chamber using real-time image data captured by infrared sensor during heating process. Due to the stereo depth of the scene in humans vision system is mapped through disparity, thus the key technology stereo reconsturction of temperature is to find the corresponding points in the image pair. We employ the block matching algorithm to search the correspondence by minimizing a cost function derived on a hierarchical tree structured pyramid probabilistic graph. The study result shows that in the back projection of the depth map, the walls, ceiling, and floor of the microwave reactor all appear mutually orthogonal, which illustrates that the stereo temperature field is well reconstructed.