Multimodal Stereo Vision Using Mutual Information with Adaptive Windowing
Mustafa Yaman, Sinan Kalkan · OpenMETU (Middle East Technical University) · 2013
This paper proposes a method for computing disparity maps from a multimodal stereovision system composed of an infrared and a visible camera pair. The method uses mutual information (MI) as the basic similarity measure where a segmentation-based adaptive windowing mechanism is proposed for greatly enhancing the results. On several datasets, we show that (i) our proposal improves the quality of existing MI formulation, and (ii) our method can provide depth comparable to the quality of Kinect depth data.