Deep-learning-supported depth-from-focus-microscope

Compact sensor systems, such as those used in rover missions, can profit from 3D measurement techniques that are both accurate and resource-efficient. The Depth-from-Focus (DFF) method derives depth information solely from variations in focus and requires no additional hardware beyond a camera system. Compared to classic DFF-approaches Deep Depth-from-Focus (DDFF) methods using Convolutional Neural Networks (CNNs) can reduce the number of images needed for depth estimation. This lowers both energy consumption and memory requirements. In this work, a microscope setup was upgraded with a DDFF capability, demonstrating how DDFF can be applied to the measurement of geological samples. A beam splitter enables the microscope to operate in combination with a spectrometer. One potential application is to use depth information obtained via DDFF to provide contextual data for spectral measurements.