Acquisition and processing of low-distortion sediment core images with computer vision and deep learning

Photographing sediment cores is the first step after splitting in paleoceanography and other geoscience fields. However, obtaining high-resolution, continuous images with very little distortion has traditionally required expensive and fragile line-scanning systems that may be difficult or impossible to transport into the field. Thus many researchers take photographs of entire core sections, which may result in distortion, particularly at the upper and lower edges. To address this issue, we developed an inexpensive, portable, system for linearly sliding a camera over a split core surface to capture sequential images. The system's rigidity makes it appropriate for usage at sea.

We further developed a set of open source tools for seamlessly stitching together the series of photographs using computer vision techniques. The resulting composite image contains less distortion than a single photograph of the entire core section, particularly when combined with a simple camera sliding mechanism. The method allows for detection of and correction for variable camera tilt and rotation between adjacent pairs of images. We trained a deep neural network to post-process the image to automate the tedious task of segmenting the sediment core from the background, while also detecting the location of the accompanying scale bar and cracks or other areas of coring-induced disturbance. A color reflectance record is then generated from the isolated core image, ignoring variations from e.g., cracks and voids.