Identifying sea scallops from benthic camera images

The article presents an algorithmic framework for the automated analysis of benthic imagery data. The data are collected by an autonomous underwater vehicle for the purpose of population assessment of epibenthic organisms, such as scallops. The architecture consists of three layers of processing: visual attention, graph-cut segmentation methods, and template matching. The visual attention layer filters the imagery input, focusing subsequent processing only on regions in the images that are likely to contain target objects. The segmentation layer prepares for subsequent template matching. Finally, template matching classifies filtered objects into targets and distractors. The significance of the proposed approach is in its modular nature and its ability to process imagery datasets of low resolution, brightness, and contrast.