Automated detection of scallops in their natural environment

Automating the counting of marine animals like scallops benefits marine population survey efforts. These surveys are tools for policy makers to regulate fishing activities, and sources of information for biologists and marine ecologists interested in population statistics of marine species. In this paper we discuss some practical difficulties that arise in the scallop detection problem from visual data, and propose a solution based on top-down visual attention. We assess the performance of the proposed method against a comparable and related method which has recently been employed in literature, using a significant amount of ground truth data.