The extended marine underwater environment database and baseline evaluations

Images captured in underwater environments usually exhibit complex illuminations, severe turbidity of water, and often display objects with large varieties in pose and spatial location, etc., which cause challenges to underwater vision research. In this paper, an extended underwater image database for salient-object detection or saliency detection is introduced. This database is called the Marine Underwater Environment Database (MUED), which contains 8600 underwater images of 430 individual groups of conspicuous objects with complex backgrounds, multiple salient objects, and complicated variations in pose, spatial location, illumination, turbidity of water, etc. The publicly available MUED provides researchers in relevant industrial and academic fields with underwater images under different types of variations. Manually labeled ground-truth information is also included in the database, so as to facilitate the research on more applicable and robust methods for both underwater image processing and underwater computer vision. The scale, accuracy, diversity, and background structure of MUED cannot only be widely used to assess and evaluate the performance of the state-of-the-art salient-object detection and saliency-detection algorithms for general images, but also particularly benefit the development of underwater vision technology and offer unparalleled opportunities to researchers in the underwater vision community and beyond.