Indexing and Selection of Well-Lit Details in Underwater Video Mosaics Using Vignetting Estimation

Video is an important tool in underwater surveys today, yet its useful field of view is restricted to image details within well lit regions on the seafloor. In this paper we present a novel vignetting-based weighting scheme for selecting these well lit details for use in the creation of a wide area view (mosaic) of the surveyed seafloor. Apart from this detail selection novelity, two other contributions are made. Firstly, because some of these scenes contain very little image texture, we introduce a hybrid homography estimation procedure that uses both feature-based and exhaustive searching techniques. Secondly, to facilitate cross referencing with the video, sections of the mosaic were indexed with the frame number in which the respective image details was selected from. We test our algorithm with real seabed survey video, whose scientific mission was population census of the particular species of lobster, Nephrops norvegicus. High quality mosaics were obtained that captured image details from well lit regions of the scene, which expert marine biologists agreed was a useful analysis tool.