• Indexing and selection of well-lit details in underwater video using vignetting estimation

      Sooknanan, K.; Kokaram, A.; Corrigan, D.; Wilson, J.; Harte, N. (IEEE, 2012)
      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. This work was supported by the Science Foundation Ireland PI Programme: SFI-PI 08/IN.1/I2112, and was done in collaboration with the Marine Institute Galway.
    • Mosaics For Burrow Detection in Underwater Surveillance Video

      Sooknanan, K.; Doyle, J.; Kokaram, A.; Corrigan, D.; Wilson, J.; Harte, N. (IEEE, 2013)
      Harvesting the commercially significant lobster,Nephrops norvegicus, is a multimillion dollar industry in Europe. Stock assessment is essential for maintaining this activity but it is conducted by manually inspecting hours of underwater surveillance videos. To improve this tedious process, we propose the use of mosaics for the automated detection of burrows on the seabed. We present novel approaches for handling the difficult lighting conditions that cause poor video quality in this kind of video material. Mosaics are built using 1-10 minutes of footage and candidate burrows are selected using image segmentation based on local image contrast. A K-Nearest Neighbour classifier is then used to select burrows from these candidate regions. Our final decision accuracy at 93.6% recall and 86.6% precision shows a corresponding 18% and 14.2% improvement compared with previous work.
    • Mosaics For Nephrops Detection in Underwater Survey Videos

      Sooknanan, K; Doyle, J; Lordan, C; Wilson, J; Kokaram, A; Corrigan, D (2014)
      Harvesting the commercially significant lobster, Nephrops norvegicus, is a multimillion dollar industry in Europe. Stock assessment is essential for maintaining this activity but it is conducted by manually inspecting hours of underwater surveillance videos. To improve this tedious process, we propose an automated procedure. This procedure uses mosaics for detecting the Nephrops, which improves visibility and reduces the tedious video inspection process to the browsing of a single image. In addition to this novel application approach, key contributions are made for handling the difficult lighting conditions in these kinds of videos. Mosaics are build using 1-10 minutes of footage and candidate Nephrops regions are selected using image segmentation based on local image contrast and colour features. A K-Nearest Neighbour classifier is then used to select the respective Nephrops from these candidate regions. Our final decision accuracy at 87.5% recall and precision shows a corresponding 31.5% and 79.4% improvement compared with previous work.