Objects look very different in the underwater environment compared to their appearance in sunlight. Images with correct colouring simplify the detection of underwater objects and may allow the use of visual SLAM algorithms developed for land-based robots underwater. Hence, image processing is required. Current algorithms focus on the colour reconstruction of scenery at diving depth where different colours can still be distinguished. At greater depth this is not the case. In this study it is investigated whether machine learning can be used to transform image data. First, laboratory tests are performed using a special light source imitating underwater lighting conditions. It is shown that the k-nearest neighbour method and support vector machines yield excellent results. Based on these results an experimental verification is performed under severe conditions in murky water of a diving basin. It is shown that the k-nearest neighbour method gives very good results for small distances between the object and the camera and for small water depths in the red channel. For higher distances, water depths, and for the other colour channels support vector machines are the best choice for the reconstruction of the colour as seen under white light from the underwater images.
展开▼
