The optimal parameters for each model were searched by a simple grid scan based on cross-validation over the training data with five folds and utilizing the root mean square error (RSME). The four-part Table 4 shows the final training parameter configurations for the models considering all targe...
[25] camera footage has been studied as well. For detecting the most salient regions and objects in an image according to human perception, a number of approaches have been introduced [27,28,29]. These methods generate a saliency map from an input image, highlighting those regions that the ...
Video transects were selected and analyzed as explained inSection 2.3. An example of a selected image from the video footage is seen inFigure 10. The seafloor in this image is lit from the above right. Visible in this image is a seafloor with sand ripples. The gentle stoss-side slopes of...