Underwater image enhancement has been receiving much attention due to its significance in facilitating various marine explorations. Inspired by the generative adversarial network (GAN) and residual network (ResNet) in many vision tasks, we propose a simplified designed ResNet model based on GAN called efficient GAN (EGAN) for underwater image enhancement. In particular, for the generator of EGAN we design a new pair of convolutional kernel size for the residual block in the ResNet. Secondly, we abandon batch normalization (BN) after every convolution layer for faster training and less artifacts. Finally, a smooth loss function is introduced for halo-effect alleviation. Extensive qualitative and quantitative experiments show that our methods accomplish considerable improvements compared to the state-of-the-art methods.
On the Mediterranean coast of Morocco, many military ships were sunk in the Al-Hoceima region during Rif war between Spanish army and the local Riffians. The aim of this study is to detect and to map shipwrecks embedded in sea-floor sediments in Al-Hoceima coastal. It has been carried out using free satellite radar image and the open-source software Sentinel Application Platform. The result of this study shows five possible locations of shipwrecks in the study area, two of them were confirmed by data shipwrecks of the Spanish hydrographic institute.
Experimental results on energetic characteristics of low frequency (about 200 Hz) underwater channel sound reflection by ocean mountains and islands are presented. lt is investigated also sound penetration into shallow water. Transformation of vertical structure of sound field over continental slope is considered. Continental slope and shelf-wedge reflection coefficients of law frequency sound propagating in the underwater waveguide were measured. Results of the work show that low-frequency sound reflections from large-scale bottom irregularities can be important in ocean acoustics.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.