One of the leading causes of overfishing is the catch of unwanted fish and marine life in commercial fishing gears. Echosounders are nowadays routinely used to detect fish schools and make qualitative estimates of the amount of fish and species present. However, the problem of estimating sizes using acoustic systems is still largely unsolved, with only a few attempts at real-time operation and only at demonstration level. This paper proposes a novel image-based method for individual fish detection, targeted at drastically reducing catches of undersized fish in commercial trawling. The proposal is based on the processing of stereo images acquired by the Deep Vision imaging system, directly placed in the trawl. The images are pre-processed to correct for nonlinearities of the camera response. Then, a Mask R-CNN architecture is used to localize and segment each individual fish in the images. This segmentation is subsequently refined using local gradients to obtain an accurate estimate of the boundary of every fish. Testing was conducted with two representative datasets, containing in excess of 2600 manually annotated individual fish, and acquired using distinct artificial illumination setups. A distinctive advantage of this proposal is the ability to successfully deal with cluttered images containing overlapping fish.

Microbathymetry data, in situ observations, and sampling along the 13°20′N and 13°20′N oceanic core complexes (OCCs) reveal mechanisms of detachment fault denudation at the seafloor, links between tectonic extension and mass wasting, and expose the nature of corrugations, ubiquitous at OCCs. In the initial stages of detachment faulting and high‐angle fault, scarps show extensive mass wasting that reduces their slope. Flexural rotation further lowers scarp slope, hinders mass wasting, resulting in morphologically complex chaotic terrain between the breakaway and the denuded corrugated surface. Extension and drag along the fault plane uplifts a wedge of hangingwall material (apron). The detachment surface emerges along a continuous moat that sheds rocks and covers it with unconsolidated rubble, while local slumping emplaces rubble ridges overlying corrugations. The detachment fault zone is a set of anostomosed slip planes, elongated in the along‐extension direction. Slip planes bind fault rock bodies defining the corrugations observed in microbathymetry and sonar. Fault planes with extension‐parallel stria are exposed along corrugation flanks, where the rubble cover is shed. Detachment fault rocks are primarily basalt fault breccia at 13°20′N OCC, and gabbro and peridotite at 13°30′N, demonstrating that brittle strain localization in shallow lithosphere form corrugations, regardless of lithologies in the detachment zone. Finally, faulting and volcanism dismember the 13°30′N OCC, with widespread present and past hydrothermal activity (Semenov fields), while the Irinovskoe hydrothermal field at the 13°20′N core complex suggests a magmatic source within the footwall. These results confirm the ubiquitous relationship between hydrothermal activity and oceanic detachment formation and evolution.

This paper presents a novel image classification scheme for benthic coral reef images that can be applied to both single image and composite mosaic datasets. The proposed method can be configured to the characteristics (e.g., the size of the dataset, number of classes, resolution of the samples, color information availability, class types, etc.) of individual datasets. The proposed method uses completed local binary pattern (CLBP), grey level co-occurrence matrix (GLCM), Gabor filter response, and opponent angle and hue channel color histograms as feature descriptors. For classification, either k-nearest neighbor (KNN), neural network (NN), support vector machine (SVM) or probability density weighted mean distance (PDWMD) is used. The combination of features and classifiers that attains the best results is presented together with the guidelines for selection. The accuracy and efficiency of our proposed method are compared with other state-of-the-art techniques using three benthic and three texture datasets. The proposed method achieves the highest overall classification accuracy of any of the tested methods and has moderate execution time. Finally, the proposed classification scheme is applied to a large-scale image mosaic of the Red Sea to create a completely classified thematic map of the reef benthos.

Detecting already-visited regions based on their visual appearance helps reduce drift and position uncertainties in robot navigation and mapping. Inspired from content-based image retrieval, an efficient approach is the use of visual vocabularies to measure similarities between images. This way, images corresponding to the same scene region can be associated. State-of-the-art proposals that address this topic use prebuilt vocabularies that generally require a priori knowledge of the environment. We propose a novel method for appearance-based navigation and mapping where the visual vocabularies are built online, thus eliminating the need for prebuilt data. We also show that the proposed technique allows efficient loop-closure detection, even at small vocabulary sizes, resulting in a higher computational efficiency.