A prerequisite for solving issues associated with surf zone variability, which affect human activity in coastal zones, is an accurate estimation of the effects of coastal protection methods. Therefore, performing frequent monitoring activities, especially when applying new nature-friendly coastal defense methods, is a major challenge. In this manuscript, we propose a pipeline for performing low-cost monitoring using RGB images, accessed by an unmanned aerial vehicle (UAV) and a four-level analysis architecture of an underwater object detection methodology. First, several color-based pre-processing activities were applied. Second, contrast-limited adaptive histogram equalization and the Hough transform methodology were used to automatically detect the underwater, circle-shaped elements of a hybrid coastal defense construction. An alternative pipeline was used to detect holes in the circle-shaped elements with an adaptive thresholding method; this pipeline was subsequently applied to the normalized images. Finally, the concatenation of the results from both the methods and the validation processes were performed. The results indicate that our automated monitoring tool works for RGB images captured by a low-cost consumer UAV. The experimental results showed that our pipeline achieved an average error of four pixels in the test set.

The burgeoning demand for critical metals used in high-tech and green technology industries has turned attention toward the vast resources of polymetallic nodules on the ocean floor. Traditional methods for estimating the abundance of these nodules, such as direct sampling or acoustic imagery are time and labour-intensive or often insufficient for large-scale or accurate assessment. This paper advocates for the automatization of polymetallic nodules detection and abundance estimation using deep learning algorithms applied to seabed photographs. We propose UNET convolutional neural network framework specifically trained to process the unique features of seabed imagery, which can reliably detect and estimate the abundance of polymetallic nodules based on thousands of seabed photographs in significantly reduced time (below 10 h for 30 thousand photographs). Our approach addresses the challenges of data preparation, variable image quality, coverage-abundance transition model and sediments presence. We indicated the utilization of this approach can substantially increase the efficiency and accuracy of resource estimation, dramatically reducing the time and cost currently required for manual assessment. Furthermore, we discuss the potential of this method to be integrated into large-scale systems for sustainable exploitation of these undersea resources.

An important problem associated with the aerial mapping of the seabed is the precise classification of point clouds characterizing the water surface, bottom, and bottom objects. This study aimed to improve the accuracy of classification by addressing the asymmetric amount of data representing these three groups. A total of 53 Synthetic Minority Oversampling Technique (SMOTE) algorithms were adjusted and evaluated to balance the amount of data. The prepared data set was used to train the Multi-Layer Perceptron (MLP) neural network used for classifying the point cloud. Data balancing contributed to significantly increasing the accuracy of classification. The best overall classification accuracy achieved varied from 95.8% to 97.0%, depending on the oversampling algorithm used, and was significantly better than the classification accuracy obtained for unbalanced data and data with downsampling (89.6% and 93.5%, respectively). Some of the algorithms allow for 10% increased detection of points on the objects compared to unbalanced data or data with simple downsampling. The results suggest that the use of selected oversampling algorithms can aid in improving the point cloud classification and making the airborne laser bathymetry technique more appropriate for seabed mapping.

The human activities in the offshore oil and gas, renewable energy and construction industry require reliable data acquired by different types of hydrographic sensors: DGNSS (Differential Global Navigation Satellite System) positioning, attitude sensors, multibeam sonars, lidars or total stations installed on the offshore vessel, drones or platforms. Each component or sensor that produces information, unique to its position, will have a point that is considered as the reference point of that sensor. The accurate measurement of the offsets is vital to establish the mathematical relation between sensor and vessel common reference point in order to achieve sufficient accuracy of the survey data. If possible, the vessel will be put on a hard stand so that it can be very accurately measured using the standard land survey technique. However, due to the complex environment and sensors being mobilized when the vessel is in service, this may not be possible, and the offsets will have to be measured in sea dynamic conditions by means of a total station from a floating platform. This article presents the method of transformation by similarity with elements of affine transformation, called Q-ST (Quasi-Similarity Transformation). The Q-ST has been designed for measurements on such unstable substrates when it is not possible to level the total station (when the number of adjustment points is small (4–6 points)). Such situation occurs, among others, when measuring before the offshore duties or during the jack up or semi-submersible rig move. The presented calculation model is characterized by zero deviations at the adjustment points (at four common points). The transformation concerns the conversion of points between two orthogonal and inclined reference frames. The method enables the independent calculation of the scale factor, rotation matrix and system translation. Scaling is performed first in real space, and then both systems are shifted to the centroid, which is the center of gravity. The center of gravity is determined for the fit points that meet the criterion of stability of the orthogonal transformation. Then, the rotation matrix is computed, and a translation is performed from the computational (centroid) to real space. In the applied approach, the transformation parameters, scaling, rotation and translation, are determined independently, and the least squares method is applied independently at each stage of the calculations. The method has been verified in laboratory conditions as well as in real conditions. The results were compared to other known methods of coordinate transformation. The proposed approach is a development of the idea of transformation by similarity based on centroids.