Comparative Analysis of Selected Geostatistical Methods for Bottom Surface Modeling.

Digital bottom models are commonly used in many fields of human activity, such as navigation, harbor and offshore technologies, or environmental studies. In many cases, they are the basis for further analysis. They are prepared based on bathymetric measurements, which in many cases have the form of large datasets. Therefore, various interpolation methods are used for calculating these models. In this paper, we present the analysis in which we compared selected methods for bottom surface modeling with a particular focus on geostatistical methods. The aim was to compare five variants of Kriging and three deterministic methods. The research was performed with real data acquired with the use of an autonomous surface vehicle. The collected bathymetric data were reduced (from about 5 million points to about 500 points) and analyzed. A ranking approach was proposed to perform a complex and comprehensive analysis integrating typically used error statistics-mean absolute error, standard deviation and root mean square error. This approach allowed the inclusion of various views on methods of assessment while integrating various metrics and factors. The results show that geostatistical methods perform very well. The best results were achieved with the modifications of classical Kriging methods, which are disjunctive Kriging and empirical Bayesian Kriging. For these two methods, good statistics were calculated compared to other methods (for example, the mean absolute error for disjunctive Kriging was 0.23 m, while for universal Kriging and simple Kriging, it was 0.26 m and 0.25 m, respectively). However, it is worth mentioning that interpolation based on radial basis function in some cases is comparable to Kriging in its performance. The proposed ranking approach was proven to be useful and can be utilized in the future for choosing and comparing DBMs, mostly in mapping and analyzing seabed changes, for example in dredging operations. The research will be used during the implementation of the new multidimensional and multitemporal coastal zone monitoring system using autonomous, unmanned floating platforms. The prototype of this system is at the design stage and is expected to be implemented.

Testing the Effect of Bathymetric Data Reduction on the Shape of the Digital Bottom Model.

Depth data and the digital bottom model created from it are very important in the inland and coastal water zones studies and research. The paper undertakes the subject of bathymetric data processing using reduction methods and examines the impact of data reduction according to the resulting representations of the bottom surface in the form of numerical bottom models. Data reduction is an approach that is meant to reduce the size of the input dataset to make it easier and more efficient for analysis, transmission, storage and similar. For the purposes of this article, test datasets were created by discretizing a selected polynomial function. The real dataset, which was used to verify the analyzes, was acquired using an interferometric echosounder mounted on a HydroDron-1 autonomous survey vessel. The data were collected in the ribbon of Lake Klodno, Zawory. Data reduction was conducted in two commercial programs. Three equal reduction parameters were adopted for each algorithm. The research part of the paper presents the results of the conducted analyzes of the reduced bathymetric datasets based on the visual comparison of numerical bottom models, isobaths, and statistical parameters. The article contains tabular results with statistics, as well as the spatial visualization of the studied fragments of numerical bottom models and isobaths. This research is being used in the course of work on an innovative project that aims to develop a prototype of a multi-dimensional and multi-temporal coastal zone monitoring system using autonomous, unmanned floating platforms at a single survey pass.

Sensors and Sensor's Fusion in Autonomous Vehicles.

Autonomous vehicle navigation has been at the center of several major developments, both in civilian and defense applications [...].

Auto-Refining Reconstruction Algorithm for Recreation of Limited Angle Humanoid Depth Data.

With the majority of research, in relation to 3D object reconstruction, focusing on single static synthetic object reconstruction, there is a need for a method capable of reconstructing morphing objects in dynamic scenes without external influence. However, such research requires a time-consuming creation of real world object ground truths. To solve this, we propose a novel three-staged deep adversarial neural network architecture capable of denoising and refining real-world depth sensor input for full human body posture reconstruction. The proposed network has achieved Earth Mover and Chamfer distances of 0.059 and 0.079 on synthetic datasets, respectively, which indicates on-par experimental results with other approaches, in addition to the ability of reconstructing from maskless real world depth frames. Additional visual inspection to the reconstructed pointclouds has shown that the suggested approach manages to deal with the majority of the real world depth sensor noise, with the exception of large deformities to the depth field.

Classification of Non-Conventional Ships Using a Neural Bag-Of-Words Mechanism.

The existing methods for monitoring vessels are mainly based on radar and automatic identification systems. Additional sensors that are used include video cameras. Such systems feature cameras that capture images and software that analyzes the selected video frames. Methods for the classification of non-conventional vessels are not widely known. These methods, based on image samples, can be considered difficult. This paper is intended to show an alternative way to approach image classification problems; not by classifying the entire input data, but smaller parts. The described solution is based on splitting the image of a ship into smaller parts and classifying them into vectors that can be identified as features using a convolutional neural network (CNN). This idea is a representation of a bag-of-words mechanism, where created feature vectors might be called words, and by using them a solution can assign images a specific class. As part of the experiment, the authors performed two tests. In the first, two classes were analyzed and the results obtained show great potential for application. In the second, the authors used much larger sets of images belonging to five vessel types. The proposed method indeed improved the results of classic approaches by 5%. The paper shows an alternative approach for the classification of non-conventional vessels to increase accuracy.

Processing of Bathymetric Data: The Fusion of New Reduction Methods for Spatial Big Data.

Floating autonomous vehicles are very often equipped with modern systems that collect information about the situation under the water surface, e.g., the depth or type of bottom and obstructions on the seafloor. One such system is the multibeam echosounder (MBES), which collects very large sets of bathymetric data. The development and analysis of such large sets are laborious and expensive. Reduction of the spatial data obtained from bathymetric and other systems collecting spatial data is currently widely used. In commercial programs used in the development of data from hydrographic systems, methods of interpolation to a specific mesh size are very frequently used. The authors of this article previously proposed original the true bathymetric data reduction method (TBDRed) and Optimum Dataset (OptD) reduction methods, which maintain the actual position and depth for each of the measured points, without their interpolation. The effectiveness of the proposed methods has already been presented in previous articles. This article proposes the fusion of original reduction methods, which is a new and innovative approach to the problem of bathymetric data reduction. The article contains a description of the methods used and the methodology of developing bathymetric data. The proposed fusion of reduction methods allows the generation of numerical models that can be a safe, reliable source of information, and a basis for design. Numerical models can also be used in comparative navigation, during the creation of electronic navigation maps and other hydrographic products.

Automatic Classification Using Machine Learning for Non-Conventional Vessels on Inland Waters.

The prevalent methods for monitoring ships are based on automatic identification and radar systems. This applies mainly to large vessels. Additional sensors that are used include video cameras with different resolutions. Such systems feature cameras that capture images and software that analyze the selected video frames. The analysis involves the detection of a ship and the extraction of features to identify it. This article proposes a technique to detect and categorize ships through image processing methods that use convolutional neural networks. Tests to verify the proposed method were carried out on a database containing 200 images of four classes of ships. The advantages and disadvantages of implementing the proposed method are also discussed in light of the results. The system is designed to use multiple existing video streams to identify passing ships on inland waters, especially non-conventional vessels.

Automatic ship classification for a riverside monitoring system using a cascade of artificial intelligence techniques including penalties and rewards.

Riverside monitoring systems are used for controlling the passage of ships, counting them to prevent overcrowding in a port, or raising an alarm if the ship is unknown or not safe. This type of control and analysis is commonly carried out by many people who supervise CCTV in real time. In this paper, we present an alternative approach to automatic image analysis using a variety of artificial intelligence techniques. Based on collaborative learning, these are punished if they make an incorrect classification. The main advantage is the possibility of continually increasing the amount of knowledge during system operation. However, overtraining is possible, so each time, the best classifier is chosen. Another advantage for practical use is the small database, which allows for the quick and practical implementation of such a system. To verify its effectiveness, this ship classification system was tested on data obtained in a Polish city, Szczecin, as part of a bigger project for classifying inland ships and publicly available databases (for more general ship problems).

Quality of Life Assessment in Students from Polish Universities during the COVID-19 Pandemic According to WHO Quality of Life Questionnaire.

The outbreak of COVID-19 in December 2019 in China influenced the lives of people all over the world. Many had to face the completely new situation of lockdown. These changes influenced many aspects of life. Students' quality of life changed as well. The aim of the study was to assess the differences in the quality of life of students with regard to the field of study and the knowledge regarding medicine. The study population consisted of 500 students from three Polish universities (Medical University of Silesia, Maritime University of Szczecin and Adam Mickiewicz University, Poznan). Study participants were invited to fill in an online cross-sectional quality of life questionnaire (WHOQOL-BREF) created by the World Health Organization (WHO). The analysis was done using the IBM SPSS Statistics 25.0 programme. The obtained results showed differences in respondents' reactions in two domains. The lowest resistance to the critical situation was observed in women who studied at the technical university. Higher values of resistance were observed in women studying medical sciences.