Side-scan sonar (SSS) images are difficult for automatic analysis due to the acoustic measurement parameters as well as the number of different objects that can be distant. In addition, there is a risk that the seabed analysis application may be attacked. For this purpose, we propose a solution based on convolutional neural networks with bilinear pooling in order to achieve higher values of classification accuracy. Bilinear pooling merge data from two networks and return classification results. The first network’s branch receives the original image and the second one after applying the superpixel method. This approach allows to focus on different types of features. In addition, we introduced a mechanism of poisoning detection that analyze images and results from the network. For the evaluation process, we used the real SSS images obtained between two water channels in Szczecin city in north-western Poland. The importance of scientific research indicates the accuracy of the analysis as well as the safety of the measurements performed.

Side-scan sonar generates an image based on the reflection of sound waves. The reflection takes place with the first encountered object, which, in practice, may be a passing fish or even a wave from the boat turbine. Therefore, such data are sensitive to all noises. In this article, we propose a real-time automatic system of side-scan sonar analysis that can detect and classify different objects. Our proposition is based on the processing of a given image to quickly verify whether there is anything other than the bottom of the river/sea. If so, this image is analyzed in terms of regions of interest (ROIs) by the histogram module. This action allows the extraction of only objects of interest, which are then classified by convolutional neural networks (CNNs). A proposed model also contains an automatic mechanism of adding the sample to the database in order to later guarantee the accuracy of the classifiers. The model is a hybridization of image processing techniques with a machine learning approach to analyze difficult images. The presented system has been tested on the bottom of a river in Szczecin, Poland. We reached 90% of accurate classification in case scenario and 88% in simulation on used datasets. The obtained results were presented and discussed in terms of the advantages of practical application in analyzing side-scan sonar images.

Ship detection and tracking is a basic task in any vessel traffic monitored area, whether marine or inland. It has a major impact on navigational safety and thus different systems and technologies are used to determine the best possible methods of detecting and identifying sailing units. Video monitoring is present in almost all of them, but it is usually operated manually and is used as a backup system. This is because of the difficulties in implementing an efficient and universal automatic detection method that would work in quickly alternating environmental conditions for all kind of sailing units—from kayaks to seagoing merchant vessels. This paper presents a method that allows the detection and tracking of ships using the video streams of existing monitoring systems for ports and rivers. The method and the results of experiments on three sets of data using cameras with different characteristics, settings, and scene locations are presented. The experiments were carried out in variable light and weather conditions, and a wide range of unit types were used as detection objectives. The results confirm the usability of the proposed solution; however, some minor issues were encountered in the presence of ships wakes or highly unfavourable weather conditions.

The article presents a method to determine the position of mechanically scanned sonar images by comparing them with the database of simulated synthetic images. The synthetic images are generated from high-density bathymetric data coming from the same fragment of water region, using the ray tracing method. The article discusses the issues related to the choice of the probability function as the method of image comparing which allows to find the correct georeference of the real image. For the correlation method and the logical conjunction method, which are believed to give the best results, detailed studies were performed, including boundary cases. The obtained results of matching are presented in tabular and graphic form.

The article presents the watercraft recognition and identification system as an extension for the presently used visual water area monitoring systems, such as VTS (Vessel Traffic Service) or RIS (River Information Service). The watercraft identification systems (AIS - Automatic Identification Systems) which are presently used in both sea and inland navigation require purchase and installation of relatively expensive transceivers on ships, the presence of which is not formally required as equipment of unconventional watercrafts, such as yachts, motor boats, and other pleasure crafts. These watercrafts may pose navigation or even terrorist threat, can be the object of interest of the customs, or simply cause traffic problems on restricted water areas. The article proposes extending the traffic supervision system by a module which will identify unconventional crafts based on video monitoring. Recognition and identification will be possible through the use of image identification and processing methods based on artificial intelligence algorithms, among other tools. The system will be implemented as independent service making use of the potential of SOA (Service Oriented Architecture) and XML/SOAP (Extensible Markup Language/Simple Object Access Protocol) technology.