A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification

Due to the strong speckle noise caused by the seabed reverberation which makes it difficult to extract discriminating and noiseless features of a target, recognition and classification of underwater targets using side-scan sonar (SSS) images is a big challenge. Moreover, unlike classification of optical images which can use a large dataset to train the classifier, classification of SSS images usually has to exploit a very small dataset for training, which may cause classifier overfitting. Compared with traditional feature extraction methods using descriptors—such as Haar, SIFT, and LBP—deep learning-based methods are more powerful in capturing discriminating features. After training on a large optical dataset, e.g., ImageNet, direct fine-tuning method brings improvement to the sonar image classification using a small-size SSS image dataset. However, due to the different statistical characteristics between optical images and sonar images, transfer learning methods—e.g., fine-tuning—lack cross-domain adaptability, and therefore cannot achieve very satisfactory results. In this paper, a multi-domain collaborative transfer learning (MDCTL) method with multi-scale repeated attention mechanism (MSRAM) is proposed for improving the accuracy of underwater sonar image classification. In the MDCTL method, low-level characteristic similarity between SSS images and synthetic aperture radar (SAR) images, and high-level representation similarity between SSS images and optical images are used together to enhance the feature extraction ability of the deep learning model. Using different characteristics of multi-domain data to efficiently capture useful features for the sonar image classification, MDCTL offers a new way for transfer learning. MSRAM is used to effectively combine multi-scale features to make the proposed model pay more attention to the shape details of the target excluding the noise. Experimental results of classification show that, in using multi-domain data sets, the proposed method is more stable with an overall accuracy of 99.21%, bringing an improvement of 4.54% compared with the fine-tuned VGG19. Results given by diverse visualization methods also demonstrate that the method is more powerful in feature representation by using the MDCTL and MSRAM.

SURVEI SIDE SCAN SONAR DALAM PENELITIAN ARKEOLOGI BAWAH AIR DI PERAIRAN SUNGAI: STUDI KASUS PADA DAERAH ALIRAN SUNGAI BRANTAS [SIDE SCAN SONAR SURVEY IN RIVERINE UNDERWATER ARCHAEOLOGICAL RESEARCH: CASE STUDY IN THE BRANTAS BASIN]

Aplikasi metode geofisika menggunakan side scan sonar dalam penelitian arkeologi bawah air belum banyak dilakukan di Indonesia. Tulisan ini memaparkan penggunaan side scan sonar untuk pemetaan dasar sungai dan identifikasi tinggalan arkeologi di dasar sungai dalam penelitian “Sungai Brantas dalam Perspektif Lanskap Kultur Maritim”, serta interpretasi hasil survei side scan sonar tersebut dalam konteks kesejarahan. Selain itu, dalam tulisan ini akan dibahas potensi pengembangan penggunaan side scan sonar dalam penelitian arkeologi bawah air di Indonesia, terutama di perairan sungai. Akuisisi data dilakukan dengan menggunakan side scan sonar Starfish 450H dengan sistem posisi GNSS Trimble R8s. Sementara itu, interpretasi diperoleh dengan melakukan analisis terhadap data peta dan arsip Belanda untuk memahami konteks temporal dari objek yang dideteksi oleh alat side scan sonar. Survei berhasil menunjukkan sedimen di dasar sungai berupa lempung dan lanau, serta beberapa objek yang diduga sebagai bangkai kapal, yang diperkirakan berasal dari pasca abad ke-19 Masehi. Hasil survei side scan sonar menunjukkan tingkat akurasi cukup hingga tinggi dan dapat menjadi pendukung penelitian arkeologi bawah air yang efisien, terutama di perairan yang keruh. Side scan sonar survey as one of the geophysics methods is still scarcely applied in underwater archaeological research in Indonesia. This paper describes the application of side scan sonar survey in mapping riverbed and identifying underwater archaeological remains in the “Sungai Brantas in the Perspective of Maritime Cultural Landscape” project, as well as interpreting its historical context based on survey results. This paper also explores the development of utilizing side scan sonar in underwater archaeological research in Indonesia, particularly in rivers. Data was acquisitioned by using the side scan sonar Starfish 450H and GNSS Trimble R8s positioning system. The interpretation was drawn by analysing related Dutch old maps and archives to understand the historical context of the survey findings. The result shows clay and silt sediment covering most of the riverbed and a number of objects, possibly shipwrecks, estimated as from the nineteenth century. The survey result has a medium to high accuracy. Thus, this method is able to serve as an efficient instrument for underwater archaeological research, especially in the low-visibility waters.

Side-scan sonar image processing: Seabed classification based on acoustic backscattering

The smoothness of vessel traffic flow is the most important thing in the shipping industry of port. Traffic problems are commonly solved by development and maintenance programs. Seabed conditions in the port-channel should be known to be considered in port development and maintenance programs related to port efficiency, safety navigation, and berthing. The objective of this paper is to characterize seabed into several classes of geological features. The Seabed condition and characteristics are classified based on image processing of side scan sonar data. The image processing will extract pixel value parameters; intensity, entropy, and standard deviation. Classification use combination of these pixel view parameter to define each class. Seabed classification has been successfully carried out in Teluk Bayur Port and classified into five classes, sandy silt, silty sand, fine sand, coarse sand, and rocks or reefs. Indication of crack or shallow structure was also identified. These results of classification are necessary to verify by sediment sampling and visual inspection, and then it should be reclassified to become a valid classification.

Vertical Configuration of a Side Scan Sonar for the Monitoring of Posidonia oceanica Meadows

Posidonia oceanica meadows are ecosystem engineers that play several roles in marine environment maintenance. In this sense, monitoring of the spatial distribution and health status of their meadows is key to make decisions about protecting them against their degradation. With the aim of checking the ability of a simple low-cost acoustic method to acquire information about the state of P. oceanica meadows as ecosystem indicators, ground-truthing and acoustic data were acquired over several of these meadows on the Levantine coast of Spain. A 200 kHz side scan sonar in a vertical configuration was used to automatically estimate shoot density, canopy height and cover of the meadows. The wide athwartship angle of the transducer together with its low cost and user friendliness entail the main advantages of this system and configuration: both improved beam path and detection invariance against boat rolling. The results show that canopy height can be measured acoustically. Furthermore, the accumulated intensity of the echoes from P. oceanica in the first 30 centimeters above the bottom is indirectly related to shoot density and cover, showing a relation that should be studied deeply.

THE SHIP WRECK OF THE LATE 4th / EARLY 3rd CENTURY BC NEAR KINBURN SPIT

During the campaign of 2018 the international underwater archaeological expedition has explored the waters of Tendra Spit and Kinburn Spit on the shelf of the Black Sea, in Mykolaiv and Kherson regions of Ukraine. Underwater archaeological exploration focused on the waters near the northern tip of Tendra Spit, from both the Gulf of Tendra and the sea, and north-western tip of Kinburn Spit. In addition to the visual reconnaissance, divers were using sonar, profiler and side-scan sonar. As a result, the bathymetric map has been compiled. In the initial part of research the work was limited to mapping and taking photographs of the discoveries. During these works was discovered and cleansed the ancient Shipwreck of the late 4th — early 3rd century BC. It was possible to identify the well-preserved fragment of the hull of ancient Wreck of a length of 9.45 m in situ with ballast stones, ceramic material from the cargo, lead plating and him constructions elements. After clearing of the sand from the preserved part of the ship hull with the help of a hydro injector the video and photo documentation was carried out. As a result of these works, large-scale photo mosaic of the object and its 3D-model were made. The condition of the wooden hull is excellent, the technological holes, connections, bronze and iron nails are preserved. Outside of Ukraine several shipwrecks of the same period are attested. The best studied are the following: shipwreck of the 3rd century BC at Grand Congloue, France; the Mazotos shipwreck of the 4th century BC in Cyprus; the Porticello shipwreck of the end of the 5th or beginning of the 4th century BC in Italy; the Alonnisos shipwreck from the end of the 5th century BC, Greece; the Kyrenia shipwreck from the end of the 4th — beginning of the 3rd centuries BC in Cyprus. In the Black Sea, in 2011 a shipwreck from the end of the 4th — beginning of the 3rd centuries BC near Eregli, Turkey (ancient Herakleia Pontica) was discovered by a deep-sea expedition of the research vessel «Nautilus» under the direction of Michael Brennan at a depth of 101 m. Most of the known merchant ships of this period were small, ranging from 12 to 17 m (table). Boris Peters provides a reconstruction sketch of the Lake Donuzlav ship of the late 4th — early 3rd centuries BC. It is almost identical to the reconstruction of the Kyrenia merchant ship, based on its hull which was preserved by 75 %, The replica named «Kyrenia 2» was built and made several voyages. It can be assumed that the Kinburn Spit ship found in 2018 was of similar appearance but further research will provide more detailed information.

Determination of the bottom scattering coefficient discontinuity lines in the multibeam ocean sounding

In this paper the problems of constructing sonar images of the seabed according to measurements of the multibeam side scan sonar are considered. The inverse problem for the non-stationary equation of radiation transfer with the diffuse reflection conditions at the boundary which consists in finding the discontinuity lines of the bottom scattering coefficient is investigated. A numerical algorithm for solving the inverse problem is developed, and an analysis of the quality of reconstructing the boundaries of inhomogeneities of the seabed is carried out, depending on the number of views and the width of a radiation pattern and the sounding range.

Integrating Underwater Data into GIS for Offshore Decommissioning in Bass Strait, Australia

Through asset lifecycle, data is collected for a variety of purposes across multiple disciplines, and exists in various formats and repositories. Decommissioning projects utilize and repurpose a multitude of these datasets; from use in analysis and planning, to facilitating systematic environmental assessments, and meaningful discussion with stakeholders. The key challenge is how do we consolidate historical data, incorporate new data, and make it evergreen to support planning and informed decision making; and how do we coordinate large volumes of previously disparate data in a meaningful way for all users with a simple access model? A team of geographic information system (GIS) practitioners and subject matter contacts in technical and health, safety and environment (HSE) disciplines was convened to collect, sort, and compile known historical offshore data, including, but not limited to; pipeline and structural inspections and environmental studies, all captured via Remote Operated Vehicle (ROV), Side Scan Sonar (SSS), and sampling programs. Data was reformatted to standardize headers and attributes allowing for merging of existing like-data and to support new data integration. To this end, we also worked collaboratively with vendors to optimize data collection and improve alignment with our internal data structures. The Esri GIS technology was utilized for data integration, specifically the web and mobile environments. Through these environments, non-GIS users could easily access data and focused applications, supporting ease of data visualization and allowing for a single view of data spanning decades and covering multiple themes. This enabled an enhanced understanding of the offshore environment, allowing us to identify gaps and focus areas for future data capture, helping to facilitate cross-discipline discussions, and identification of operational synergies; improving access, efficiency, and reducing decommissioning costs. Data integration resulting from this initiative and delivery through a spatially aware GIS environment is providing unprecedented access to a vast scope of cross-disciplinary data previously not possible with more traditional engineering methods and data formats. Data accessibility aids communication, and when combined with early engagement across multi-disciplinary teams, the path to decision making is reduced, synergies gained, and costs are reduced through improved efficiency and optimization.

An AUV Path Planner for Large-scale Search and Rescue based on A* Algorithm

For large-scale search and rescue (SAR) tasks that require complete coverage of the workspace, it is important to increase the efficiency and obtained sensor data quality. A novel path planner named SAR-A* to this problem is introduced, which takes into account the sensor performance and practical prior information. Firstly, the workspace is decomposed into plenty of hexagonal cells which are treated as waypoints for A* algorithm. Target present probability is then modeled to Gaussian distribution and the performance of the side-scan sonar (SSS) is evaluated. The proposed path planner is validated in a complex terrain scenario which proves that the SAR-A* path planner can increase confidence in locating the target quickly, and is suitable for the large-scale SAR.

A Preliminary Survey of the Eastern Harbor, Alexandria, Egypt, Including a Comparison of Side Scan Sonar and Remote Viewing

This paper reports a preliminary survey of one of humanity's most historic harbors--Alexandria, Egypt. It constitutes one phase of a broader joint land/sea examination of the largest and most famous city to bear Alexander the Great's name. The research overall had two goals: 1) to resolve locational uncertainties concerning the city's past configuration, particularly its Ptolemaic antecedents; and 2) to compare electronic remote sensing survey technologies with Remote Viewing generally, and the applications methodology developed by the Mobius Groups specifically. In the area of the Eastern Harbor, the aim of the research was: 1) the location of the ancient shore line; the locaton of and predictive description of several sites including the island of Antirrhodus and the Emporium/Poseidium/Timonium complex; a palace complex associated with Cleopatra; and a further elaboration, both in terms of location and predictive description, of the Pharos lighthouse area; 2) a comparison of Remote Viewing and side scan sonar data after each approach had surveyed the same area. This paper describes the probable location of the Emporium, the Poseidium, and the Timonium, the palace complex of Cleopatra, the island of Antirrhodus, a site at the tip of Fort Sisila (known prevously as Point Lochias), new discoveries pertaining to the lighthouse, andd an associated temple. The most important discovery though is the identification and location of the ancient seawall which extends some 65 meters farther out into the harbor than was previously suspected, and whoe location resolves a key piece in the puzzle of the ancient city's layout. The discoveries reported here were principally the result of Remote Viewing. Except for one clear "hit," side scan sonar proved unproductive because of the large amount of particulate in the water.

A Mosaic Method for Side-Scan Sonar Strip Images Based on Curvelet Transform and Resolution Constraints

Due to the complex marine environment, side-scan sonar signals are unstable, resulting in random non-rigid distortion in side-scan sonar strip images. To reduce the influence of resolution difference of common areas on strip image mosaicking, we proposed a mosaic method for side-scan sonar strip images based on curvelet transform and resolution constraints. First, image registration was carried out to eliminate dislocation and distortion of the strip images. Then, the resolution vector of the common area in two strip images were calculated, and a resolution model was created. Curvelet transform was then performed for the images, the resolution fusion rules were used for Coarse layer coefficients, and the maximum coefficient integration was applied to the Detail layer and Fine layer to calculate the fusion coefficients. Last, inverse Curvelet transform was carried out on the fusion coefficients to obtain images in the fusion area. The fusion images in multiple areas were then combined in the registered images to obtain the final image. The experiment results showed that the proposed method had better mosaicking performance than some conventional fusion algorithms.