Scan Sonar Research Articles

Geophysical surveys and satellite imaging for the evaluation of near‐surface terrain dynamic – A case study on Grand Portage, MN, USA

AbstractFlooding, erosion and increases in the water level in Lake Superior have contributed to changes in the stem location and width of the Grand Portage Creek. Those events threaten parts of the Grand Portage National Monument, a historically significant site on the North Shore of Lake Superior, Minnesota. We performed geophysical surveys to investigate these dynamic effects. We studied the near‐surface geological deposits, the mechanisms associated with creek stem dynamics and sediment transport, as well as deposition along the lakeshore in Grand Portage Bay. We deployed ground‐penetrating radar (GPR), sub‐bottom profiler, side scan sonar, Geoprobe coring and Van Veen grab samplers and evaluated time‐lapse satellite images to assess the interaction of the Grand Portage Creek with the Grand Portage Bay. The onshore GPR surveys next to the national monument, the creek and the shoreline showed the presence of a complex deposition with eroded ground surfaces and sediment layers across the creek valley. Results from the offshore geophysical campaigns and the interpretations of satellite images also document a heterogeneous deposition sequence environment with fine‐grained sediment deposits present south and southwest of the creek mouth. In addition, we documented an exposed boulder bed towards the east of the creek mouth that was exposed by the current and wave‐driven erosion process in the Grand Portage Bay. Time‐lapse satellite images and hydraulic current velocity simulations validate these observations and provide insight into how anthropogenic activities and natural events interact and might contribute to the long‐term stability of a site of historical and cultural importance.

Evaluating the use of side scan sonar for improved detection and targeted retrieval of abandoned, lost, or otherwise discarded fishing gear

Abandoned, lost, or otherwise discarded fishing gear (ALDFG) has surfaced as a significant conservation issue that continues to compromise the economic, social, and ecological aspects of the marine environment. To alleviate these concerns, methods of lost gear detection at the seabed can be applied to increase the precision of derelict gear retrieval and potentially improve the likelihood of success. Targeted in Canada's most productive American lobster (Homarus americanus) fishing area, a “hotspot” analysis was performed by mapping the density of reported lost gear at a 3 km × 3 km grid resolution. The hotspot analysis was used to target the collection of 27 side scan sonar (SSS) transects in Lobster Fishing Area (LFA) 34 over a 12-day survey period in Clark's Harbour, Nova Scotia, to evaluate the benefits of gear detection in large-scale retrieval missions. Following a comprehensive review of the SSS data post-processing, 114 potential ALDFG targets were visually identified, and only one item was confirmed retrieved. Despite this, a large volume of ALDFG was retrieved in areas where there was no SSS coverage based on fisher's local knowledge. The findings from this study demonstrate that retrieval of ALDFG based on SSS data can be difficult due to limitations of retrieval methods used, and that costs of SSS data acquisition may prohibit widescale use of this technology on an annual basis in spatially extensive fishing areas. Nonetheless, the use of SSS to identify ALDFG is recommended at smaller geographic scales in areas where the benthic environment may be sensitive. Although the use of fisher's local knowledge was not evaluated in this study, where the impacts of grappling for ALDFG are considered minimal, local knowledge can be extremely effective in the removal of lost fishing gear and other debris from the benthic environment.

Real-time underwater target detection for AUV using side scan sonar images based on deep learning

To overcome the shortcomings of traditional methods for underwater target detection in sonar images, a novel target detection algorithm based on deep learning is proposed for the real-time detection for an autonomous underwater vehicle equipped with a side scan sonar (SSS). First, the preprocessing of raw SSS images and data augmentation methods are proposed to improve the quality and quantity of the data set. Second, to improve the detection efficiency, a method based on threshold segmentation and pixel importance value is used to quickly determine whether there are suspected targets in the SSS images. Then, an MA-YOLOv7 network based on YOLOv7 with multi-scale information fusion and an attention mechanism is proposed to detect targets in the screened images, and a target localization method is proposed to obtain the location (latitude and longitude) of the target. Finally, the algorithm is verified through simulation experiments and field tests. The results demonstrate that the proposed algorithm achieves state-of-the-art performance and can be applied to real underwater tasks with a detection recall of 0.836 and time consumption of 0.355 s per image.

Distribution of boulders in coastal waters of Western Pomerania, German Baltic Sea

This study contributes to a better understanding of geogenic reef distribution in the southern Baltic Sea and highlights the implications of survey-related factors on automated boulder classification when utilizing data from multiple surveys. The distribution of hard grounds and reefs is needed as a baseline for geological and biological studies, but also for offshore construction, navigation and coastal management. In this study we provide maps of the distribution of geogenic reefs for about 750 km2 in the southern Baltic Sea, at the sites Wismar Bay, Darss Sill and Plantagenet Ground. The maps are based on full-coverage backscatter surveys with different side scan sonar and multibeam echo sounder systems. The distribution and number of boulders in the backscatter maps was determined using a convolutional neural network combined with quality control by human experts. The extent of the geogenic reefs was calculated on the basis of the number of boulders in 50 m x 50 m grid cells. We compare the results with previous reef maps based on point sampling, which show reefs of either biogenic or geogenic origin. According to the earlier maps, 11% of the Plantagenet Ground seabed was classified as reef habitat type. This is similar to the result of our study (12%), although we only considered reefs of geogenic origin. In the Darss Sill, geogenic reefs are larger in this study than in previous maps (30% versus 23%). In both regions, the spatial distribution of reefs differs significantly between old and new maps. For Wismar Bay, previous maps classify 3% of the seafloor as habitat type reef, whereas this study classifies 35% as geogenic reef. The use of automated classification during seafloor mapping allowed large areas to be interpreted in a few days. It also provided more information on the distribution of boulders within the geogenic reef. However, the boulder distribution maps show the negative effects of survey geometry, frequency and environmental conditions on automated boulder classification when data from different surveys are combined.

Density and abundance estimate of Antillean manatees (Trichechus manatus) within a landlocked lake in Southeastern México

Manatees are threatened along their range. In México, this species is listed as endangered. Manatee conservation strategies require density or occupancy estimates, especially in areas where species face survival risks. On turbid waters, like those found in rivers and lakes of the Southern Gulf of México coast, visual methods used to detect and count manatees underestimate actual numbers. Our goal was to estimate the density and abundance (N) of Antillean manatees in a small State Natural Protected Area, where a manatee population of unknown size inhabits. We performed line transects using a side scan sonar to detect animals and mark-recapture in the isolated population of manatees within Laguna de las Ilusiones, México, a landlocked lake that excludes transit. Using distance sampling from 14 boat trips, estimates of density and abundance were 15.5 manatees km-2 and 27 ± 5 manatees in the lake (CV ≈ 16.6 %). With MARK, from six capture events and 19 individual encounter records, the abundance estimated was 24 manatees (CV ≈ 16 to 24 %). Previous number of manatees were based only on visual surveys, which reported at least seven manatees. Density is lower than other similar studies along narrow waterways in important areas in México and other Central and South America countries. Studying this endangered subspecies is limited by cryptic habits, turbid waters, poor funding, and low densities, making density or abundance estimates difficult. However, within particular areas and established monitoring areas, these methods could be useful to generate baselines for conservation strategies.

Relating side scan sonar backscatter data to geotechnical properties for the investigation of surficial seabed sediments

Side scan sonar is a common tool for seafloor imaging and surveying due its efficiency and high resolution. The backscatter information from side scan sonar enables to identify sediment types and seabed roughness, often used to study sediment dynamics. Theory suggests that side scan sonar backscatter can be correlated to the geotechnical properties of the seabed surface. This could enhance the prediction of erodibility and efficiency of seabed sediment characterization, considering that side scan sonar can offer large spatial coverage in a short time. In this study, high-frequency (1000 kHz) side scan sonar backscatter data, sediment samples, and in-situ seabed strength profiles were collected of the seabed surface at ten locations. Statistical analysis of the backscatter data compared with geotechnical data showed trends between mean backscatter, soil strength, and textural sediment properties. Generally, mean backscatter increased when sediment strength and mean grain size increased and when water content and fines content decreased. However, roughness from bedforms, the presence of oysters, shell hash as well as variations in water content (i.e., porosity) of the seafloor heavily influenced the backscatter and sometimes masked any relationships with the strength properties directly.

Shallow structures, interactions, and recurrent vertical motions of active faults in Lingayen Gulf, Philippines

The surface trace of the East Zambales Fault (EZF) and its associated faults in the Lingayen Gulf have been previously mapped but no other characteristics were reported. This study utilized seismic reflection, multi-beam bathymetry, and side scan sonar to characterize the offshore EZF in terms of magnitudes of vertical displacement. Sequence stratigraphy and radiocarbon dates provided age constraints on the recurrence interval within the Holocene.The EZF extends for ∼ 57 km into the gulf, follows a north-northwest trend, and bounds the karstic terrane (west) and fluvio-deltaic deposits (east). Sinistral motion is indicated by: 1) normal and reverse drag geometries, 2) reversal in the sense of throw with depth, 3) flower structure, and 4) right-stepping and the uplift of a pressure ridge named Pudoc Bathymetric High. The Central Lingayen Gulf Fault (CLGF), to the east of EZF, follows the same trend. The Lingayen Gulf Transverse Fault (LGTF), oriented east–west, forms a flower structure with the CLGF. The EZF, CLGF, and LGTF combined form the Lingayen Gulf Fault System, which divides the gulf into five fault blocks where uplift and subsidence locally occurred.A paleo-delta at −60 m yielded an age of 6.8 kyBP, indicating it was formed during the first Holocene highstand. With natural compaction considered, fault-associated subsidence of 46–53 m may have occurred. The average Holocene vertical displacement is 2.1–2.2 m, which translates to a recurrence interval of 320–270 years for the fault system. The faults can likely generate earthquakes with magnitudes 7.5 (EZF), 6.7 (CLGF), and 6.6 (LGTF).

Automatic tracking method for submarine cables and pipelines of AUV based on side scan sonar

Submarine cables and pipelines laid on the seafloor are critical infrastructures for energy transportation and communication transmission and must be inspected in a timely manner to determine maintenance needs. Autonomous inspection of cables (including pipelines) and their surroundings using underwater vehicles is difficult because of sensor myopia and deviations in cable routing. This study proposes an automatic cable-tracking method (ACTM) based on side-scan sonar (SSS) that endows autonomous underwater vehicles (AUVs) with autonomous decision-making capabilities to achieve fast localization and stable tracking of submarine cables with large uncertainties. Compared with the traditional predefined waypoint method, the proposed method decomposes the tasks into a series of independent behaviors according to operational objectives; thus, the AUV can perform online dynamic task replanning and realize an autonomous coverage search of the target region. When a cable is detected, the cable-tracking task is constructed as a path-following control problem on the horizontal plane. To reduce uncertainties caused by environmental noise and sensor measurement errors, a uniform motion model based on target tracking theory was used to model the virtual mass abstracted from the cable, and the states of the cable were estimated using the Kalman filter. Subsequently, an adaptive line-of-sight guidance algorithm for the SSS is established to dynamically adjust the look-ahead distance by introducing states such as cable curvature and angular change rate, which somewhat alleviates the tracking loss caused by the SSS short-sightedness. The proposed ACTM effectiveness and robustness were validated through numerical simulations and field tests. The results showed that the proposed method can achieve automatic search and adaptive tracking of cables, further reducing the role of humans in the task.

Scanning Scheme for Underwater High-Rise Pile Cap Foundation Based on Imaging Sonar

This study developed a sonar scanning scheme for underwater high-rise pile cap foundations (HRPCFs) to improve the efficiency of bridge inspection and prolong structural durability. First, two key factors in the measurement point arrangement that significantly affect the accuracy of sonar measurement—the appropriate range of measurement distance and the pitch angle—were determined experimentally. Subsequently, an assembled platform was designed to firmly hold the sonar and conveniently move it under strong currents to effectively provide clear images of the pile. A strategy was developed to determine the appropriate number and horizontal and vertical positions of the measurement points around each pile in the pile group, particularly to avoid the obstruction of signal propagation caused by adjacent piles and pile caps. The method was applied to the scanning of an underwater high-rise pile cap foundation of a bridge, and the results showed that the scanning ranges of the imaging sonar at all arranged measurement points were not affected by adjacent piles. The imaging sonar carried by the proposed platform could obtain clear images stably at a water speed of ~2.0 m/s and obtain all surface data of the pile quickly and completely.

Anomalously large marine potholes on a submerged relict shore platform: The Eastern Cape shelf of SE Africa

Marine potholes are common features along rocky shore platforms from around the world. Their occurrence can be used as a palaeo-sea level indicator, however, little attention has been given to submerged marine potholes found on relict shore platforms below the depth limits of SCUBA (≤50 m). This paper examines (n = 238) anomalously large potholes found on a submerged aeolianite shore platform on the outer shelf of the Eastern Cape, South Africa. Using a combined ultra-high resolution seismic reflection, side scan sonar and multibeam bathymetry approach, together with remote observation vehicle dives, the pothole occurrences are mapped.Potholes are either individual or occasionally conjoined, form on sediment-free aeolianite platform and cluster mostly between water depths of 85–95 m. Their sizes are an order of magnitude larger than previously documented, and larger than their fluvial equivalents. Pothole strings are common, associated with the high points between NNW-SSE striking bedding planes of the aeolianite that crop out at the seabed. Potholes are often elongated and aligned with these bedding planes, or in a coast parallel fashion, associated with joints and micro-cliffs in the aeolianite.The potholes possibly formed during several slowstands or stillstands surrounding the Last Glacial Maximum (LGM, 25,000 to 20,000 yr BP) and the Bølling-Allerød interstadial (B-A, 14,500 yr BP). Given their sizes, we ascribe part of their development to chemical weathering of the platform, especially during the periods where sea spray could pond to form dissolution pans in the supratidal part of the aeolianite platform. A wet and warm B-A climate exacerbated chemical weathering, with karst processes initially dominant, followed by mechanical weathering with shoreline migration. Once submerged, only horizontal enlargement ensued. Geological contingencies (joints, bedding planes and platform lowpoints), modified by early weathering-dominant and later wave-dominant processes, were responsible for the evolution of the shore platform morphology.

A High-Efficiency Side-Scan Sonar Simulator for High-Speed Seabed Mapping.

Side scan sonar (SSS) is a multi-purpose ocean sensing technology, but due to the complex engineering and variable underwater environment, its research process often faces many uncertain obstacles. A sonar simulator can provide reasonable research conditions for guiding development and fault diagnosis, by simulating the underwater acoustic propagation and sonar principle to restore the actual experimental scenarios. However, the current open-source sonar simulators gradually lag behind mainstream sonar technology; therefore, they cannot be of sufficient assistance, especially due to their low computational efficiency and unsuitable high-speed mapping simulation. This paper presents a sonar simulator based on a two-level network architecture, which has a flexible task scheduling system and extensible data interaction organization. The echo signal fitting algorithm proposes a polyline path model to accurately capture the propagation delay of the backscattered signal under high-speed motion deviation. The large-scale virtual seabed is the operational nemesis of the conventional sonar simulators; therefore, a modeling simplification algorithm based on a new energy function is developed to optimize the simulator efficiency. This paper arranges several seabed models to test the above simulation algorithms, and finally compares the actual experiment results to prove the application value of this sonar simulator.

Experimental and theoretical research on the debrining process in sediments for a gas storage salt cavern

The sediments account for a large part of the total mined volume of the cavern in high impurity salt mines. This paper was aimed at the scientific problem of gas storage in the pore space of the sediments, and expanded the storage capacity of salt cavern in high impurity salt mines. Debrining in the mined space of salt caverns (contained sediments) is a vital step to complete the gas storage. To experimentally observe the debrining process, debrining experiments are carried out using a self-developed experimental device. The debrining process can be divided into four typical stages, e.g., rapid increase of injection gas pressure, discharging the upper brine, i.e. the brine free of sediments, discharging the brine in sediments, and rapid decrease of injection gas pressure. A mathematical model is proposed for calculating debrining parameters of a salt cavern including sediments based on the pressure equilibrium principle at the gas-brine interface. A numerical method is established for calculating the total debrining time of irregular salt caverns including sediments. The effective cross-sectional area of debrining process is calculated by using the porosity of the sediments. A linear function of the porosity of the transition zone of the sediment surface is put forward. Therefore, the porosity of the upper brine space can gradually transition to the sediments, avoiding the error of sudden increase of the gas-brine interface and debrining rate, which is consistent with the practical debrining process. The porosity of sediments is considered to be a decaying exponential function of depth based on the accumulation of sediment particles. The cross-sectional area at any depth can be obtained through the interpolation of the sonar scanning data. The Jianghan salt cavern is selected for the applications of the proposed model, and the descending speed and depth of the gas-brine interface, and injection gas pressure with debrining time are analyzed. Results show that the greater the debrining rate, the shorter the time to reach the final sediment surface. The descending speed of the gas-brine interface shows a U-shaped curve, which is significantly affected by the cavern shape and porosity of sediments. The increment of the debrining rate has little effect on the ultimate injection gas pressure but has a significant effect on the increasing rate of injection gas pressure. These results can provide a reference for enhancing gas storage by using the sediment pore space of the mined volume and thereby expanding the effective gas storage volume of salt caverns.

IDENTIFICATION ACTIVE POCKMARKS USING THE COMBINATION OF SIDE SCAN SONAR AND SUB-BOTTOM PROFILER

It should be suitable for direct inclusion in abstracting services and should not normally be more than 300 words. Geohazards assessments are important before any engineering activity as they could block facilities and cause millions of dollars in losses. Pockmark as geohazards is often observed on the seabed with various amounts, especially on the clayey seabed sediments. Pockmarks indicate that the gas escapes from below the seabed. Pockmark may cause the jack-up rig to be slipped, pipeline free-span, and even blow out while drilling if it has a gas trap below. Side scan sonar and sub-bottom profiler as the geophysical method using acoustic wave can be used to investigate the active pockmarks. By using these two datasets, the distribution of active and inactive pockmarks can be achieved properly. So that hazards that may occur in engineering activities in the future can be prevented.

Sparsity Regularization-Based Real-Time Target Recognition for Side Scan Sonar with Embedded GPU

Side Scan Sonar (SSS) is widely used to search for seabed objects such as ships and wrecked aircraft due to its high-imaging-resolution and large planar scans. SSS requires an automatic real-time target recognition system to enhance search and rescue efficiency. In this paper, a novel target recognition method for SSS images in varied underwater environment, you look only once (YOLO)-slimming, based on convolutional a neural network (CNN) is proposed. The method introduces efficient feature encoders that strengthen the representation of feature maps. Channel-level sparsity regularization in model training is performed to speed up the inference performance. To overcome the scarcity of SSS images, a sonar image simulation method is proposed based on deep style transfer (ST). The performance on the SSS image dataset shows that it can reduce calculations and improves the inference speed with a mean average precision (mAP) of 95.3 and at least 45 frames per second (FPS) on an embedded Graphics Processing Unit (GPU). This proves its feasibility in practical application and has the potential to formulate an image-based real-time underwater target recognition system.

Sonar investigation of the old Nubian Villages in the bottom topography of Nasser Lake, Egypt

Underwater sonar survey using Side Scan Sonar (SSS) and Single beam Echo-sounder (SBES) was used for the investigation of the old Nubian archaeological villages buried within the bottom topography of Nasser Lake. The research objective involved emphasizing the efficiency of marine geophysical techniques in the detection of the submerged old Nubian Villages in Nasser Lake behind the High Dam, the study also aimed to study riverbed topography and determining the old course of the Nile River in the area. The resulted bathymetric maps showed that the two former banks of the Nile River in the study area were characterized by two distinct natures, while the shoreline has retreated with different extents starting from 250 m at the southern regions up to 3 km in the northern parts. The high-resolution sonar images of the bottom uncovered distinctive acoustic patterns according to difference in the returned backscatter strength. Submerged Nubian houses were detected along some areas of the eastern bank, which were found either standing over elevated rocky cliffs or built on multiple tiered levels. Precise target measurements were applied on the detected houses and different dimensions were obtained, which suggest that these houses were built according to the availability of suitable land to construct such dwellings.

A novel method for real-time ATR system of AUV based on Attention-MobileNetV3 network and pixel correction algorithm

This paper proposes an Automatic Target Recognition (ATR) system based on the Autonomous Underwater Vehicle (AUV) equipped with side scan sonar for real-time detection and positioning of underwater targets. The system introduces a pre-processing algorithm for the original Side Scan Sonar (SSS) image, which performs pixel-level correction of the image according to the slant range setting of the SSS sensor and the height from the seabed to eliminate the influence of target geometric distortion on the subsequent recognition algorithm and improve the recognition accuracy. At the same time, the attitude angle information of the AUV is obtained to correct the target position, making each pixel of the pre-processed image has underwater positioning (latitude and longitude) information. Since SSS images are seriously disturbed by noise, in order to accurately extract target features in real time, on the basis of selecting the lightweight network MobileNetV3, we introduce attention mechanism and integrated learning to meet the requirements of underwater target recognition accuracy and real-time performance. The multi-classifier ensemble prediction results further reduce the mis-identification rate of submarine targets. The ATR system fuses the prediction results and the submarine target position and sends it to the AUV main control system to guide the AUV how to navigate and plan path at the subsequent. The experimental results show that, we validate that the proposed method matches the state of the art in segmentation accuracy, the ATR system proposed in this paper can be embedded in the underwater unmanned platform, and achieve accurate underwater target detection and positioning, The real-time recognition speed of each picture is about 0.058 s.

Improved Neural Network with Spatial Pyramid Pooling and Online Datasets Preprocessing for Underwater Target Detection Based on Side Scan Sonar Imagery

Fast and high-accuracy detection of underwater targets based on side scan sonar images has great potential for marine fisheries, underwater security, marine mapping, underwater engineering and other applications. The following problems, however, must be addressed when using low-resolution side scan sonar images for underwater target detection: (1) the detection performance is limited due to the restriction on the input of multi-scale images; (2) the widely used deep learning algorithms have a low detection effect due to their complex convolution layer structures; (3) the detection performance is limited due to insufficient model complexity in training process; and (4) the number of samples is not enough because of the bad dataset preprocessing methods. To solve these problems, an improved neural network for underwater target detection—which is based on side scan sonar images and fully utilizes spatial pyramid pooling and online dataset preprocessing based on the You Look Only Once version three (YOLO V3) algorithm—is proposed. The methodology of the proposed approach is as follows: (1) the AlexNet, GoogleNet, VGGNet and the ResNet networks and an adopted YOLO V3 algorithm were the backbone networks. The structure of the YOLO V3 model is more mature and compact and has higher target detection accuracy and better detection efficiency than the other models; (2) spatial pyramid pooling was added at the end of the convolution layer to improve detection performance. Spatial pyramid pooling breaks the scale restrictions when inputting images to improve feature extraction because spatial pyramid pooling enables the backbone network to learn faster at high accuracy; and (3) online dataset preprocessing based on YOLO V3 with spatial pyramid pooling increases the number of samples and improves the complexity of the model to further improve detection process performance. Three-side scan imagery datasets were used for training and were tested in experiments. The quantitative evaluation using Accuracy, Recall, Precision, mAP and F1-Score metrics indicates that: for the AlexNet, GoogleNet, VGGNet and ResNet algorithms, when spatial pyramid pooling is added to their backbone networks, the average detection accuracy of the three sets of data was improved by 2%, 4%, 2% and 2%, respectively, as compared to their original formulations. Compared with the original YOLO V3 model, the proposed ODP+YOLO V3+SPP underwater target detection algorithm model has improved detection performance through the mAP qualitative evaluation index has increased by 6%, the Precision qualitative evaluation index has increased by 13%, and the detection efficiency has increased by 9.34%. These demonstrate that adding spatial pyramid pooling and online dataset preprocessing can improve the target detection accuracy of these commonly used algorithms. The proposed, improved neural network with spatial pyramid pooling and online dataset preprocessing based on the YOLO V3 method achieves the highest scores for underwater target detection results for sunken ships, fish flocks and seafloor topography, with mAP scores of 98%, 91% and 96% for the above three kinds of datasets, respectively.

Deep Multi-Look Sequence Processing for Synthetic Aperture Sonar Image Segmentation

Deep learning has enabled significant improvements in semantic image segmentation, especially in underwater imaging domains such as side scan sonar (SSS). In this work, we apply deep learning to synthetic aperture sonar (SAS) imagery, which has an advantage over traditional SSS in which SAS produces coherent high- and constant-resolution imagery. Despite the successes of deep learning, one drawback is the need for abundant labeled training data to enable success. Such abundant labeled data are not always available as in the case of SAS where collections are expensive and obtaining quality ground-truth labels may require diver intervention. To overcome these challenges, we propose a domain-specific deep learning network architecture utilizing a unique property to complex-valued SAS imagery: the ability to resolve angle-of-arrival (AoA) of acoustic returns through <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -space processing. By sweeping through consecutive incrementally advanced AoA bandpass filters (a process sometimes referred to as multi-look processing), this technique generates a sequence of images emphasizing angle-dependent seafloor scattering and motion from biologics along the seafloor or in the water column. Our proposal, which we call multi-look sequence processing network (MLSP-Net), is a domain-enriched deep neural network architecture that models the multi-look image sequence using a recurrent neural network (RNN) to extract robust features suitable for semantic segmentation of the seafloor without the need for abundant training data. Unlike previous segmentation works in SAS, our model ingests a complex-valued SAS image and affords the ability to learn the AoA filters in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -space as part of the training procedure. We show the results on a challenging real-world SAS database, and despite the lack of abundant training data, our proposed method shows superior results over state-of-the-art techniques.

Temporal Fusion Based 1-D Sequence Semantic Segmentation Model for Automatic Precision Side Scan Sonar Bottom Tracking

Precision bottom tracking is a core step in the data processing of side scan sonar (SSS), which is of critical value for the quality of the final SSS production. Currently, the automatic precision SSS bottom tracking remains challenging due to the complex noise caused by the measuring environment, especially the existing methods did not fully exploit the temporal correlations or depended on the hand-crafted setting. Therefore, we proposed a novel temporal fusion based one-dimensional (1-D) sequence semantic segmentation model, TFSSM-1D, to fuse the temporal correlation features and perform automatic precision SSS bottom tracking. The TFSSM-1D uses the deep learning encoder-decoder model for mapping inputs to 1-D semantic label outputs, with the aid of preprocess and temporal fusion modules to improve the accuracy and robustness. Among them, preprocess module is used to introduce the prior knowledge of bilateral symmetry, which alleviates the defect of long-distance features correlation caused by the inductive bias of convolution neural network. The temporal fusion consists of the point-wise temporal fusion module (PTFM) and the bi-directional attention propagation module (BAPM) guides the model to explicitly fuse the temporal variation features on different scales. The experimental results demonstrate the effectiveness of TFSSM-1D, and its mean port offset error reaches 2.7058 on the testing set without down-sampling, which is 40% lower than the previous deep learning based model with single ping input, and other evaluation metrics have also significantly improved. The inference on unseen data shows that TFSSM-1D can achieve precision bottom tracking with good noise immunity.

Synthetic Scan Formation for Underwater Mapping With Low-Cost Mechanical Scanning Sonars (MSS)

Synthetic Scan Formation for Underwater Mapping With Low-Cost Mechanical Scanning Sonars (MSS)