• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.121-129
• /
• 2021

This paper deals with a super-resolution that improves the resolution of side scan sonar images using learning-based compressive sensing. Learning-based compressive sensing combined with deep learning and compressive sensing takes a structure of a feed-forward network and parameters are set automatically through learning. In particular, we propose a method that can effectively extract additional information required in the super-resolution process through various initialization methods. Representative experimental results show that the proposed method provides improved performance in terms of Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) than conventional methods.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.133-141
• /
• 2023

Accurate measurement of seafloor topography plays a crucial role in developing marine industries such as maritime safety, resource exploration, environmental protection, and coastal management. The seafloor topography is constructed using side scan sonar (SSS) and single beam echosounder (SBES) or multibeam echosounder (MBES), which transmit and receive ultrasound waves through a device attached to a marine survey vessel. However, the use of a sonar system is affected by noise pollution areas, and the single beam has a limited scope of application. At the same time, the multibeam is mainly applicable for depth observation. For these reasons, it is difficult to determine the boundaries and areas of seafloor topography. Therefore, this study proposes a method to improve the backscatter data of multibeam echosounder, which has a relationship with the seafloor quality, by using digital image processing to classify the shape of the underwater surface.

• Nuclear Engineering and Technology
• /
• v.55 no.12
• /
• pp.4695-4702
• /
• 2023

Nuclear power plants play a pivotal role in the global energy infrastructure, fulfilling a substantial share of the world's energy requirements in a sustainable way. The management of these facilities, especially the handling of spent nuclear fuel (SNF), necessitates meticulous inspections to guarantee operational safety and efficiency. However, the prevailing inspection methodologies lean heavily on human operators, which presents challenges due to the potential hazards of the SNF environment. This study introduces the design of a novel Pre-Batched Inspection Strategy (PBIS) that integrates robotic automation and image processing techniques to bolster the inspection process. This methodology deploys robotics to undertake tasks that could be perilous or time-intensive for humans, while image processing techniques are used for precise identification of SNF targets and regulating the robotic system. The implementation of PBIS holds considerable promise in minimizing inspection time and enhancing worker safety. This paper elaborates on the structure, capabilities, and application of PBIS, underlining its potential implications for the future of nuclear energy inspections.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.4 no.1
• /
• pp.18-24
• /
• 1999

The satellite image acquired by RADARSAT SAR on August 15, 1996 reveals internal waves in north coastal waters of Cheju Island. It is indicated from the image data, the tidal elevation data, and the bottom topography data, the internal waves seem to be generated by interaction between shallow bottom and tidal currents travelling in the stratified water in the summer time during the tidal changeovers from ebb to flood. The internal waves generated in such condition show patterns of trains of solitons. Probable amplitude of observed solitons is calculated using estimation of the soliton wave length from SAR image data and K-dV equation. Detection of the internal waves is very significant not only to military strategist for underwater maneuvers such as operation of submarines, but also to physical and biological oceanographers. Temporal and spatial variation of the internal waves are needed to be measured by simultaneous in-situ field study together with SAR to examine the nature of these internal waves.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.6
• /
• pp.375-382
• /
• 2016

This paper realizes control of the motion of a swimming robot fish in order to implement an underwater robot fish aquarium. And it implements positional control of a two-axis trajectory path of the robot fish in the aquarium. The performance of the robot was verified though certified field tests. It provided excellent performance in driving force, durability, and water resistance in experimental results. It can control robot motion, that is, it recognizes an object by using an optical flow object-detecting algorithm, which uses a video camera rather than image-detecting sensors inside the robot fish. It is possible to find the robot's position and control the motion of the robot fish using a radio frequency (RF) modem controlled via personal computer. This paper proposes realization of robot fish motion-tracking control using the optical flow object-detecting algorithm. It was verified via performance tests of lead-lag action control of robot fish in the aquarium.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.483-485
• /
• 2012

본 논문에서는 수중 영상 환경에 특화된 자동 수중 영상 보정 시스템을 제안한다. 수중 영상은 빛 희석(light attenuation)을 인한 가시거리 제한, 낮은 영상 대비(low contrast) 그리고 부유물질과 같은 영상의 노이즈 등의 특수한 환경적 제약이 따른다. 기존의 수중 영상 보정 알고리즘은 색 및 대비(contrast) 보정, 가시거리 확장 및 노이즈 제거 기법등을 이용한 부분적으로 보정 연구가 진행되어 왔는데, 부분적 영상 보정 기법으로는 선명한 영상의 결과를 얻기 힘들다. 제안한 통합 수중 영상 보정 시스템은 색 및 대비 보정, 부유물질 제거를 위한 노이즈 필터링, 객체 윤곽선 강화를 위한 기법들을 통합하여 수중 영상에 특화하였다. 실험을 통하여 제안된 수중 영상 보정 시스템의 효율성을 확인하였다.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.687-698
• /
• 2021

We present quantitative estimations of changes in the areal extent of coral reef habitats at Weno Island, Micronesia, using high-spatial-resolution remote sensing images and field observations. Coral reef habitat maps were generated from Kompsat-2 satellite images for September 2008 and September 2010, yielding classifications with 78.6% and 72.4% accuracy, respectively, which is a relatively high level of agreement. The difference between the number of pixels occupied by each seabed type was calculated, revealing that the areal extent of living corals decreased by 8.2 percentage points between 2008 and 2010. This result is consistent with a comparison of the seabed types determined by field observations. This study can be used as a basis for remediation planning to diminish the impact of changes in coral reefs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.10
• /
• pp.1973-1980
• /
• 2017

In the case of a small UUV operating an active synthetic aperture sonar, various velocity disturbances may occur on the path due to the influence of external underwater environment, and this causes phase errors in coherent synthetic aperture processing, which has a large influence on the detected image. In this paper, when a periodic sinusoidal velocity disturbance is generated in the traveling direction, the phase generated by the round trip slope range at each position is estimated the cross correlation coefficient for multiple received signals and compensated the position variation in the overlapped DPC by the average value within the maximum allowable width. Through simulations, it has been confirmed that the images degraded by the velocity disturbance amplitude and fluctuating frequency of the UUV are removed from the false targets and the performance of azimuth resolution is improved by the proposed phase compensation method.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.2
• /
• pp.241-246
• /
• 2014

The purpose of this study is to investigate the flow characteristics around underwater triangular structure with various inclination and Reynolds number. A flow fields around the triangular structure model were measured by visualization method and PIV in the circulating water channel. The result of the experiment is where the triangular structure that has a inclination of $45^{\circ}$ and the reynolds number at $Re=2.9{\times}10^3$ showed rising velocity component to 2.7 times of the structure height. When the reynolds number is steady and when the inclination is greater the descending velocity component of the structure's rears current form is greatly shown and for the areas where it's more than y/hs=1.75 has a change in the angle of inclination but it doesn't give a great effect to it.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.225-233
• /
• 2024

Active sonar transmits sound waves to detect covertly maneuvering underwater objects and detects the signals reflected back from the target. However, in addition to the target's echo, the active sonar's received signal is mixed with seafloor, sea surface reverberation, biological noise, and other noise, making target recognition difficult. Conventional techniques for detecting signals above a threshold not only cause false detections or miss targets depending on the set threshold, but also have the problem of having to set an appropriate threshold for various underwater environments. To overcome this, research has been conducted on automatic calculation of threshold values through techniques such as Constant False Alarm Rate (CFAR) and application of advanced tracking filters and association techniques, but there are limitations in environments where a significant number of detections occur. As deep learning technology has recently developed, efforts have been made to apply it in the field of underwater target detection, but it is very difficult to acquire active sonar data for discriminator learning, so not only is the data rare, but there are only a very small number of targets and a relatively large number of non-targets. There are difficulties due to the imbalance of data. In this paper, the image of the energy distribution of the detection signal is used, and a classifier is learned in a way that takes into account the imbalance of the data to distinguish between targets and non-targets and added to the existing technique. Through the proposed technique, target misclassification was minimized and non-targets were eliminated, making target recognition easier for active sonar operators. And the effectiveness of the proposed technique was verified through sea experiment data obtained in the East Sea.