• 로봇학회논문지
• /
• 제19권2호
• /
• pp.188-195
• /
• 2024

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.

• 해양환경안전학회지
• /
• 제28권3호
• /
• pp.441-450
• /
• 2022

The introduction of autonomous underwater gliders (AUGs) specifically addresses the reduction of operational costs that were previously prohibited with conventional autonomous underwater vehicles (AUVs) using a "scaling-down" design philosophy by utilizing the characteristics of autonomous drifters to far extend operation duration and coverage. Long-duration, wide-area missions raise the cost and complexity of in-water testing for novel approaches to autonomous mission planning. As a result, a simulator that supports the rapid design, development, and testing of autonomy solutions across a wide range using software-in-the-loop simulation at faster-than-real-time speeds becomes critical. This paper describes a faster-than-real-time AUG simulator that can support high-resolution bathymetry for a wide variety of ocean environments, including ocean currents, various sensors, and vehicle dynamics. On top of the de facto standard ROS-Gazebo framework and open-sourced underwater vehicle simulation packages, features specific to AUGs for ocean mapping are developed. For vehicle dynamics, the next-generation hybrid autonomous underwater gliders (Hybrid-AUGs) operate with both the buoyancy engine and the thrusters to improve navigation for bathymetry mappings, e.g., line trajectory, are is implemented since because it can also describe conventional AUGs without the thrusters. The simulation results are validated with experiments while operating at 120 times faster than the real-time.

• 제어로봇시스템학회논문지
• /
• 제19권8호
• /
• pp.667-675
• /
• 2013

This paper presents vision-based techniques for underwater landmark detection, map-based localization, and SLAM (Simultaneous Localization and Mapping) in structured underwater environments. A variety of underwater tasks require an underwater robot to be able to successfully perform autonomous navigation, but the available sensors for accurate localization are limited. A vision sensor among the available sensors is very useful for performing short range tasks, in spite of harsh underwater conditions including low visibility, noise, and large areas of featureless topography. To overcome these problems and to a utilize vision sensor for underwater localization, we propose a novel vision-based object detection technique to be applied to MCL (Monte Carlo Localization) and EKF (Extended Kalman Filter)-based SLAM algorithms. In the image processing step, a weighted correlation coefficient-based template matching and color-based image segmentation method are proposed to improve the conventional approach. In the localization step, in order to apply the landmark detection results to MCL and EKF-SLAM, dead-reckoning information and landmark detection results are used for prediction and update phases, respectively. The performance of the proposed technique is evaluated by experiments with an underwater robot platform in an indoor water tank and the results are discussed.

• 반도체디스플레이기술학회지
• /
• 제23권2호
• /
• pp.23-27
• /
• 2024

Underwater images are typically degraded due to color distortion, light absorption, scattering, and noise from artificial light sources. Restoration of these images is an essential task in many underwater applications. In this paper, we propose a two-phase deep learning-based method, Underwater Deep Curve Estimation (UWDCE), designed to effectively enhance the quality of underwater images. The first phase involves a white balancing and color correction technique to compensate for color imbalances. The second phase introduces a novel deep learning model, UWDCE, to learn the mapping between the color-corrected image and its best-fitting curve parameter maps. The model operates iteratively, applying light-enhancement curves to achieve better contrast and maintain pixel values within a normalized range. The results demonstrate the effectiveness of our method, producing higher-quality images compared to state-of-the-art methods.

• 로봇학회논문지
• /
• 제13권3호
• /
• pp.190-197
• /
• 2018

Geomagnetic field signals have potential for use in underwater navigation and geophysical surveys. To map underwater geomagnetic fields, we propose a method that exploits an autonomous surface vehicle. In our system, a magnetometer is rigidly attached to the vehicle and not towed by a cable, minimizing the system's size and complexity but requiring a dedicated calibration procedure due to magnetic distortion caused by the vehicle. Conventional 2D methods can be employed for the calibration by assuming the horizontal movement of the magnetometer, whereas the proposed 3D approach can correct for horizontal misalignment of the sensor. Our method does not require a supporting crane system to rotate the vehicle, and calibrates and maps simultaneously by exploiting data obtained from field operation. The proposed method has been verified experimentally in inland waters, generating a magnetic field map of the test area that is of much higher resolution than the public magnetic field data.

• 한국해양공학회지
• /
• 제30권3호
• /
• pp.227-233
• /
• 2016

This paper presents an underwater structure 3D reconstruction method using a 2D multibeam imaging sonar. Compared with other underwater environmental recognition sensors, the 2D multibeam imaging sonar offers high resolution images in water with a high turbidity level by showing the reflection intensity data in real-time. With such advantages, almost all underwater applications, including ROVs, have applied this 2D multibeam imaging sonar. However, the elevation data are missing in sonar images, which causes difficulties with correctly understanding the underwater topography. To solve this problem, this paper concentrates on the physical relationship between the sonar image and the scene topography to find the elevation information. First, the modeling of the sonar reflection intensity data is studied using the distances and angles of the sonar beams and underwater objects. Second, the elevation data are determined based on parameters like the reflection intensity and shadow length. Then, the elevation information is applied to the 3D underwater reconstruction. This paper evaluates the presented real-time 3D reconstruction method using real underwater environments. Experimental results are shown to appraise the performance of the method. Additionally, with the utilization of ROVs, the contour and texture image mapping results from the obtained 3D reconstruction results are presented as applications.

• 한국해양공학회지
• /
• 제34권3호
• /
• pp.227-236
• /
• 2020

Underwater acoustics, which is the domain that addresses phenomena related to the generation, propagation, and reception of sound waves in water, has been applied mainly in the research on the use of sound navigation and ranging (SONAR) systems for underwater communication, target detection, investigation of marine resources and environment mapping, and measurement and analysis of sound sources in water. The main objective of remote sensing based on underwater acoustics is to indirectly acquire information on underwater targets of interest using acoustic data. Meanwhile, highly advanced data-driven machine-learning techniques are being used in various ways in the processes of acquiring information from acoustic data. The related theoretical background is introduced in the first part of this paper (Yang et al., 2020). This paper reviews machine-learning applications in passive SONAR signal-processing tasks including target detection/identification and localization.

• Ocean Systems Engineering
• /
• 제14권2호
• /
• pp.101-114
• /
• 2024

Seafloor sediment mapping is an essential research topic in shallow coastal waters, especially in port development, benthic habitat mapping, and underwater communications. The seafloor sediments can be interpreted by collecting sediment samples directly in the field using a grab sampler or corer. Another method is optical, especially using underwater cameras and videos. Both methods each have weaknesses in terms of area coverage (mechanic) and accurate positioning (optic). The latest technology used to overcome it is the acoustic method (echosounder) with Global Navigation Satellite System (GNSS) Real Time Kinematic (RTK) positioning. Therefore, in this study will propose the classification of seafloor sediments in coastal waters using acoustic method that is Multibeam Echosounder (MBES) multi-frequency with five frequency (200 kHz, 250 kHz, 300 kHz, 350 kHz, and 400 kHz). In this study, the deep neural network (DNN) used the bathymetric multi frequency, bathymetric difference inters frequencies, and bathymetric features from 5 (five) frequencies as input layer and 4 (four) sediment types in 74 (seventy-four) sample sediment as output layer to make a seafloor sediment map. Results of sediment mapping using the DNN method show an overall accuracy of 71.6% (significant) and a kappa coefficient of 0.59 (moderate). The distribution of seafloor sediment in the study area is mainly silt (41.6%), followed by clayey sand (36.6%), sandy silt (14.2%), and silty sand (7.5%).

• 한국산업융합학회 논문집
• /
• 제23권3호
• /
• pp.463-471
• /
• 2020

Recently, various tries to apply ROV (Remotely Operated Vehicle) into underwater are being developed. However, due to underwater environment uniqueness, the additional problem must be taken into account when designing an ROV for the inspection of the underwater structure. This is because a GPS-based information method cannot be applied, and the obtainable image is also dependent on the turbidity. Also, it is necessary to be able to satisfy waterproof and operating speeds in consideration of most practical application environments. This paper describes the design results of the ROV system for underwater structure inspection considering the above problems. The designed system applied INS / DVL for location recognition and was configured to support 3D mapping and stereo camera-based image information using sonar depending on visibility. To satisfy the waterproof, a pressure vessel using a composite material was applied. And over-actuated system using eight thrusters to maintain a stable posture and operating speed was applied also. The designed system was verified by structural analysis and flow analysis also.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권2호
• /
• pp.837-856
• /
• 2016

Underwater image enhancement has received considerable attention in last decades, due to the nature of poor visibility and low contrast of underwater images. In this paper, we propose a new automatic underwater image enhancement algorithm, which combines nonsubsampled contourlet transform (NSCT) domain enhancement techniques with the mechanism of the human visual system (HVS). We apply the multiscale retinex algorithm based on the HVS into NSCT domain in order to eliminate the non-uniform illumination, and adopt the threshold denoising technique to suppress underwater noise. Our proposed algorithm incorporates the luminance masking and contrast masking characteristics of the HVS into NSCT domain to yield the new HVS-based NSCT. Moreover, we define two nonlinear mapping functions. The first one is used to manipulate the HVS-based NSCT contrast coefficients to enhance the edges. The second one is a gain function which modifies the lowpass subband coefficients to adjust the global dynamic range. As a result, our algorithm can achieve contrast enhancement, image denoising and edge sharpening automatically and simultaneously. Experimental results illustrate that our proposed algorithm has better enhancement performance than state-of-the-art algorithms both in subjective evaluation and quantitative assessment. In addition, our algorithm can automatically achieve underwater image enhancement without any parameter tuning.