• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.92-100
• /
• 2020

Currently, the demand for underwater or underwater photography is growing very fast. Its coverage of underwater shooting for broadcasting, leisure and sports, and military and operational use is also growing rapidly. Among them, we specifically select the best camera to be used in underwater drones to photograph and inspect marine life attached to the ship's hull. To compare three cameras performance, they are compared and evaluated using objective and subjective criteria in special circumstances such as underwater shooting. This study checks whether performance criteria, such as resolution of a camera, meet objective and subjective standards in the unusual situation of underwater shooting. And it shows that in addition to the filter that calibrates the image, proper camera selection is important for providing good picture quality. Even after this study, research using more diverse cameras could provide an appropriate standard for comparison of underwater camera quality.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.14-21
• /
• 2019

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.2
• /
• pp.679-687
• /
• 2019

This paper presents the autonomous swimming technology developed for an Autonomous Underwater Vehicle (AUV) operating in the underwater jacket structure environment. To prevent the position divergence of the inertial navigation system constructed for the primary navigation solution for the vehicle, we've developed kinds of marker-recognition based underwater localization methods using both of optical and acoustic cameras. However, these two methods all require the artificial markers to be located near to the cameras mounted on the vehicle. Therefore, in the case of the vehicle far away from the structure where the markers are usually mounted on, we may need alternative position-aiding solution to guarantee the navigation accuracy. For this purpose, we develop a sonar image processing based underwater localization method using a Forward Looking Sonar (FLS) mounted in front of the vehicle. The primary purpose of this FLS is to detect the obstacles in front of the vehicle. According to the detected obstacle(s), we apply an Occupancy Grid Map (OGM) based path planning algorithm to derive an obstacle collision-free reference path. Experimental studies are carried out in the water tank and also in the Pohang Yeongilman port sea environment to demonstrate the effectiveness of the proposed autonomous swimming technology.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.60 no.2
• /
• pp.128-141
• /
• 2024

Fish resource surveys were conducted near Jeju Island in June, August and October 2021 using an underwater camera monitoring system, fish pots, and SCUBA diving methods. The efficiency of the methods used to survey fish resources was compared using the number of individuals compared to area per unit time (inds/m³/h) and the number of species compared to area per unit time (spp./m³/h). As a result of comparing the number of individuals compared to the area per unit time (inds/m³/h), the order was underwater camera 214.69, SCUBA diving 124.62, and fish pots 0.57 inds/m³/h. The number of species compared to area per unit time (spp./m³/h) is in the following order: SCUBA diving 0.85, underwater camera 0.38, and fish pots 0.01 spp./m³/h. The fish resource monitoring method using underwater cameras was found to be more efficient in individual counts, and the SCUBA diving method was found to be more efficient in species counts. When considering cost and survey efficiency, the fish resource survey method using underwater cameras was judged to be more effective. The results of this study are expected to be widely used in estimating the population density of fish, which is the core of future fisheries resource surveys.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.22 no.1
• /
• pp.11-18
• /
• 1986

Schooling behavier to a fishing gear and estimation of the volume of fish school in set net have ~ been studied by making use of such techniques as visual observations, underwater cameras, under- water televison. However, all of these observation techniques are subject to restrictions caused by illumination, underwater visibility, underwater transparent and sea conditions. For the above mentioned reasoa, one of the most effective method by this time become generally known a method using fish finder. In this paper, in order to control the fishing ground of set net effectively and to develope the telemetric fish finder, the experiments for the target strength, underwater shape of fishing gear, schooling behavier and volume of fish school with fish finder were performed at Galgott fishing ground of set net located Keouje Island, 15th-24th July and 18th-20th October in 1985. The results of these experiment showed that a method using fish finder in fishing grOlllld of set net is available for estimating distribution and school size, fish behavier in relation to a fishing gear and underwater shape of fishing gears.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.22 no.4
• /
• pp.12-17
• /
• 2018

A natural cavitation-type high-speed underwater vehicle with solid rocket motor is tested, and its speed and running distance are measured. The outputs from pressure sensors on the surface of the vehicle reveal a pressure-time history reflecting the development of supercavitation. Underwater cameras installed on the wall of the test pool record the entire process from the onset of supercavitation to its full development. CNU-SuperCT, based on two-dimensional inviscid theoretical analysis, is used to simulate test results. Considering CNU-SuperCT does not include the control fins of the vehicle, simulation results agree with test results very well. Additionally, pictures from underwater cameras support the test results.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2000.10a
• /
• pp.90-95
• /
• 2000

This paper presents the vergence control of a parallel stereo camera and its application to underwater stereo camera to enhance the working efficiency of underwater vehicles that equips with manipulators in seabed operation. The stereo camera consists of two parallel lenses mounted on a lateral moving base and two CCD cameras mounted on a longitudinal moving base, which is embedded in a small pressure canister for underwater application. Because the lateral shift is related to the backward shift with a nonlinear relation, only one control input is needed to control the vergence and focus of the camera with a special driving device. We can get a clear stereo vision with the camera for all the range of objects in air and in water, especially in short range objects. The control system of the camera is so simple that we are able to realize a small stereo camera system and to apply it to a stereo vision system for underwater vehicles. This paper also shows how to acquire the distance information of an underwater object with this stereo camera. Whenever we focus on an underwater object with the camera, we can obtain the three-dimensional images and the distance information in real-time.

• Journal of Ocean Engineering and Technology
• /
• v.15 no.1
• /
• pp.79-84
• /
• 2001

This paper present the control of the image disparity of a parallel stereo camera and its application to an underwater stereo camera to enhance the working efficiency of underwater vehicles that are equiped with manipulators in seabed operation. The stereo camera consists of two parallel lenses mounted on a lateral moving base and two CCD cameras mounted on a longitudinal moving base, which is embedded in a small pressure canister for underwater application. Because the lateral shift is related to the backward shift with a nonlinear relation, only one control input is needed to control the vergence and focus of the camera with a special driving device. We can get clear stereo vision with the camera for all the range of objects in air and in water, especially in short range object. The control system of the camera is so simple that we are able to realize a small stereo camera system and apply it to a stereo vision system for underwater vehicles. This paper also shows how to acquire the distance information of an underwater object with this stereo camera. Whenever we focus on an underwater object with the camera, we can obtain three-dimensional images and distance information in real-time.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1379-1386
• /
• 2018

Conventional underwater cameras used in fish farms can only shoot limited areas and are vulnerable to underwater contamination. There is also a problem with contaminated farms as surplus residues are deposited as a result of feed supply to farms' nets. This paper proposes underwater drones for underwater monitoring of fish farms and cleaning nets. If underwater drones are used for management of fish farms, underwater imaging, monitoring and cleaning of fish farms' nets can be possible. By using this technology, data can be collected by detecting changes in the environment of a fish farm and responding to changes that occur within a fish farm based on the data. In addition, the establishment of an integrated control system will enable to build efficient and stable smart farms.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.23 no.6
• /
• pp.451-456
• /
• 1990

Underwater acoustic navigation and position fixing systems have been extensively used not only in surface position fixing but also in underwater position fixing. Tn recently, application of these systems has been in the field of underwater inspection of offshore platforms, where it is vital to track the position of an unmanned submersible or diver carrying underwater cameras and nondestructive testing equipment. But these systems are included the fixing errors as results of a signal with additive noise, the attenuation of sound and the interference effects due to multipath reflection and forward scattering. In this paper to improve the position fixing by the supershort baseline acoustic position system, a method to apply the Kalman filter to the fix of the system is proposed and the digital simulation under noise condition is conducted. The optimal positions by the Kalman filter are compared with original positions, and it is confirmed that the results of the pro-posed method are evidently more accurate.