• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.117-126
• /
• 2020

A maritime object detection system is an intelligent assistance system to maritime autonomous surface ship(MASS). It detects automatically floating debris, which has a clash risk with objects in the surrounding water and used to be checked by a captain with a naked eye, at a similar level of accuracy to the human check method. It is used to detect objects around a ship. In the past, they were detected with information gathered from radars or sonar devices. With the development of artificial intelligence technology, intelligent CCTV installed in a ship are used to detect various types of floating debris on the course of sailing. If the speed of processing video data slows down due to the various requirements and complexity of MASS, however, there is no guarantee for safety as well as smooth service support. Trying to solve this issue, this study conducted research on the minimization of computation volumes for video data and the increased speed of data processing to detect maritime objects. Unlike previous studies that used the Hough transform algorithm to find the horizon and secure the areas of interest for the concerned objects, the present study proposed a new method of optimizing a binarization algorithm and finding areas whose locations were similar to actual objects in order to improve the speed. A maritime object detection system was materialized based on deep learning CNN to demonstrate the usefulness of the proposed method and assess the performance of the algorithm. The proposed algorithm performed at a speed that was 4 times faster than the old method while keeping the detection accuracy of the old method.

• Journal of the HCI Society of Korea
• /
• v.8 no.2
• /
• pp.21-27
• /
• 2013

Recently, the use of floating hologram has increased in many different aspects, such as exhibitions, education, advertisements, and so on. Especially, the floating hologram that makes use of half-mirror is widely used. Nevertheless, half-mirror, unfortunately, cannot lead users to the perfect three dimensional hologram experience. Even though it can make the vision look to be up on the air, it does not have the capacity to display itself up on the air, which is the ultimate goal of hologram. In addition, it looks inconsistent when a real object is located behind the half-mirror in order to show the convergence of the two (object and the half-mirror). In this paper, we did the study on comparison of 3D space perception for the stereoscopic AR holography. At first, we applied stereoscopic technology to the half-mirror hologram system for the accurate and realistic AR environment. Then, the users can feel as if the real 3D object behind half-mirror and the reflected virtual image are converged much better in the 3D space. Furthermore, by using depth camera, the location and direction of graphics can be controlled to change depending on the user's point of view. This is the effective way to produce augmented stereoscopic images simply and accurately through half-mirror film without any additional devices. What we saw from the user test were applying 3D images and user interaction leads the users to have 3D spatial awareness and realism more effectively and accurately.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.1
• /
• pp.1-7
• /
• 1999

We present VLSI architecture for a high performance 2-D DCT processor which is used compressing system of real time image processing or HDTV using fast computational algorithm of the Optimized Integer Cosine Transform(OICT). The coefficients of the OICT are integer, so the OICT performs only the integer operations for both forward and inverse transform. Therefore the proposed architecture could be greatly enhanced in improving the speed, reduced the hardware cost considerably by replacing the multiplication operations with shift and addition operations compared with DCT which performs floating-point operations.

• Journal of the Korea Convergence Society
• /
• v.6 no.6
• /
• pp.177-183
• /
• 2015

The image information acquired by a model submarine is transmitted through the repeater. The control signal of a position for submarine and its speed is also controlled by the repeater. Shooting images of underwater circumstances are transmitted to the repeater where the received signal controls a position and speed of underwater submarine. This repeater is combined by a buoy that is floating on the surface to relay the signal of image as well as control between a control unit and a submarine whereas the repeater communicates wirelessly with a control unit. Due to wire communication between the repeater and the submarine, the underwater exploration can be smoothly carried out without a risk of loss of a model submarine. Also, connecting to the repeater and control unit wirelessly makes it possible to conduct easily the underwater exploration. The convergence technology that combines a wireless communication and a control as well as a model submarine is designed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.5
• /
• pp.479-485
• /
• 2011

To acquire images in a thermionic-scanning electron-beam system, a scanning unit is needed to control the electron beam emitted from the tungsten filament source. In scanning the electron beam on the solid surface, the signalto-noise ratio depends on the scanning frequency. We used a digital filter to reduce noise by analyzing the real-time frequency of a secondary electron signal. The noise and the true image signal were well separated. We designed the digital filter via a DSP floating-point operation, and the noise elimination resulted in enhanced image quality in a highresolution mode.

• Journal of the Korean Institute of Gas
• /
• v.3 no.2 s.7
• /
• pp.62-69
• /
• 1999

This paper presents a design method of dynamic positioning control system(DPS) for floating Platform with rotatable and retractable thrusters using H$\infty$ servo control design method. The norm band of uncertainty is captured by multiplicative perturbation between nominal model and reduced order model. A controller robust to the uncertainty is designed applying H$\infty$ synthesis. The control law satisfying robust stability and nominal performance condition is determined through the mixed sensitivity approach. The control algorithm was evaluated on the basis of computer simulation for a proposed DPS design method and experiments was carried out with an image processing method for measurement of DPS position in a water tank The results of overall experiments show that proposed control method will be good to keep at a specified position. And they are compared with the experimental results by LQG synthesis and H$\infty$ optimal control design method.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.7
• /
• pp.923-928
• /
• 2014

Communication underwater is severely limited when compared to communications in air because water is essentially opaque to electromagnetic radiation except in visible range. Acoustic systems are capable of long range communication, but offer limited data rates and significant latency due to the speed of sound in water. On the other hand, optical wireless communication has been proposed as one of the best alternatives to meet the requirements of the underwater observation and subsea monitoring systems. It will help In this study, we are developing an underwater optical communication system that integrates with a depot ship floating on the water. An interface between LED lighting communication system and Bluetooth module is presented to support the underwater-to-air communications. Error free image and text transmission at 3 m of water were achieved at bit rates of 230.4 kbps. This development effort will enhance infrastructure to efficiently interconnect between underwater wireless systems and command ship networks for underwater monitoring.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1158-1165
• /
• 2021

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm². The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image.

• Nuclear Medicine and Molecular Imaging
• /
• v.43 no.5
• /
• pp.443-450
• /
• 2009

Purpose: Conventional image reconstruction uses simplified physical models of projection. However, real physics, for example 3D reconstruction, takes too long time to process all the data in clinic and is unable in a common reconstruction machine because of the large memory for complex physical models. We suggest the realistic distributed memory model of fast-reconstruction using parallel processing on personal computers to enable large-scale technologies. Materials and Methods: The preliminary tests for the possibility on virtual manchines and various performance test on commercial super computer, Tachyon were performed. Expectation maximization algorithm with common 2D projection and realistic 3D line of response were tested. Since the process time was getting slower (max 6 times) after a certain iteration, optimization for compiler was performed to maximize the efficiency of parallelization. Results: Parallel processing of a program on multiple computers was available on Linux with MPICH and NFS. We verified that differences between parallel processed image and single processed image at the same iterations were under the significant digits of floating point number, about 6 bit. Double processors showed good efficiency (1.96 times) of parallel computing. Delay phenomenon was solved by vectorization method using SSE. Conclusion: Through the study, realistic parallel computing system in clinic was established to be able to reconstruct by plenty of memory using the realistic physical models which was impossible to simplify.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.4
• /
• pp.415-420
• /
• 2017

In this paper, an algorithm for object counting via a conveyor system using machine vision is suggested. Object counting systems using image processing have been applied in a variety of industries for such purposes as measuring floating populations and traffic volume, etc. The methods of object counting mainly used involve template matching and machine learning for detecting and tracking. However, operational time for these methods should be short for detecting objects on quickly moving conveyor belts. To provide this characteristic, this algorithm for image processing is a region-based method. In this experiment, we counted young abalone shells that are similar in shape, size and color. We applied a characteristic conveyor system that operated in one direction. It obtained information on objects in the region of interest by comparing a second frame that continuously changed according to the information obtained with reference to objects in the first region. Objects were counted if the information between the first and second images matched. This count was exact when young shells were evenly spaced without overlap and missed objects were calculated using size information when objects moved without extra space. The proposed algorithm can be applied for various object counting controls on conveyor systems.