• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1230-1237
• /
• 2009

In this paper, we develop a design methodology of Granular-based Radial Basis Function Neural Networks(GRBFNN) by context-based clustering. In contrast with the plethora of existing approaches, here we promote a development strategy in which a topology of the network is predominantly based upon a collection of information granules formed on a basis of available experimental data. The output space is granulated making use of the K-Means clustering while the input space is clustered with the aid of a so-called context-based fuzzy clustering. The number of information granules produced for each context is adjusted so that we satisfy a certain reconstructability criterion that helps us minimize an error between the original data and the ones resulting from their reconstruction involving prototypes of the clusters and the corresponding membership values. In contrast to "standard" Radial Basis Function neural networks, the output neuron of the network exhibits a certain functional nature as its connections are realized as local linear whose location is determined by the values of the context and the prototypes in the input space. The other parameters of these local functions are subject to further parametric optimization. Numeric examples involve some low dimensional synthetic data and selected data coming from the Machine Learning repository.

• Elastomers and Composites
• /
• v.45 no.3
• /
• pp.170-187
• /
• 2010

Much interest on the thermoplastic elastomers (TPEs) has recently been attracted in commercial fields as well as scientific and applied researches. The TPEs have their own characteristic area especially in relation with block copolymers as well as many other polymeric materials, since they show interesting features displayed by the conventional vulcanized rubber, and at the same time, by the thermoplastics. In addition, they are characterized by a set of interesting properties inherent to block and graft copolymers, variety of blends and vulcanized materials. The importance of TPE as organic materials can be evaluated by the number of published reports (papers, patents, technical reports, etc). The input of the concept 'thermoplastic elastomer' to SciFinderScholar yields 18,508 results between 1939 and July 10, 2010, and the number increased exponentially after the mid of 1990. For the suitable introduction of the TPE, historic, scientific, technical and commercial considerations should be taken into account. This review article starts with a brief discussion on historical considerations, followed by a introduction of the main preparations and analytical techniques utilized in chemical, structural, and morphological studies. The properties, processing tools, the position among organic materials, and applications of TPEs are also briefly reviewed. Finally, the most probable trends of their future development are discussed in a short final remarks.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.370-376
• /
• 2023

In the underwater image, it is not clear to distinguish the shape of the target due to underwater noise and low resolution. In addition, as an input of deep learning, underwater images require pre-processing and segmentation must be preceded. Even after pre-processing, the target is not clear, and the performance of detection and identification by deep learning may not be high. Therefore, it is necessary to distinguish and clarify the target. In this study, the importance of target shadows is confirmed in underwater images, object detection and target area acquisition by shadows, and data containing only the shape of targets and shadows without underwater background are generated. We present the process of converting the shadow image into a 3-mode image in which the target is white, the shadow is black, and the background is gray. Through this, it is possible to provide an image that is clearly pre-processed and easily discriminated as an input of deep learning. In addition, if the image processing code using Open Source Computer Vision (OpenCV)Library was used for processing, the processing speed was also suitable for real-time processing.

• Journal of Ocean Engineering and Technology
• /
• v.38 no.2
• /
• pp.64-73
• /
• 2024

Oil spills pose significant threats to marine ecosystems, human health, socioeconomic aspects, and coastal communities. Accurate real-time predictions of oil slick transport along coastlines are paramount for quick preparedness and response efforts. This study used an open-source OpenOil numerical model to simulate the fate and trajectories of oil slicks released during the 2007 Hebei Spirit accident along the Korean coasts. Six combinations of input parameters, derived from a five-day met-ocean dataset incorporating various hydrodynamic, meteorological, and wave models, were investigated to determine the input variables that lead to the most reasonable results. The predictive performance of each combination was evaluated quantitatively by comparing the dimensions and matching rates between the simulated and observed oil slicks extracted from synthetic aperture radar (SAR) data on the ocean surface. The results show that the combination incorporating the Hybrid Coordinate Ocean Model (HYCOM) for hydrodynamic parameters exhibited more substantial agreement with the observed spill areas than Copernicus Marine Environment Monitoring Service (CMEMS), yielding up to 88% and 53% similarity, respectively, during a more than four-day oil transportation near Taean coasts. This study underscores the importance of integrating high-resolution met-ocean models into oil spill modeling efforts to enhance the predictive accuracy regarding oil spill dynamics and weathering processes.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.2
• /
• pp.175-181
• /
• 2004

Analysis of brake characteristics has progressed rapidly in recent years, as computer techniques have developed. However, there are many problems in predicting braking characteristics, due to the numerous design variables of the brake system. Therefore, a synthetic braking performance analysis is required for all brake system parts such as master cylinder, booster, control valve and split system. In this paper, a program which can analyze braking performance such as force distribution, braking efficiency, pedal force and pedal travel, is presented. The preprocessor of the program helps users prepare input files through a dialog box. An additional postprocessor makes the graph presentation of solved results. Also, a simple example problem is applied to show the usefulness of the presented program.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.4
• /
• pp.419-426
• /
• 1999

A novel motion analysis system is presented in this paper. The proposed system is inspired by processing functions observed in the fly visual system, which detects changes in input light intensities, determines motion on both the local and the wide-field levels. The system has several differences from conventional motion analysis system. First, conventional systems usually focused on matching similar feature or optical flow, but neural network is applied in this system. Back propagation is used by learning method, and Tine Delay Neural Network (TDNN) is also used as analysis method. Second, while conventional systems usually limited on only two frames of sequence, the proposed system accept multiple frames of sequence. The experimental results showed a 94.7% correct rate with a speed of 71.47 milli seconds for real and synthetic images.

• Journal of Environmental Science International
• /
• v.5 no.3
• /
• pp.361-367
• /
• 1996

An inverse fluidized-bed biofilm reactor (IFBBR) was used for the treatment of highly-emulsified oily wastewater. When the concentration of biomass which was cultivated in the synthetic wastewater reached to 6000 mg/1, the oily wastewater was employed to the reactor with a input COD concentration range of 50 mg/1 to 1900 mg/l. Virtually the IFBBR showed a high stability during the long operation period although soma fluctuation was observed. The COD removal efficiency was maintained over 9% under the condition that organic loading rate should be controlled under the value of 1.5 kgCOD/$m^3$/day, and F/M ratio is 1.0 kgCOD/kgVSS/day at $22{\circ}C$ and HRT of 12 hrs. As increasing organic loading rates, the biomass concentration was decreased steadily with decreasing of biofilm dry density rather than biofilm thickness. Based on the experimental jesuits, it was suggested that the decrease in biofilm dry density was caused by a loss of biomass inside the biofilm.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.111-114
• /
• 2004

Object-based segmentation is the first essential step for image processing applications. Recently, SAR (Synthetic Aperture Radar) segmentation techniques have been developed, however not enough to preserve the significant information contained in the small regions of the images. The proposed method is to partition an SAR image into homogeneous regions by using a fuzzy hit-or-miss operator with an inherent spatial transformation, which endows to preserve the small regions. In our algorithm, an iterative segmentation technique is formulated as a consequential process. Then, each time in iterating, hypothesis testing is used to evaluate the quality of the segmented regions with a homogeneity index. The segmentation algorithm is unsupervised and employed few parameters, most of which can be calculated from the input data. This comparative study indicates that the new iterative segmentation algorithm provides acceptable results as seen in the tested examples of satellite images.

• Journal of the Korean Society of Combustion
• /
• v.7 no.2
• /
• pp.42-48
• /
• 2002

Experiments on burning process of the industrial wastes were performed on a nozzle-type grate in the industrial waste incinerator with a capacity of 160 kilograms per hour. The temporal variations of temperatures and concentrations of the exhaust gas were measured and analyzed. The synthetic leather waste with the moisture content less than 2% was used. The experimental results show that the CO concentration in the exhaust gas exceeds the limit, 600 ppm, and the gas temperature fluctuates too much when 8 kg of waste was supplied every 3 minutes, equivalent to the capacity of 160kg per hour. That is a typical burning mode of this high-calorific industrial waste. When the smaller unit waste input, 6kg per every 2 min 15 seconds was supplied, we could reduce the fluctuations of the furnace temperature and improve the exhaust emissions, especially the CO concentration.