• Journal of Korea Multimedia Society
• /
• v.18 no.12
• /
• pp.1432-1438
• /
• 2015

We present a methodology to detect moving shadows in video sequences, which is considered as a challenging and critical problem in the most visual surveillance systems since 1980s. While most previous moving shadow detection methods used hand-crafted features such as chromaticity, physical properties, geometry, or combination thereof, our method can automatically learn features to classify whether image segments are shadow or foreground by using a deep learning architecture. Furthermore, applying Markov Random Field enables our system to refine our shadow detection results to improve its performance. Our algorithm is applied to five different challenging datasets of moving shadow detection, and its performance is comparable to that of state-of-the-art approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1674-1688
• /
• 2019

As environmental pollution and fossil fuel energy problems from fuel vehicle have occurred, the interest of electric vehicle(EV) has increased. EV industry and energy industry have grown dynamically in these days. It is expected that the next generation of primary transportation will be EV, and it is necessary to prepare EV infra and efficient energy management such as EV communication protocol, EV charge station, and smart grid. Those EV and energy industry fields are now on growth. Also, the study and development of them are now in progress. In this paper, distributed charge signal processing software for smart slow and quick EV charge is proposed and designed for dealing with EV charge demand. The software consists of smart slow and quick EV charge schedule engine and EV charge power distribution core. The software is designed to support two charge station types. One is normal EV charge station and the other is bus garage EV charge station. Both two types collect the data from EV charge stations, and then analyze the collected data. The software suggests optimized EV charge schedule and deliveries EV charge power distribution information to power switchboard system, and the designed software is implemented on embedded system. It is expected that the software provides efficient EV charge schedule.

• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.3
• /
• pp.177-183
• /
• 2003

Recently, Ryu et al. proposed a multiple target DOA tracking algorithm, which has good features that it has no data association problem and simple structure. But its performance is seriously degraded in the low signal-to-noise ratio. In this paper, a measurement fusion method is presented based on ML(Maximum Likelihood), and the new DOA tracking algorithm is proposed by incorporating the presented fusion method into Ryu's algorithm. The proposed algorithm has a better tracking performance than that of Ryu's algorithm, and it sustains the good features of Ryu's algorithm.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.351-354
• /
• 2004

The concept of e-Business has been around for more than two decades but it has not been used widely enough due to high installation and maintenance cost and complexity. In order to solve such problems, two standardization organizations UN/CEFACT and OASIS have developed an open e-Business standard called ebXML that can be easily adopted by industries. Based on the ebXML, we have developed an e-Logistics integrated platform for industries to do business electronically. The e-Logistics integrated platform was applied to B2B postal logistics industry and efficient interoperability between companies with different systems has been achieved.

• Journal of Power Electronics
• /
• v.11 no.6
• /
• pp.864-869
• /
• 2011

This paper presents a sensorless control and parameter estimation strategies for a Transverse Flux Rotating Motor (TFRM). The proposed sensorless control method is based on a Model Reference Adaptive System (MRAS) to estimate the stator flux. Parameter estimation theory is also applied into the sensorless control method to estimate motor parameters, such as inductances. The effectiveness of the proposed methods is verified by some simulations and experiments.

• Electronics and Telecommunications Trends
• /
• v.32 no.5
• /
• pp.107-116
• /
• 2017

Artificial intelligence has recently been regarded as a key engine of future industry, and cloud computing and big data technologies have begun to receive significant attention. Major global vendors such as IBM, Microsoft, Google, and Amazon have been launching cloud-computing services for artificial intelligence. On the other hand, the situation domestically is now at an early stage. This report describes the industry trends both domestically and internationally regarding cloud computing for artificial intelligence. We also describe to significance of cloud computing ecosystem and data competitiveness for artificial intelligence.

• Electronics and Telecommunications Trends
• /
• v.35 no.5
• /
• pp.43-56
• /
• 2020

The 5G system standardization body has been developing standard functions to provide ultra-high speed, ultra-high reliability, ultra-low latency, and ultra-connected services. In 3GPP Rel-16, which was recently completed, this system has begun to develop ultra-high reliability and ultra-low latency communication functions to support the vertical industry. It is expected that the trend in the adoption of mobile communication by the vertical industry will continue with the introduction of 5G. In this paper, we present the industrial Internet-of-Things (IIoT) service scenarios and requirements for the adoption of 5G systems by the vertical industry and the related standardization trend at present. In particular, we introduce the 5G time-sensitive networking standard technology, a core technology for realizing 5G-based smart factories, for IIoT services.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.7 no.5
• /
• pp.465-471
• /
• 2002

This paper presents a novel PID speed controller for industry servo applications. Considering the speed loop delay, it allows an automatic controller bandwidth/gain setup with the bandwidth of current controller. In addition, the proposed design nile gives uniformly satisfactory performance and the motor speed stays on a desired response curve with minimal oscillation and settling time. This approach can be applied in conjunction with the cascaded position controller which is widely used in practice.

• Journal of Power Electronics
• /
• v.3 no.3
• /
• pp.159-166
• /
• 2003

The winding insulation of low-voltage induction motors in adjustable-speed drive system with voltage-fed Inverters is substantially stressed due to the uneven voltage distribution and excessive voltage stress (dv/dt), which result in the premature insulation breakdown In this paper, the detailed insulation test results of 26 low-voltage induction motors are presented. Six different types of insulation techniques are applied to 26 motors. The insulation characteristics are analyzed with partial discharge, discharge inception voltage, AC current, and dissipation factor tests Also, insulation breakdown tests by high voltage pulses are performed, and the corresponding breakdown voltages obtained.

• Electronics and Telecommunications Trends
• /
• v.33 no.2
• /
• pp.77-85
• /
• 2018

At present, agriculture in Korea is experiencing difficulties, such as a stagnation in farm income, an increase in imported agricultural products, a decrease in arable land, a decrease in the self-sufficiency rate of grain, a decrease in rural population, and aging. To solve these problems and vitalize the rural economy, our government is promoting its 6th industrialization policy, which links agriculture with primary industry, secondary, industry and tertiary industry, and as well as smart agriculture based on information and communication technology. Smart agriculture is an agriculture form used to improve the quality of life in rural areas through making greater efficiency and intelligence by applying ICT convergence technology to the whole entire process of agricultural production, distribution, and consumption in the areas of outdoor agriculture, facility horticulture, and livestock. Therefore, in this paper, we analyze the policy, technology, and standardization trends of domestic and foreign smart agriculture, and suggest ways to apply them to domestic smart agriculture during the in the introduction stage.