• Journal of the Korea Computer Graphics Society
• /
• v.13 no.2
• /
• pp.55-60
• /
• 2007

Diminished reality (DR) is a technique that provide a visual convenience by virtually hiding an object. Most of existing DR systems have been implemented based on HMDs or desktop displays. However, Here has been no report on the development of DR system based on projection displays due to technical difficulty in spite of its superiority in the aspect of human factor to conventional displays. Rapid advances of projection displays and projection-based vision technologies motivated us to develop a projection-based DR system. As the first attempt, this paper proposes a projection-based diminished reality system using an image completion technique. Its usefulness is demonstrated through experiments and its potential applications are discussed.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.85-94
• /
• 2004

Object tracking in a real time image is one of interesting subjects in computer vision and many Practical application fields during the past couple of years. But sometimes existing systems cannot find all objects by recognizing background noise as object. This paper proposes a method of object detection and tracking using adaptive background image in real time. To detect object which is not influenced by illumination and to remove noise in background image, this system generates adaptive background image by real time background image updating. This system detects object using the difference between background image and input image from camera. After setting up Minimum Bounding Rectangle(MBR) using the internal point of detected object, the system tracks object through this MBR In addition, this paper evaluates the test result about performance of proposed method as compared with existing tracking algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.191-194
• /
• 1995

This paper evaluates the influences of sex on the human emotions while coexisting with robots. When we consider human vision, robot's motion is the most important parameter which influences human emotions and must be well controlled for males and females emotions. On the other hand, when we consider human touch of sense, which is effective for cooperation transmitting mutual forces, the softness of robot is an important parameter for human emotions and must be also well controlled for males and females emotions. From these points of view, at first, we evaluate robot's motion under four different shapes of velocity pattern while handing over a cup to humans. Second, we evaluate robot's softness realized by impedance control. From the first experiment, we concluded that the conditions of choosing an adequate maximum velocity value and locating the velocity peak at the center or the first half of the duration are necessary for male's emotions. In addition, the smooth velocity decrease in the last part of the velocity pattern's duration is desired for female's emotions. From the second experiment, we concluded that females prefer lighter values of virtual impedance characteristics than males and any small increase on the heaviness of virtual impedance values is followed by the negative exponential change on human emotions.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.17-24
• /
• 2016

Many organizations have transformed their business in order to survive and compete in the future. They generate projects by creating a vision, using strategies and objectives with funds aligning strategies and make efforts to complete them successfully because project success leads to business success. All projects have triple constraints such as scope, time, and cost to be completed. Project cost performance is a key factor to achieve project goals and which is mostly related with risks among various cost drivers. Projects require a cost estimation method to complete them within their budget and on time. An accurate budget cannot be estimated due to the uncertainties and risks. Thus some additional money should be funded in addition to the base budget as a contingency reserve for identified risks and a management reserve for unidentified risks. While research on contingency reserve for identified risks included in project budget baseline have been presented, research on management reserve for unidentified risks included in total project budget is still scarce. The lack of research on estimation method and role of the management reserve have made project managers little confidence to estimate project budget accurately with reasonable basis. This study proposes a practical model to estimate budgets including contingency and management reserves for not only project cost management but also to keep the balance of organization's total funds to maximize return on investments for project portfolio management. The advantages of the proposed model are demonstrated by its application to construction projects in Korea and the processes to apply this model for verification are also provided.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.2
• /
• pp.119-128
• /
• 2016

Use of ICT in Government has ability to improve service delivery to its citizens, and yet many developing countries have lagged behind in the implementation of e-Government. Many e-Government initiatives also failed to achieve their objectives in developing countries. This paper therefore aims to identify critical failure or success factors in Kenya, using Heeks' Factor Model. A survey questionnaire was developed and data were collected and analyzed from officials and interested citizens. The analysis results enabled to highlight seven specific success and failure factors, and their constituent elements in Kenya. The Kenyan overall e-Government implementation score belongs to the Zone of Improvement (3.52 of total 5.0), which means partial success or failure. The enablers of e-Government projects are good strategy formulation, and internal and external drive, whereas main failures of e-Government are weak ICT infrastructure. The areas for improvement are project management, design, competencies and funding. Data analysis highlights both strengths and weaknesses for each factor or variable. In particular, Kenyan government excels at the drive for change by top to bottom government officers as well as external stakeholders, while the government officers who are using e-Government are satisfied with the availability of vision, strategy and plan of e-Government implementation. Both technologies and e-transactions laws were the worst of all the variables in e-Government implementation. Two areas should be improved using immediate corrective action. In-depth study reveals that government officers and citizens can't fully use their laptop and mobile devices due to the lack of both ICT network and its operating technology, and legal system associated with the transaction of business information. Finally, the study ends up with recommendations for policy makers to shape the future of e-Government system in both developing and developed countries.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.169-189
• /
• 2015

Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.

• Journal of Sensor Science and Technology
• /
• v.19 no.2
• /
• pp.99-111
• /
• 2010

This paper proposes an efficient hardware architecture to estimate disparities between 2D images for generating 3D depth images in a stereo vision system. Stereo matching methods are classified into global and local methods. The local matching method uses the cost functions based on pixel windows such as SAD(sum of absolute difference), SSD(sum of squared difference) and NCC(normalized cross correlation). The NCC-based cost function is less susceptible to differences in noise and lighting condition between left and right images than the subtraction-based functions such as SAD and SSD, and for this reason, the NCC is preferred to the other functions. However, software-based implementations are not adequate for the NCC-based real-time stereo matching, due to its numerous complex operations. Therefore, we propose a fast pipelined hardware architecture suitable for real-time operations of the NCC function. By adopting a block-based box-filtering scheme to perform NCC operations in parallel, the proposed architecture improves processing speed compared with the previous researches. In this architecture, it takes almost the same number of cycles to process all the pixels, irrespective of the window size. Also, the simulation results show that its disparity estimation has low error rate.

• Korean Journal of Soil Science and Fertilizer
• /
• v.37 no.4
• /
• pp.288-291
• /
• 2004

The development of land classification and soil productivity rating systems (SPR) are examined for their application to valuation of agricultural land in South Dakota, USA. For current and impending environmental and agricultural land issues, there is virtually no hard data available. Therefore, the study works with government and private sector clients to identify needs, and develop and apply a variety of techniques to mine data and carry out appropriate assessment methods. The application of SPR data to land valuation work conducted by real estate appraisers, tax assessors, and economists are discussed along with an assessment of its benefits and limitations. However, the actual value of the agricultural land can be determined by fulfilling the agricultural's vision of protecting and improving the environment by agricultural activities besides the safe food production. Therefore, it is increasingly important that we understand the impacts of farming and forestry on land, water and air.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.161-166
• /
• 2014

Recently, indoor sports simulator equipped with virtual reality devices, like screen golf system, are riding high. There have been many attempts to develop the indoor simulator systems which can make people enjoy exercises in various sports area. A real horseback riding could not have been popularized, because of the cost involved, difficulty to learn and its dangerousness. In this research, a robotic horseback riding platform based on parallel mechanism and virtual reality device is proposed. The proposed platform provides realistic riding feels and various levels of riding difficulty. The equipped motion capture system with a vision sensor enables riders to correct their riding posture based on expert's one. The developed horseback riding platform make it possible to enjoy a horseback riding in all weather, and also can be used for systematic horseback riding training.