• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.52-58
• /
• 2007

In this paper we propose a new robust method to extract accurate human silhouettes indoors with active stereo camera. A prime application is for gesture recognition of mobile robots. The segmentation of distant moving objects includes many problems such as low resolution, shadows, poor stereo matching information and instabilities of the object and background color distributions. There are many object segmentation methods based on color or stereo information but they alone are prone to failure. Here efficient color, stereo and image segmentation methods are fused to infer object and background areas of high confidence. Then the inferred areas are incorporated in graph cut to make human silhouette extraction robust and accurate. Some experimental results are presented with image sequences taken using pan-tilt stereo camera. Our proposed algorithms are evaluated with respect to ground truth data and proved to outperform some methods based on either color/stereo or color/contrast alone.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.3
• /
• pp.34-38
• /
• 2007

There has been skeptical aspects for the robot to be effective in combat fields even though consensus of operational needs and some technological advancements. One of fundamental problems is difficulties in the autonomous technology applicable. This technology is not sufficient to be applied for heavy combat operation, therefore, developer first make open architecture, then, application is implemented on the condition that new functions or technologies will be developed later. It is also required to partition all the functions with common segments which are general to all platforms in order to operate together in the fields and to reduce the load of development to each platform respectively. In addition, common middleware based on the reference architecture is also developed to accommodate new technology evolution. This paper introduces the architecture and middleware applied in XAV(eXperimental Autonomous Vehicle) developed in ADD. In addition, the performance of autonomous navigation and system design characteristics are introduced briefly.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.151-157
• /
• 2013

This paper proposes an online adaptive fuzzy controller for a wind energy conversion system (WECS) that is intrinsically highly nonlinear plant. In real application, to obtain exact system parameters such as power coefficient, many measuring instruments and off-line implementations are required, which is very difficult to perform. This shortcoming can be avoided by introducing fuzzy system in the controller design in this paper. The proposed adaptive fuzzy control scheme using self-structuring algorithm requires no system parameters to meet control objectives. Even the structure of the fuzzy system is automatically grows on-line, which distinguishes our proposed algorithm over the previously proposed fuzzy control schemes. Combining derivative estimator for wind velocity, the whole closed-loop system is shown to be stable in the sense of Lyapunov.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.731-733
• /
• 2016

The primary goal of the line tracer is to accurately and quickly detect the movement up to the target position given by the sensor juhaengseon. It has been used in applications in various fields such as the current unmanned transport vehicles, laser cutting machine, autonomous mobile robots and unmanned driving is possible, and is held annually at various universities in the competition field with the possibility of great progress, depending on the application. However, there arises a large difference in running performance, depending on the hardware design and control. In this paper, improving the characteristics of the tracer line and characters to design a PID controller is to apply the point on ways of improving the properties of the system.

• Journal of Convergence for Information Technology
• /
• v.7 no.5
• /
• pp.95-102
• /
• 2017

Modular toys for creative education require functional blocks to create various types of movements. An active drive module and a lot of passive connection blocks are needed to express motion with combination. In this paper, we propose the design of modular toys to produce various creative movements and controller structure working with them. In order to facilitate the connection between the designed modules, a connection method and a suitable mechanism are suggested. We also dealt with the design of various types of sensor modules that can work in conjunction with modular toys. Using these toys, typical standard application form that can be imitated educationally is suggested and showed the usefulness of the modular toy by actually applying it with designed modules and components. The proposed method is applied to actual educational toys, and the operation is effectively performed by recording operation and playing repetitive operation.

• Journal of The Korean Association of Information Education
• /
• v.14 no.3
• /
• pp.385-393
• /
• 2010

Elementary information education is currently provided in accordance with the 2000 ICT educational guidelines. Although the focus of education has shifted from practical use to computer science since 2005, in which way academic education should be led isn't yet clear. The purpose of this study was to examine the impacts of computer science education(CS education) by an education programming tool on school children's awareness of that education. The selected students received education about unplugged, scratch and robot programming, part of the computer science curriculum, in 12 sessions. As a result, there were significant differences between the experimental and control groups in all the variables that included attitude to computer science, interest in that, satisfaction level, self-efficacy and perception of the value of CS education. The findings of the study suggested that in CS education, the improvement of thinking faculty should take precedence over practical use of what's learned, which is expected to heighten the value of that education.

• The Journal of the Convergence on Culture Technology
• /
• v.1 no.1
• /
• pp.73-77
• /
• 2015

Existing sports simulators on the market focus on the motion of platform or reality expression using basic visual contents, and are limited to entertainment products. Therefore, the stimulus on 5 senses is not good enough to be applied on high virtual reality. Moreover, there are not enough professional contents to be applied to an educational sports simulator. In this paper, we developed a sport platform by separating the multi axis based common platform module and the sports application module. We designed the common platform which has 4 degrees of freedom such as surge, sway, heave and yaw motion. This platform has the purpose of stabilizing motion and minimizing interference. The changeable sport module which is attached to the common module has 2 degrees of freedom such as roll and pitch, so that it can be applied to the various fields of 2 degrees of freedom virtual reality sports such as horse riding and yacht.

• Proceedings of the CALSEC Conference
• /
• 1999.07a
• /
• pp.277-299
• /
• 1999

Since Chrysler Motor Co. had experienced the digital development system in the beginning of 1990's, most of leading automobile companies are trying to apply a digital information system for their own business process reengineering based upon concurrent engineering system from product planning phase. This is called as virtual DMU(Digital Mock-Up) system instead of the traditional PMU(Physical Mock-Up) system. By using the virtual prototype, all of the design requirements and system specifications can be checked, changed and optimized more quickly and more efficiently. This paper consists of five chapters for the DMU information system. In the 1$^{st}$ chapter, the principle of digital design system is suggested by using four basic modules such as product design module, process design module, manufacturing system design module and central control module. The basic scheme of DMU is introduced with the benefits of application in the chapter 2. In the chapter 3, a digital design process of new car development is explained with the detailed DMU design and design review processes. In the chapter 4, the practical DMU manufacturing techniques and applications are introduced as CAD/CAM analyses, DPA(Digital Pre-Assembly)reviews for development, production, operation and maintenance phases, digital tolerance analyses and digital factory analyses for assembling line simulation, automated robot welding processes, production jig ＆ fixtures and painting process simulation. Finally, the activities of digital design support; CAS-styling, CAE-engineering and CAT-testing are summarized for design optimization in the chapter 5. As today's automobile manufactures and related business organizations are struggling to compete in the global marketplace, they are concentrating on efficient use of DMU information system to reduce the new car development cost, to have shorten the delivery schedule and to improve product design quality. To meet the demand of those automobile industries on digital information systems, the CALS(Computer aided Acquisition and Logistics Support) and EC(Electronic Commerce)initiative has been focused as a dominant philosophy in defense ＆ commercial industries, specially automobile industries.s.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.4
• /
• pp.106-115
• /
• 2003

In crossing stereo camera system as a security equipment system, a new algorithm for the tracking method of the moving object and the measurement method of distance of the object from cameras to moving object is proposed. The stereo input images are matched by a pixel for the moving object extraction, then the moving elements obtained from an adaptive threshold's value for an error correction and the moving object area extracted by noise eliminative algorithm. In addition to, the moving object traced by control pan/tilt of cameras using a coordinate value of the moving object, and the measurement method of distance to moving object by using special features of the crossing stereo camera system is proposed. From the experimental results, the proposed algorithm was found to be able to measure of the distance and trace for moving object in a stereo security camera system. The error rate of a distance measurement be existed within 6%. Moreover in implementation the proposed algorithm, the stereo security system, the automatic moving robot system and the stereo remote control system will be applied practical application.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2179-2184
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper described appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.