• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.6
• /
• pp.867-875
• /
• 2004

In order to inspect burr geometry and hole quality in micro-drilling processes, a cost-effective method using an image processing and shape from focus (SFF) methods on the machine tool is proposed. A CCD camera with a zoom lens and a novel illumination unit is used in this paper. Since the on-machine vision unit is incorporated with the CNC function of the machine tool, direct measurement and condition monitoring of micro-drilling processes are conducted between drilling processes on the machine tool. Stainless steel and hardened tool steel are used as specimens, as well as twist drills made of carbide are used in experiments. Validity of the developed system is confirmed through experiments.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.743-746
• /
• 1998

In this paper, we developed an outdoor augmented reality system which has remote real scences acquisition ability. The real scenes acquisition system consists of image acquisition system, tracking system, wireless data transceiver and power supply. Tracking system that consists of Tans Vector and RT-20 measures a position and attitude of the CCD camera that attached at the remote control helicopter. Wireless data transceiver system is utilized for data transmission of remote system that of attitude, position information, andreal scenes data that acquired by the CCD camera. Maximum propelling power of remote control helicopter is 15Kg, so we used 7.2V li-ion cell as a power supply for system minimize. As the results of experiment, the developing system presented application possibility of remote information acquisition system such as construction simulation & estimation, broadcasting, tour guide.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1894-1898
• /
• 1991

A landmark tracking system(LTS) has been developed for use in locating objects in a manufacturing environment. The Landmark Tracking System is an integrated system which consists of a grey scale CCD camera, an image processor, an illumination system based on electronic flash, and software intended primarily for tracking retroreflective landmarks. The term "integreated" means that the camera electronics and the strobe electronics are directly linked to the computer system, governed by the same clock and under direct software control. A novel element in the LTS is that a pinhole is used for the optics.he optics.

• Journal of ILASS-Korea
• /
• v.1 no.2
• /
• pp.66-73
• /
• 1996

The present study investigates experimentally the characteristics of liquid jet, which is, the spray flow in the normal direction of the air stream under the flow conditions of air velocity $110\sim125m/s$. The present study adopts with the flow visualization technique using a short duration light bulb and the image processing analyse with CCD camera. Two types of injector were used: one is a flat plate type, and the other is backward facing step type, which height are 5, 8, 10mm. Dispersion of liquid jet can be represented by gray level of CCD camera. In the upstream of liquid jet, the backward facing step shows better liquid jet penetration. However, in the downstream. mean droplet size for backward facing step injector is smaller than that for flat plate injector

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.315-319
• /
• 2007

This paper presents a algorithm, what is able to recognize 4 different continuous human motion using a single stationary camera as input. For the first step, we acquire images from a camera. To enhance the image, we perform preprocessing which deals with removing noise using median filter, thresholding. And then morphological operations are performed to remove which small blobs and eliminates small holes. At the forth step, blobs are analysed to extracts for foreground region. Then, motions are predicted from these images by using optical flow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.644-647
• /
• 2003

This paper describes a neural network based machine vision system designed for inspecting yellow beans in real time. The system consists of a camera. lights, a belt conveyor, air ejectors, and a computer. Beans are conveyed in four lines on a belt and their images are taken by a monochrome line scan camera when they fall down from the belt. Beans are separated easily from their background on images by back-lighting. After analyzing the image, a decision is made by a multilayer artificial neural network (ANN) trained by the error back-propagation (EBP) algorithm. We use the global mean, variance and local change of gray levels of a bean for the input nodes of the network. In an our experiment, the system designed could process about 520kg/hour.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.1558-1563
• /
• 2004

A measurement technique for the void fraction and the bubble dynamics in gas-liquid two-phase flows has been proposed using a time-resolved two-phase PIV system. For the three-dimensional evaluation of the bubble information, both the images from the front and side views are simultaneously recorded into a high speed CCD camera by reflecting the side image into the front view with the help of a $45^{\circ}$ oriented mirror. Then, a stereo-matching technique is applied to calculate the void fraction, bubble size and shape. To obtain the rising bubble velocities, the 2-frame PTV method was applied. Consequently, the present technique shows good feasibility for the measurements of the volume fractions, mean diameters, aspect ratios and velocities of the bubbles at the three-dimensional point of view.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.4
• /
• pp.85-96
• /
• 2000

An Eggcrate assembly is an important part to hold and support 16,000 tubes containing hot and contaminated water in the steam generator of nuclear power plant. As a great number of tubes should be inserted into the eggcrate assembly, the dimensions of each eggcrate grid are one of the critical factors to determine the availability of tube insertion. in this paper. we propose a machine vision algorithm for measuring the inner-circle diameter of each eggcrate grid whose shape is not exact quadrangular. The overall procedure of the algorithm is composed of camera calibration, eggcrate image preprocessing, grid height adjustment, and inner-circle diameter estimation. The algorithm is tested on real specimens and the results show that the algorithm works fairly well.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.231-234
• /
• 2003

This paper describes the structure, operation, image processing, and decision making techniques of a color machine vision system designed for the automatic sorting of soybeans. The system consists of feeder, conveyor belt, line-scan camera, lights. ejector, and a PC Unlike manufactured goods, agricultural products including soybeans have quite uneven features. The criteria for sorting good and bad beans also vary depending on inspectors. We tackle these problem by letting the system learn the inspecting parameters from good samples selected manually by a machine user before running the system for sorting. Real-time processing has another importance In the design. Four parallel DSPs are employed to increase the processing speed. When the designed system was tested with real soybeans and the result was successful.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.505-506
• /
• 2008

Motion capture system that is used in movies and games today requires large equipments and expensive that it is still not common as a reasonable family game. Therefore, this research project focused on solving these problems mentioned above and move on to develop a new type of approach and by using reasonable family use USB camera and augmented reality to develop a bodily sensation motion capture system which can be used in making a video game. In order to develop this, I used a pair of Marker which can be placed on both hands and one USB camera and the image that was extracted in real time goes through the AR toolkit and ed the 3D coordinates of data and developed a motion capture system.