• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.590-593
• /
• 2001

In this paper we describe the 6-axes robot's position determination using a stereo vision and an image based control method. When use a stereo vision, it need a additional time to compare with mono vision system. So to reduce the time required, we use the stereo vision not image Jacobian matrix estimation but depth estimation. Image based control is not needed the high-precision of camera calibration by using a image Jacobian. The experiment is executed as devide by two part. The first is depth estimation by stereo vision and the second is robot manipulator's positioning.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.118-122
• /
• 1997

This paper presents a 3d image processing which uses neural networks to combine a 2D vision camera and a laser slit beam. A laser slit beam from laser source is slitted by a set of cylindrical lenses and the line image of the slit beam on the object is used to estimate the object parameters. The neural networks allow to get the 3D image parameters such as the size, the position and the orientation form the line image without knowing the camera intrinsic parameters.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2006.06a
• /
• pp.34-39
• /
• 2006

An automated surface-strain measurement system, named ASIAS, was developed by using the image processing and stereo vision techniques in the previous studies by the corresponding author and his coworkers. This system has been upgraded mainly to improve the accuracy through image enhancement, sub-pixel measurement, surface smoothing, etc., since the first version was released. The present study has still more improved the convenience of users as well as the accuracy of measurement by processing high resolution images 8 mega pixels or more which can be easily obtained from a portable digital steal camera. It is proved that high resolution image processing greatly decreases the measurement error and gives strain data without considerable deterioration of accuracy even when the deformed grids to be measured and the master grids for camera calibration are captured together in the same image, making the whole process of strain measurement much simpler.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.1
• /
• pp.66-72
• /
• 2004

To assess tunnel safety, cracks in tunnel lining are measured by inspectors, who observe cracks with their naked eyes and record them. But manual inspection is slow, and measured crack data is subjective. Therefore, this study proposes inspection system fur measuring cracks in tunnel lining and providing objective crack data to be used in safety assessment. The system consists of On-vehicle system and Laboratory system. On-Vehicle system acquires image data with line CCD camera on scanning along the tunnel lining. Laboratory system extracts crack information from the acquired image using image processing. Measured crack information is crack thickness, length and orientation. To improve accuracy of crack recognition, the geometric properties and patterns of cracks in concrete structure were applied to image processing. The proposed system was verified with experiments in both laboratory environment and field environment such as subway tunnel.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.4
• /
• pp.288-292
• /
• 2016

In this paper, we propose an infrared image based human victim recognition method for a search and rescue robot in dark environments, like general disaster situations. For recognizing a human victim, an infrared camera on a RGB-D camera, Microsoft Kinect, is used. The contrast and brightness of the infrared image are first improved by histogram equalization, and the noise on the image is removed by morphological operation and Gaussian filtering. For recognizing a human victim, the binarization and blob labeling methods are applied to the improved image. Finally, for verifying the effectiveness and feasibility of the proposed method, an experiment for human victim recognition is carried out in a dark environment.

• Journal of information and communication convergence engineering
• /
• v.11 no.2
• /
• pp.132-138
• /
• 2013

In this paper, an accelerated generation algorithm to effectively generate an elemental image array in computational integral imaging system is proposed. In the proposed method, the depth information of 3D object is extracted from the images picked up by a stereo camera or depth camera. Then, the elemental image array can be generated by using the proposed accelerated generation algorithm with the depth information of 3D object. The resultant 3D image generated by the proposed accelerated generation algorithm was compared with that the conventional direct algorithm for verifying the efficiency of the proposed method. From the experimental results, the accuracy of elemental image generated by the proposed method could be confirmed.

• Current Optics and Photonics
• /
• v.3 no.5
• /
• pp.408-414
• /
• 2019

In this paper we propose a method to generate a true color image in scanning white-light interferometry (SWLI). Previously, a true color image was obtained by using a color camera, or an RGB multichannel light source. Here we focused on acquiring a true color image without any hardware changes in basic SWLI, in which a monochrome camera is utilized. A Fourier transform method was used to obtain the spectral intensity distributions of the light reflected from the sample. RGB filtering was applied to the intensity distributions, to determine RGB values from the spectral intensity. Through color corrections, a true color image was generated from the RGB values. The image generated by the proposed method was verified on the basis of the RGB distance and peak signal-to-noise ratio analysis for its effectiveness.

• Current Optics and Photonics
• /
• v.3 no.4
• /
• pp.329-335
• /
• 2019

Wide FOV imaging systems are important for acquiring rich visual information. A conventional catadioptric imaging system deploys a camera in front of a curved mirror to acquire a wide FOV image. This is a cumbersome setup and causes unnecessary occlusions in the acquired image. In order to reduce both the burden of the camera deployment and the occlusions in the images, this study uses a secondary planar mirror in the catadioptric imaging system. A compact design of the catadioptric imaging system and a condition for the position of the secondary planar mirror to satisfy the central imaging are presented. The image acquisition model of the catadioptric imaging system with a secondary planar mirror is discussed based on the principles of geometric optics in this study. As a backward mapping, the acquired image is restored to a distortion-free image in the experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1565-1567
• /
• 2004

Various defects are found in FPD (Flat Panel Display) manufacturing process. So detecting these defects early and reprocessing them is an important factor that reduces the cost of production. In this paper, the bare glass inspection system for the FPD which is the early process inspection system in the FPD manufacturing process is designed and implemented using the high performance and accuracy CCD line scan camera. For the preprocessing of the high speed line image data, the Image Processing Part (IPP) is designed and implemented using high performance DSP (Digital signal Processor), FIFO (First in First out), FPGA (Field Programmable Gate Array) and the Data Management and System Control part are implemented using ARM (Advanced RISC Machine) processor to control many IPP and cameras and to provide remote users with processed data. For evaluating implemented system, experiment environment which has an area camera for reviewing and moving shelf is made.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.364-366
• /
• 2004

WDR(Wide Dynamic Range) camera has been recently introduced to provide good detailed information for the extremely dark or white area. The double shuttering camera acquires two pictures with different exposure time for the same scenes so that each image has its unique information as for the bright/dark area. Those images are combined internally to produce an image with enough details. This paper proposes a NN based method to control the exposure time of the WDR camera. Our goal is to develop a method to automatically control the exposure time like human decision. A neural model is trained to determine to increase/decrease shutter time for the given situation. The ability to adapt to unknown situation is shown for the sample cases.