• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.153-158
• /
• 2000

This paper addresses an intelligent robot control system using an off-line programming to teach a precise assembly task of electronic components in a flexible way. The investigated task consists of three job: heat caulking test, soldering on a circuit board, and checking of soldering defects on the back cover of a camera. This study investigates the remodelling of the most complicated cell in terms of the accuracy and fault rate among the twelve cells in a camera back-cover assembly line. We have attempted to enhance back-cover assembly line. We have attempted to enhance soldering quality, to add task flexibility, to reduce failure rate, and to increase product reliability. This study modifies the cell structure, and improves the soldering condition. The developed all system implements the real-time control of assembly with vision data, and realized an easier task teaching on off-line programming.

• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.1255-1258
• /
• 2008

Roll to roll (R2R) system, known as 'web processing', is the process of producing these electronic devices on a roll of flexible plastic. With the need of improved performance and productivity in R2R industry, effective control and on-line supervision for web quality is essential. In this report, we present a system for on-line measurement of wrinkles, one of defects incurring due to compressive stresses developed in the web. This system is able to capture an image generated when a well defined line shape laser beam passes through a transparent web. The system calculates 3D shape information, including the height of the wrinkle on the web, and displays the images for the shape information of the web in real time. By using area scan camera and machine vision laser, this system takes more advantages of setting up as a simple and low cost system compared to the line scan camera systems that widely used in web manufacturing. Specific calibration method and analysis on the achievable accuracy will be discussed.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.8
• /
• pp.113-121
• /
• 1999

It is necessary to calibrate measurement systems to enhance its measurement accuracy. The visual sensing system that is presented in our previous work has to be calibrated, too. It is a multiple mirror system for three-dimensional measurement, which is composed of a camera and a series of mirrors. It is important to calibrate the positions and orientations of the mirrors relative to the camera because they have direct influence on the relationship between the image plane and the task space. This paper presents the calibration method for the visual sensing system. To confirm the measurement performance of the implemented system. its measurement accuracy in measuring the locations in three-dimensional space is investigated. A series of experiments for measuring the locations of the circle-shaped marks are performed. Experimental results show that the sensing system can be effectively used for three-dimensional measurement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.9
• /
• pp.3721-3737
• /
• 2015

3D reconstruction based on binocular data is significant to machine vision. In our method, we propose a new and high efficiency 3D reconstruction approach by using a consumer camera aiming to: 1) address the configuration problem of dual camera in the binocular reconstruction system; 2) address stereo matching can hardly be done well problem in both time computing and precision. The kernel feature is firstly proposed in calibration stage to rectify the epipolar. Then, we segment the objects in the camera into background and foreground, for which system obtains the disparity by different method: local window matching and kernel feature-based matching. Extensive experiments demonstrate our proposed algorithm represents accurate 3D model.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• Journal of the Semiconductor & Display Technology
• /
• v.6 no.3
• /
• pp.65-70
• /
• 2007

A method to focus the object in camera system by applying the Hill climb algorithm from optical lens moving device (VCM; Voice coil motor) is proposed. The focusing algorithm from VCM is focus on the object but in these criteria is a well-known drawback; the focus is good only at same distance objects but the focus is bad (blur image) at different distance objects because of the DOF (Depth of focus) or DOF (Depth of field) at the optical characteristic. Here, the new camera system that describes the Reflector of free curvature systems (or Diffractive Fresnel lens) and the partition of focusing window area is proposed. The method to improve the focus in all areas (different distance objects) is proposed by new optical system (discrete auto in-focus) using the Reflector of free curvature systems (or Diffractive Fresnel lens) and by applying the partition of all areas. The proposal is able to obtain good focus in all areas.

• Journal of information and communication convergence engineering
• /
• v.8 no.4
• /
• pp.466-471
• /
• 2010

We have proposed a method to detect and track moving ships using position from Radar and image processor. Real-time segmentation of moving regions in image sequences is a fundamental step in the radar-camera integrated system. Algorithms for segmentation of objects are implemented by composing of background subtraction, morphologic operation, connected components labeling, region growing, and minimum enclosing rectangle. Once the moving objects are detected, tracking is only performed upon pixels labeled as foreground with reduced additional computational burdens.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.03a
• /
• pp.52-55
• /
• 1996

Though the increment of using computer vision system in modern industry, there are lots of difficulties to measure precisely because of measurement error distortion phenomenon. Between these reasons, the distortion of edge is dominant reason which is occured by the blurred image. The blurred image is happened when camera can not discriminate its precise focus. To correct and generalize distortion phenomenon is imprrtant. Thus we must fix the discrimination criteria which is collected by image recognition of precise focus. The edge of image means discontinuous point of intensity, and the component of edge is discribed as high frequency component at special domain specturm of image. The good condition of focus means there are much high frequency energy in image. The method of discribing high frequency energy is gradient operater which determines the condition of focus.

• Proceedings of the KSR Conference
• /
• 2006.11b
• /
• pp.1483-1487
• /
• 2006

In electric railway, image monitoring using high speed camera provides reliable, timely information of wear and geometry status, important in taking decisions for overhead contact wire maintenance. The contribution of this research is the development of a simple real-time monitoring system for use in measurement subsystem of contact wire and geometry of overhead contact wire in electric railway. The system has been consists of a high speed CMOS camera with resolution $1024{\times}1280$ pixels, line type laser source and PC-based image acquisition system with PCI Express slot. Vision acquisition software have been used in application programming interface for image acquisition, display, and storage with a frequency of sampling of 500 acquisitions per second.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.10
• /
• pp.82-88
• /
• 2003

Many visual servoing algorithms have been recently developed by the robot vision researchers. They do not, however, consider the stability of servoing system. The camera calibration is the most important factor to the control stability and performance of position based visual servoing. In this article we describe the ECL(End Point Closed Loop) servoing can make no steady state error for the control of 6-DOF robot of which accuracy is dependent on the camera calibration and kinematics. And we propose a dynamic calibration algorithm, which can improve stability and performance of ECL visual servoing. To verify the potential of our approach, we run assembly experiments and present our finding.