• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.5
• /
• pp.973-979
• /
• 2007

A laser vision system is developed to measure the three-dimensional feature of an object. This system consists of two low cost cameras and a cross laser. One camera and a cross laser are used to measure a plane equation of an object. Using this information, the other camera measures a hole size of an object. The proposed system provides 0.05 mm accuracy measurement systems with relatively low cost.

• KIEAE Journal
• /
• v.3 no.2
• /
• pp.59-66
• /
• 2003

To be the design method supporting aesthetic ability of human, CAAD system should essentially recognize architectural form in the same way of human. In this study, visual perception process of human was analyzed to search proper computational method performing similar step of perception of it. Through the analysis of visual perception, vision was separated to low-level vision and high-level vision. Edge detection and neural network were selected to model after low-level vision and high-level vision. The 24 images of building, tree and landscape were processed by edge detection and trained by neural network. And 24 new images were used to test trained network. The test shows that trained network gives right perception result toward each images with low error rate. This study is on the meaning of artificial intelligence in design process rather than on the design automation strategy through artificial intelligence.

• Journal of Biosystems Engineering
• /
• v.23 no.5
• /
• pp.481-490
• /
• 1998

A computer vision system to measure low flow rate of solid particles was developed and tested to examine its performance with various sized 7 kinds of seeds, perilla, mung bean, paddy, small red bean, black soybean, Cuba bean and small potato tuber. The test was performed for two types of particle flow, continuous and discontinuous. For the continuous flow tested with perilla, mung bean and paddy, the tests resulted correlation coefficients for the flow rates measured by the computer vision and direct method about 0.98. Average errors of the computer vision measurement were in a range of 6∼9%. For the discontinuous flow tested with small red bean, black soybean, Cuba bean and small potato tuber, the tests resulted correlation coefficients for the flow rates measured by the computer vision and direct method 0.98∼0.99. Average errors of the computer vision measurement were in a range of 5∼10%. Performance of the computer vision system was compared with that of the conventional optical sensor to count particles in discontinuous flow. The comparison was done with black soybean, Cuba bean and small potato tuber, and resulted that the computer vision has much better performance than the optical sensor in a sense of precision of the measurement.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.6
• /
• pp.546-551
• /
• 2011

Tilt sensor is required to control the attitude of the biped robot when it walks on an uneven terrain. Vision sensor, which is used for recognizing human or detecting obstacles, can be used as a tilt angle sensor by comparing current image and reference image. However, vision sensor alone has a lot of technological limitations to control biped robot such as low sampling frequency and estimation time delay. In order to verify limitations of vision sensor, experimental setup of an inverted pendulum, which represents pitch motion of the walking or running robot, is used and it is proved that only vision sensor cannot control an inverted pendulum mainly because of the time delay. In this paper, to overcome limitations of vision sensor, Kalman filter for the multi-rate sensor fusion algorithm is applied with low-quality gyro sensor. It solves limitations of the vision sensor as well as eliminates drift of gyro sensor. Through the experiment of an inverted pendulum control, it is found that the tilt estimation performance of fusion sensor is greatly improved enough to control the attitude of an inverted pendulum.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.605-611
• /
• 2019

3D Vision system has many applications recently but popularization have many problems that need to be overcome. Volumetric display may process a amount of visual data and design the high efficient vision system for display. In case of stereo system for volumetric display, disparity vectors from the stereoscopic sequences and residual images with the reference images has been transmitted, and the reconstructed stereoscopic sequences have been displayed at the receiver. So central issue for the design of efficient volumetric vision system lies in selecting an appropriate stereo matching and robust vision system. In this paper, we propose high efficient vision system with the reduction of rectification error which can perform the 3D data extraction efficiently with low computational complexity. In experimental results with proposed vision system, the proposed method can perform the 3D data extraction efficiently with reducing rectification error and low computational complexity.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.66-71
• /
• 2023

As cameras have become primary sensors for mobile robots, vision based Simultaneous Localization and Mapping (SLAM) has achieved impressive results with the recent development of computer vision and deep learning. However, vision information has a disadvantage in that a lot of information disappears in a low-light environment. To overcome the problem, we propose an image enhancement method to perform visual SLAM in a low-light environment. Using the deep generative adversarial models and modified gamma correction, the quality of low-light images were improved. The proposed method is less sharp than the existing method, but it can be applied to ORB-SLAM in real time by dramatically reducing the amount of computation. The experimental results were able to prove the validity of the proposed method by applying to public Dataset TUM and VIVID++.

• ETRI Journal
• /
• v.30 no.6
• /
• pp.783-789
• /
• 2008

A bio-inspired vision chip for edge detection was fabricated using 0.35 ${\mu}m$ double-poly four-metal complementary metal-oxide-semiconductor technology. It mimics the edge detection mechanism of a biological retina. This type of vision chip offer several advantages including compact size, high speed, and dense system integration. Low resolution and relatively high power consumption are common limitations of these chips because of their complex circuit structure. We have tried to overcome these problems by rearranging and simplifying their circuits. A vision chip of $160{\times}120$ pixels has been fabricated in $5{\times}5\;mm^2$ silicon die. It shows less than 10 mW of power consumption.

• Journal of Korea Multimedia Society
• /
• v.23 no.11
• /
• pp.1418-1427
• /
• 2020

The web has become indispensable in all of our daily lives. We communicate, study and get information with others through the web. This behavior also continues in the smart phone environment. The biggest problem is that the small display screen of a smart phone degrades the accuracy in selecting or manipulating content for people with low vision. To compensate for this, voice guidance services that combine touch and voice, such as VoiceOver and Talkback, are currently provided to smart phone devices. However, restrictions arise in GUI, TTS control problems, and content expansion and selection. In addition, unnecessary content is also output by voice, which causes fatigue for low vision people to use. In this study, we propose a mobile web browser interface that selects and enlarges a desired area from web browsers and contents, or outputs it as a voice so that people with low vision can easily use the mobile web browser. In this paper, we propose a context selective focusing function that enables selection for each element of web content. In addition, we intend to develop a mobile voice web browser that can enlarge the selected content or output it by voice.

• Journal of Korean Ophthalmic Optics Society
• /
• v.13 no.2
• /
• pp.51-57
• /
• 2008

Purpose: This study has been conducted to know how the size and position of the circle of least confusion has an influence on the vision for minimization of asthenopia when astigmatism is corrected and appropriated prescription to provided clear vision life. Methods: The method of the study has been worked on 68 students (136 eyes) of man and woman enrolled in university of Gyeong-gi-do aged 20 to 40, who have myopic astigmatism in order to know how the corrected vision changes according to the size and position of the circle of least confusion of astigmatism, the vision has been tested by giving the vision whose astigmatic power of 0.25D and 0.50D was just reduced, low correcting the astigmatic power into 0.50D, and at the same time inserting additionally spherical power -0.25D, all under a condition that the corrected vision after completely corrected astigmatism, and the axis of astigmatism was not changed. Results: The average vision was 1.047 when the astigmatic power was fully corrected, and in low correction of 0.25D, it was 0.914, and in low correction of 0.50, it was 0.772. It has been learned that the bigger the circle of least confusion was the bigger the range of vision reduction and the corrected vision in astigmatism has correlation with the size of the circle of least confusion. It has been examined that the average vision according to position of the circle of least confusion in astigmatism was 1.047 when the astigmatic power was completely corrected and focused on the retina with state of point, and in case that the astigmatic power was 0.50D of state of low correction, that is, the circle of least confusion was focused before retina, it was 0.828, and it was also 0.826 when the astigmatic power is low corrected with 0.50D and the circle of least confusion was focused on the retina. Explained briefly, It has been examined that in case that the state of low correction of the astigmatic power was same, the vision reduction was less in the image of the circle of least confusion focused upon the retina than in the image of its being focused before the retina. Conclusions: In case that the refractive power of cylindrical lens is reduced in test of wearability in astigmatism, there needs surely an adjustment of spherical lens that can place the circle of least confusion on the retina.

• Journal of Korean Ophthalmic Optics Society
• /
• v.16 no.3
• /
• pp.319-325
• /
• 2011

Purpose: The relativity of factors between low vision and socioeconomic status were investigated. This study represented the preliminary data for establishment of public eye health policy. Further, this report would encourage people to change the social attitudes about the eye health equity of the nation. Methods: The number of people (2,514 people) who have been tested the forced visual activity were examined as it was referred the Korea National Health and Nutrition Examination Survey (KNHNE) of 2009-year data. The prevalence rate of low vision of subjects which are related with house income, education level and occupations were conducted with ttest and chi square test. Besides, the Binominal Logistic Regression was conducted to measure the odds ratio of the subjects. Results: In outline, the prevalence rate of low vision was high with low house income, low education level and low function. The odds ratio represented that 2.77(95% CI, 1.72-4.47) at low house income group and 4.02(95% CI, 1.75-9.23) at the case of below primary school education level. Moreover, the results of unemployed group showed 3.65(1.14-11.68) from the odds ratio measurement. Conclusions: The eye health policy need be instituted which is broad and meticulous support to ease the eye health equity of low eye sight patients. For instance, the education about eye health, examination business of eye disease, and education of assistant units which are useful for low eye sight would suggest practical solution.