• Journal of KIISE:Software and Applications
• /
• v.30 no.12
• /
• pp.1228-1238
• /
• 2003

This paper presents a new and practical method based on computer vision for detecting the monitor position where the user is looking. In general, the user tends to move both his face and eyes in order to gaze at certain monitor position. Previous researches use only one wide view camera, which can capture a whole user's face. In such a case, the image resolution is too low and the fine movements of user's eye cannot be exactly detected. So, we implement the gaze detection system with dual camera systems(a wide and a narrow view camera). In order to locate the user's eye position accurately, the narrow view camera has the functionalities of auto focusing and auto panning/tilting based on the detected 3D facial feature positions from the wide view camera. In addition, we use dual R-LED illuminators in order to detect facial features and especially eye features. As experimental results, we can implement the real-time gaze detection system and the gaze position accuracy between the computed positions and the real ones is about 3.44 cm of RMS error.

• Clinical and Experimental Pediatrics
• /
• v.55 no.1
• /
• pp.29-33
• /
• 2012

PHACE association is a rare neurocutaneous condition in which facial hemangiomas associate with a spectrum of posterior fossa malformations, arterial cerebrovascular anomalies, cardiovascular anomalies, and eye anomalies. We reported a case of PHACE association in a premature infant showing facial, intracranial, and oropharyngeal hemangiomas with evidence of the Dandy-Walker variant and complicated cardiovascular anomalies, including a right-sided aortic arch and an atypical patent ductus arteriosus arising from a tortuous left subclavian artery. To our knowledge, intracranial hemangiomas are rare in PHACE association, and a concomitant oropharyngeal hemangioma has not been previously reported in the PHACE association literature. In infants presenting with large, plaque-like facial hemangiomas, it is important to conduct active cardiovascular and neurological evaluations. Special attention should be given to the laryngoscopic examination to search for additional hemangiomas in the airway.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2711-2713
• /
• 2000

능동시각시스템의 가장 큰 장점은 주어진 환경에 대해 능동적으로 반응할 수 있는 자유도가 있어 이를 활용하여 필요한 정보를 쉽게 추출할 수 있다는 점이다. 이를 위해서는 능동시각시스템의 시선을 원하는 위치로 이동시키는 것이 필요한데, 시스템의 여자유도 인해 해가 무수히 많이 존재하게 된다. 본 논문에서는 이러한 여자유도 문제를 기구의 동역학적 특성을 제한 조건으로 하여 최적의 해를 구하고 이를 이용해 각 관절을 제어하는 제어기를 설계하는 방법에 대해 소개한다. 설계된 제어기는 제작과 실험을 통해 고속으로 움직이는 물체를 실시간으로 추적하는 성능을 보였다.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1257-1271
• /
• 2022

Recently, many Earth observation optical satellites have been developed, as their demands were increasing. Therefore, a rapid preprocessing of satellites became one of the most important problem for an active utilization of satellite images. Satellite image matching is a technique in which two images are transformed and represented in one specific coordinate system. This technique is used for aligning different bands or correcting of relative positions error between two satellite images. In this paper, we propose an automatic image matching method among satellite images with different ground sampling distances (GSDs). Our method is based on improved feature matching and robust estimation of transformation between satellite images. The proposed method consists of five processes: calculation of overlapping area, improved feature detection, feature matching, robust estimation of transformation, and image resampling. For feature detection, we extract overlapping areas and resample them to equalize their GSDs. For feature matching, we used Oriented FAST and rotated BRIEF (ORB) to improve matching performance. We performed image registration experiments with images KOMPSAT-3A and RapidEye. The performance verification of the proposed method was checked in qualitative and quantitative methods. The reprojection errors of image matching were in the range of 1.277 to 1.608 pixels accuracy with respect to the GSD of RapidEye images. Finally, we confirmed the possibility of satellite image matching with heterogeneous GSDs through the proposed method.

• Environmental Analysis Health and Toxicology
• /
• v.15 no.3
• /
• pp.61-67
• /
• 2000

Toxic lesions of styrene in the Japanese Medaka (Oryzias latipes) were compared with those of styrene oxide, the active metabolite of styrene, using embryo-larval assays. The developmental stages of Japanese Medaka (Oryzias latipes) treated with both chemicals were not altered and progressed normally. However, styrene oxide was more toxic than styrene in terms of causing death and lesions . High concentrations of styrene (higher than 4.9 ppm) and styrene oxide (higher than 2.4 ppm), resulting in more than 50% mortality, caused similar lesions of cardiovascular system, craniofacial bone formation and spinal deformities, although a number of lesions were not observed by both chemicals . In the group treated with styrene, eyeball sizes and intereye distances were reduced, while, in the group treated with styrene oxide , the eyes and eye cups were not developed and two eyes were sometimes fused. In addition, styrene oxide caused the lesion which involved the posterior brain and brain stem were herniated through the spinal cord . The noticeable difference of toxic symptoms between these two chemicals was the time of onset. Toxicities of cardiovascular system and craniofacial bone formation appeared on day 3 of development in styrene oxide treated group, but, styrene treated group staned to show hemorrhages on day 3 and the craniofacial malformation were appeared on day 5, These differences between two chemicals may be due to the metabolism of styrene to styrene oxide, the reactive intermediate.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1979-1980
• /
• 2006

최근 인간과 유사한 휴머노이드에 대한 연구가 상당히 활발하고 그 영역이 계속해서 확대되고 있는 추세다. 휴머노이드에는 로봇의 몸체 뿐 아니라 머리 부분, 특히 시각 시스템이 매우 중요하다. 본 논문에서는 생리학적인 측면에서 인간의 눈과 목의 운동을 관찰하여 휴머노이드에 적용 가능한 능동 시각 시스템의 기구부 설계 방법을 제안하고 제어 방식을 설명한다. 기존의 팬-틸트 방식의 시각 시스템에 없는 인공 안구의 롤 회전 기능을 추가함으로써, 사람의 시각 시스템과 거의 유사한 동작 영역과 동작 속도를 보이게 된다. 소형 비전센서 모듈을 사용함으로써 시스템의 크기가 줄고 경량화 되었다. DC 모터를 엑츄에이터로 사용함으로써, 위치와 속도 제어가 가능하고, 인간 안구의 단속적 운동을 모사 할 수 있다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.5
• /
• pp.805-815
• /
• 2001

Glaucoma is an eye disease which is caused by abnormal high IOP (Intra Ocular Pressure). High IOP is caused by the aqueous humor which is produced consistently but not drained due to malfunction of the trabecular system which has a role of draining the aqueous humor into the venous system. Currently, there are three methods to treat glaucoma-using medicines, surgical operation, and using implant device. The first and second methods are not long acting, so the use of implants is increasing in these days in order to drain out the aqueous humor compulsory. However, though conventional implants have a capability of pressure regulation, they cannot maintain IOPs desired for different patients, and too much aqueous humor are usually drained, to cause hypotony. To solve these problems, it is needed to develop a new implant which is capable of controling the IOP actively and copes with personal difference of patients. An active glaucoma implant consists of the valve actuator, pressure sensor, controller, and power supply. In this paper, firstly, we make an analysis of the operation of a conventional implant using a bond graph and show defects and limitations of the conventional valve analytically. Secondly, we design and analyze a valve actuator considering actuation principles, resistance elements, control methods, and energy sources focused on power saving problem. Finally, using simulations the possibility of the proposed valve actuator is investigated.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.6 no.2
• /
• pp.195-201
• /
• 2005

This paper describes preliminary results we have obtained in developing a computer vision system based on active IR illumination for real time gaze tracking for interactive graphic display. Unlike most of the existing gaze tracking techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze tracker can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using the Generalized Regression Neural Networks (GRNN). With GRNN, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Furthermore, the mapping function can generalize to other individuals not used in the training. The effectiveness of our gaze tracker is demonstrated by preliminary experiments that involve gaze-contingent interactive graphic display.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.477-483
• /
• 2004

This paper describes preliminary results we have obtained in developing a computer vision system based on active IR illumination for real time gaze tracking for interactive graphic display. Unlike most of the existing gaze tracking techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person our gaze tracker can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using the Generalized Regression Neural Networks(GRNN). With GRNN, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Futhermore, the mapping function can generalize to other individuals not used in the training. The effectiveness of our gaze tracker is demonstrated by preliminary experiments that involve gaze-contingent interactive graphic display.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.917-922
• /
• 2021

In modern society, deaths and property damage due to drowsiness occur every year enormously. Methods to reduce such damage are being studied a lot in all walks of life, and research on preventing drowsy driving is particularly active in automobiles. In this paper, as an Arduino-based water gun firing system that learns open and closed eyes using YOLO, we propose a drowsy prevention system that fires a water gun when the duration of the closed eye exceeds a certain time. This system can be applied and used in various fields, but especially when applied to a car, it is not necessary to purchase expensive specifications and if you pay a little attention, you can reduce accidents caused by drowsy driving by 100% at a very low cost. In addition, it can be said that it is an independent system that overcomes different specifications for each company.