• Journal of Korea Multimedia Society
• /
• v.17 no.7
• /
• pp.787-796
• /
• 2014

Many mobile robot navigation methods utilize laser scanners, ultrasonic sensors, vision camera, and so on for detecting obstacles and path following. However, human utilizes only vision(e.g. eye) information for navigation. In this paper, we study a mobile robot control method based on only the camera vision. The Gaussian Mixture Model and a shadow removal technology are used to divide the foreground and the background from the camera image. The mobile robot uses a combined CAMSHIFT and KLT feature tracker algorithms based on the information of the foreground to follow a person. The algorithm is verified by experiments where a person is tracked and followed by a robot in a hallway.

• Journal of Korean Neurosurgical Society
• /
• v.57 no.1
• /
• pp.58-60
• /
• 2015

A 15-year-old female patient with progressive pulsatile exophthalmos caused by intraorbital encephalocele was evaluated with computed tomography (CT) and magnetic resonance imaging (MRI) in our clinic. She had no history of trauma or reconstructive surgery. When she was a little girl, she had undergone surgery for congenital glaucoma on the right eye. On the three-dimensional image of CT, a hypoplasic bone defect was observed in the greater wing of the right sphenoid bone. MRI and CT scan showed herniation through this defect of the arachnoid membrane and protruded cerebral tissue into the right orbita. Intraorbital encephalocele is an important entity that can cause pulsatile exophthalmos and blindness.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.322-325
• /
• 1997

In this study, we propose a non-invasive method to detect the drowsiness of a driver. The computer vision technology was used to extract an eye, track eyelids and measure the parameters related to the blink. We examined the blink patterns of a driver in drowsy state. For the evaluation of our image processing algorithm, the blink patterns were compared with the measured EOG signals. The result showed that our algorithm might be available in detection of drowsiness.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.566-571
• /
• 1994

This paper presents in image-based visual servo control scheme for tracking a workpiece with a hand-eye coordinated robotic system using the fuzzy-neural-network. The goal is to control the relative position and orientation between the end-effector and a moving workpiece using a single camera mounted on the end-effector of robot manipulator. We developed a fuzzy-neural-network that consists of a network-model fuzzy system and supervised learning rules. Fuzzy-neural-network is applied to approximate the nonlinear mapping which transforms the features and theire change into the desired camera motion. In addition a control strategy for real-time relative motion control based on this approximation is presented. Computer simulation results are illustrated to show the effectiveness of the fuzzy-neural-network method for visual servoing of robot manipulator.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.50-63
• /
• 1995

In this paper, we propose a face recognition method using a neuro-fuzzy algorithm. In the preprocessing step, we extract the face part from the background image by tracking face boundaries. Then based on the a priori knowledge of human faces we extract the features such as widths of eyes and mouth, and distances from eye to nose and nose to mouth. In the recognition step. We use a neuro-fuzzy algorithm that employs a fuzzy membership function and modified error backpropagation algorithm. The former absorbs the variation of feature values and the latter shows good learning efficiency. Computer simulation results with 20 persons show that the proposed method gives higher recognition rate than the conventional ones.

• International Journal of Internet, Broadcasting and Communication
• /
• v.7 no.2
• /
• pp.51-55
• /
• 2015

This paper proposes an algorithm for risk situation recognition using facial expression. The proposed method recognitions the surprise and fear expression among human's various emotional expression for recognizing dangerous situation. The proposed method firstly extracts the facial region using Harr-like technique from input, detects eye region and lip region from the extracted face. And then, the method applies Uniform LBP to each region, detects facial expression, and recognizes dangerous situation. The proposed method is evaluated for MUCT database image and web cam input. The proposed method produces good results of facial expression and discriminates dangerous situation well and the average recognition rate is 91.05%.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.512-517
• /
• 2007

There are several researches on 2D gaze tracking techniques for the 2D screen for the Human-Computer Interaction. However, the researches for the gaze-based interaction to the stereo images or contents are not reported. The 3D display techniques are emerging now for the reality service. Moreover, the 3D interaction techniques are much more needed in the 3D contents service environments. This paper addresses gaze-based 3D interaction techniques on stereo display, such as parallax barrier or lenticular stereo display. This paper presents our researches on 3D gaze estimation and gaze-based interaction to stereo display.

• 한국HCI학회:학술대회논문집
• /
• 2007.02b
• /
• pp.633-638
• /
• 2007

본 연구에서는 신체상 위협상황에서 대처 전략을 측정할 수 있는 한국판 신체상 대처전략 척도(K-BICSI: The Korean Version of the Body Image Coping Strategy: K-BICSI)를 사용하여 회피 전략을 사용하는 정도에 따라 고회피집단(N=12)과 저 회피집단(N=12)으로 구분하여 실험참가자를 모집하였다. 연구의 목적은 외모 관련 자극이 제시 되었을 때 달라지는 주의편향과 자극 제시 전후의 정서변화를 살펴보는 것이었다. 실험 참가자는 여대생 24명으로, 안구운동 추적장비의 최초 응시방향과 응시시간을 이용해 주의편향을 확인했으며, 정서변화는 VAS로 측정하였다. 분석 결과 고 회피집단은 저 회피집단에 비해 비매력자극에 대한 더 높은 최초응시 경향을 나타냈지만, 매력자극에 대해서는 유의미하게 긴 응시시간을 보였고, 외모관련 지극 제시 전보다 후에 더 유의미하게 정서가 부정적으로 변하였다. 본 연구의 결과로 고 회피집단은 저 회피집단과는 다른 주의 인지기제를 가지고 있으며 외모관련 자극에 정서적으로 민감하게 반응한다는 것을 확인할 수 있었다.

• Journal of the Optical Society of Korea
• /
• v.20 no.4
• /
• pp.481-487
• /
• 2016

This study presents a new optical system for a combiner-type head-up display (HUD) with a cylindrical lens as an asymmetrical aberration corrector, instead of a freeform mirror. In the initial design process based on off-axial aberration analysis, we obtain an off-axis two-mirror system corrected for linear astigmatism and spherical aberration by adding a conic secondary mirror to an off-axis paraboloidal mirror. Thus, since the starting optical system for an HUD is corrected for dominant aberrations, it enables us to balance the residual asymmetrical aberrations with a simple optical surface such as a cylinder, not a complex freeform surface. From this design process, an optical system for an HUD having good performance is finally obtained. The size of the virtual image is 10 inches at 2 meters away from a combiner, and the area of the eye box is 130×50 mm².

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.83-86
• /
• 2003

This paper suggests user's interface with computer by means of detecting gaze under HMD, head mounted display, environment. System is derived as follows; firstly, calibrate a camera in HMD, which determines geometrical relationship between monitor and captured image. Second, detect the center of pupil using algorithm of the center of mass and represent a gazing position on the computer screen. If user blinks or stares at a certain position for a while, message is sent to computer. Experimental results show the center of mass is robust against glint effects, and detecting error was 7.1%. and 4.85% in vertical and horizontal direction, respectively. To adjust detailed movement of a mouse takes 0.8 sec more. The 98% of blinking is detected successfully and 94% of clicking detection is resulted.