• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.59-65
• /
• 2023

This paper proposes an Extended and Adaptive Inverse Perspective Mapping (EA-IPM) model that can obtain an accurate bird's-eye view (BEV) from the forward-looking monocular camera on the sidewalk with various curves. While Inverse Perspective Mapping (IPM) is a good way to obtain ground information, conventional methods assume a fixed relationship between the camera and the ground. Due to the nature of the driving environment of the mobile robot, there are more walking environments with frequent motion changes than flat roads, which have a fatal effect on IPM results. Therefore, we have developed an extended IPM process to be applicable in IPM on sidewalks by adding a formula for complementary Y-derive processes and roll motions to the existing adaptive IPM model that is robust to pitch motions. To convince the performance of the proposed method, we evaluated our results on both synthetic and real road and sidewalk datasets.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.180-182
• /
• 2021

본 논문은 눈 랜드마크 위치 검출과 시선 방향 벡터 추정이 하나의 딥러닝 네트워크로 통합된 시선 추정 네트워크를 제안한다. 제안하는 네트워크는 Stacked Hourglass Network[1]를 백본(Backbone) 구조로 이용하며, 크게 랜드마크 검출기, 특징 맵 추출기, 시선 방향 추정기라는 세 개의 부분으로 구성되어 있다. 랜드마크 검출기에서는 눈 랜드마크 50개 포인트의 좌표를 추정하며, 특징 맵 추출기에서는 시선 방향 추정을 위한 눈 이미지의 특징 맵을 생성한다. 그리고 시선 방향 추정기에서는 각 출력 결과를 조합하고 이를 통해 최종 시선 방향 벡터를 추정한다. 제안하는 네트워크는 UnityEyes[2] 데이터셋을 통해 생성된 가상의 합성 눈 이미지와 랜드마크 좌표 데이터를 이용하여 학습하였으며, 성능 평가는 실제 사람의 눈 이미지로 구성된 MPIIGaze[3] 데이터 셋을 이용하였다. 실험을 통해 시선 추정 오차는 0.0396 MSE(Mean Square Error)의 성능을 보였으며, 네트워크의 추정 속도는 42 FPS(Frame Per Second)를 나타내었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.6
• /
• pp.2078-2087
• /
• 2010

This study conducted a chi-square test and a logistic regression analysis by not only using a investigation data of discharged patients with damages from 2004 to 2006, but also using a census and a research data on the actual condition from health care system. The result follows; First, the centralization of medical utilization of operation patients is becoming apparent, centrally the capital area. To improve this, a policy that can not only provide medical centers and sickbed, but also improve the quality of local medical treatments for the localization of medical treatments. Second, propelling localization policy of certain diseases for the localization of medical utilization is needed as the rate of non-residential of operation patients that have diseases of the eye and adnexa, or cancers is high. Third, a localization policy for patients with damages is needed as the rate of treatments in other regions of operation patients with industrial accidents is increasing day by day.

• Progress in Medical Physics
• /
• v.3 no.1
• /
• pp.63-69
• /
• 1992

Recently, stereotactic radiosurgery plan is required with the information of 3-D image and dose distribution. The purpose of this research is to develop 3-D radiosurgery planning system using personal computer. The procedure of this research is based on three steps. The first step is to input the image information of the patient obtained from CT or MR scan into personal computer through on-line or digitizer. The position and shape of target are also transferred into computer using Angio or CT localization. The second step is to compute dose distribution on image plane, which is transformed into stereotactic frame coordinate. and to optimize dose distribution through the selection of optimal treatment parameters. The third step is to display both isodose distribution and patient image simultaneously using superimpose technique. This prototype of radiosurgery planning system was applied recently for several clinical cases. It was shown that our planning system is fast, accurate and efficient while making it possible to handle various kinds of image modelities such as angio, CT and MRI. It is also possible to develop 3-D planning system in radiation therapy using beam's eye view or CT simulation in future.

• Korean Journal of Cognitive Science
• /
• v.18 no.3
• /
• pp.223-244
• /
• 2007

Two well known mis-localization effects, flash-lag effect (FLE) and the Pulfrich effect, have similar phenomena and theoretical explanations. In order to directly compare two phenomena, thereby examining the possibility that two phenomena have a common mechanism, the magnitudes of two effects were measured under the same experimental settings and stimuli. The Pulfrich depth was measured from each of four different brightness ratios of two moving stimuli, each of which was projected to each eye. The magnitude of FLE was measured from each of five different brightness levels, which were the same levels used in the Pulfrich experiment. The Pulfrich depth was increased with the increase of brightness ratio, whereas similar pattern was not found in the magnitude of FLE. Furthermore, actual Pulfrich depths were greatly different from those predicted from the difference of two FLEs. These results suggest that two phenomena may not have a common mechanism.

• Radiation Oncology Journal
• /
• v.11 no.1
• /
• pp.167-174
• /
• 1993

Recently, stereotactic radiosurgery plan is required with the information of 3-D image and dose distribution. A project has been doing if developing LINAC based stereotactic radiosurgery since April 1991. The purpose of this research is to develop 3-D radiosurgery planning system using personal computer. The procedure of this research is based on two steps. The first step is to develop 3-D localization system, which input the image information of the patient, coordinate transformation, the position and shape of target, and patient contour into computer system using CT image and stereotactic frame. The second step is to develop 3-D dose planning system, which compute dose distribution on image plane, display on high resolution monitor both isodose distribution and patient image simultaneously and develop menu-driven planning system. This prototype of radiosurgery planning system was applied recently for several clinical cases. It was shown that our planning system is fast, accurate and efficient while making it possible to handle various kinds of image modalities such as angiography, CT and MRI. It makes it possible to develop general 3-D planning system using beam's eye view or CT simulation in radiation therapy in future.

• Journal of Korea Multimedia Society
• /
• v.8 no.11
• /
• pp.1421-1431
• /
• 2005

There are two methods in 3-D sound reproduction: a surround system, like 3.1 channel method and a binaural system using 2-channel method. The binaural system utilizes the sound localization principle of a human using two ears. Generally, a crosstalk between each channel of 2-channel loudspeaker system should be canceled to produce a natural 3-D sound. To solve this problem, it is necessary to trace a head movement. In this paper, we propose a new algorithm to correctly trace the head movement of a listener. The Proposed algorithm is based on the detection of face and eye. The face detection uses the intensity of an image and the position of eyes is detected by a mathematical morphology. When the head of the listener moves, length of borderline between face area and eyes may change. We use this information to the tracking of head movement. A computer simulation results show That head movement is effectively estimated within +10 margin of error using the proposed algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.3
• /
• pp.210-216
• /
• 2016

This paper presents a novel collision avoidance technique for mobile robots based on omni-directional vision simultaneous localization and mapping (SLAM). This method estimates the avoidance path and speed of a robot from the location of an obstacle, which can be detected using the Lucas-Kanade Optical Flow in images obtained through fish-eye cameras mounted on the robots. The conventional methods suggest avoidance paths by constructing an arbitrary force field around the obstacle found in the complete map obtained through the SLAM. Robots can also avoid obstacles by using the speed command based on the robot modeling and curved movement path of the robot. The recent research has been improved by optimizing the algorithm for the actual robot. However, research related to a robot using omni-directional vision SLAM to acquire around information at once has been comparatively less studied. The robot with the proposed algorithm avoids obstacles according to the estimated avoidance path based on the map obtained through an omni-directional vision SLAM using a fisheye image, and returns to the original path. In particular, it avoids the obstacles with various speed and direction using acceleration components based on motion information obtained by analyzing around the obstacles. The experimental results confirm the reliability of an avoidance algorithm through comparison between position obtained by the proposed algorithm and the real position collected while avoiding the obstacles.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.442-450
• /
• 2002

In measuring EEG, which is widely used for studying brain function, EEG is frequently mixed with noise and artifact. In this study, the signals relevant to the artifact were distracted by applying ICA to EEG signal. First, each independent component which was assumed to be the source was separated by applying ICA to EEG which involved artifact relevant to the eye movement of a normal person. Next, the signal which was assumed to be artifact was removed from the separated 18 independent components, and the nonlinear analysis method such as correlation dimension and the Iyapunov exponent was applied to each reconstructed EEG signal and the original signal including artifact in order to find meaningful difference between the two signals and infer the anatomical localization of its source and distribution. This study shows it is possible not only to analyze the brain function visually and spatially for visually complex EEG signal, but also to observe its meaningful change through the quantitative analysis of EEG by means of the nonlinear analysis.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2111-2112
• /
• 2006

얼굴 영상에서 사람의 눈을 검출하는 것은 얼굴 인식의 전체적인 성능을 좌우하는 매우 중요한 사항이다. 눈 검출은 얼굴 영상의 특징이 변하기 때문에 항상 신뢰할 수 있는 결과를 얻는 것은 어려우며, 또한 실시간 얼굴 인식에 응용되기 위해서는 빠른 연산 시간도 고려되어야 한다. 본 논문에서는 빠르고 정확한 새로운 눈 검출 방법을 제안하다. 첫째, Ada-Boosting 알고리즘을 사용하여 얼굴 영역을 검출한다. 둘째, Intensity valley와 edge 정보를 사용하여 얼굴 영상의 회전(Rotation in plane)을 보상한다. 셋째, Intensity edge정보를 사용하여 두 눈의 수직, 수평라인을 검출한다. 넷째, 일반적인 (generic) 사람 눈의 패턴을 이용하여 고안된 Filter로 두 눈의 위치를 검출한다. 본 논문을 통하여 새로 제안된 알고리즘에 대한 논의와 실험 결과를 통해 새로운 알고리즘이 눈 검출에 적합함을 제시한다.