• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1165-1166
• /
• 2023

본 논문에서는 YOLOPv2 를 기반으로 OpenCV 를 활용한 후처리 과정을 도입하여 차선 검출 성능을 극대화할 수 있는 알고리즘을 제안한다. 주요 단계로는 YOLOPv2 모델을 활용한 차선 인식, Bird's eye view 변환, Sobel 및 Morphology Filter 를 통한 왜곡 보정, Histogram 기반 차선 검출, 그리고 후처리 알고리즘 적용이 있다. 이 기술은 자율 주행 및 도로 정보 활용 분야에 활용 가능할 것으로 기대되며, 차선 검출 정확도를 향상시킬 수 있다.

• Journal of Korean Society of Archives and Records Management
• /
• v.12 no.3
• /
• pp.29-46
• /
• 2012

Electronic records are merely series of bits without understanding the formats of content files. There are numerous types of formats and also possibilities of extinction. For long term preservation, it is essential to understand and manage formats. In addition to managing format itself, accurate information on the format needs to be stored for electronic records. In this study, various types of electronic files, without checking with the naked eye, has developed a tool to extract the header information in the format of electronic files with the file extension validation tool to compare format and validate digital component.

• Journal of the Korean Society of Safety
• /
• v.24 no.4
• /
• pp.104-110
• /
• 2009

In this driving simulation study, the impairing effects of various types of electronic devices usage(i. e., destination search by using in-vehicle navigation system, TV watching and dialing cellular phone) during driving on front-to-rear-end collision avoidance were investigated. Percentage of collisions, driving speeds when the drivers collided, and initial reaction time for collision avoidance were analyzed and compared as the dependent measures. The results indicated that (1) any types of electronic devices usage during driving induced more serious collision-related impairment than control condition where no additional task was required, and (2) in general, destination search task appeared to impair drivers collision avoidance performance more than the other task requirements in terms of percentage of collisions and initial reaction time for collision avoidance, but TV watching induced most serious collision impact. These results suggested that any types of electronic device usage could distract drivers attention from the primary task of driving, and be resulted in serious outcome in potentially risky situation of front-to-rear-end collision. In particular, mandatory use of eye-hand coordination and receiving feedback seemed to one of essential factor leading the drivers visual attentional distraction.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2036-2038
• /
• 2001

In this paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using vision system. In the proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Also, we use R,G,B(red, green, blue) color image data and the gray image data to get the highly trust rate of feature point extraction. For this, we propose an algorithm to extract four feature points (eyebrow, eye, nose, mouth) from the face image acquired by the color CCD camera and find some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector(position and distance among the feature points). Finally, we show the practical application possibility of the proposed method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.307-313
• /
• 2012

This paper proposes a hand-eye laser range finder (LRF) based welding plane recognition method for autonomous robotic welding. The robot welding is the process of joining a metal piece and the welding plane along the welding path predefined by the shape of the metal piece. Thus, for successful robotic welding, the position and direction of the welding plane should be exactly detected. If the detected position and direction of the plane is not accurate, the autonomous robotic welding should fail. For precise recognition of the welding plane, a line on the plane is detected by the LRF. For obtaining the line on the plane, the Hough transform is applied to the obtained data from the LRF. Since the Hough transform is based on the voting method, the sensor noise can be reduced. Two lines on the plane are obtained before and after rotation of the robot joint, and then the direction of the plane is calculated by the cross product of two direction vectors of two lines. For verifying the feasibility of the proposed method, the simulation with the robot simulator, RoboticsLab developed by Simlab Co. Ltd., is carried out.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.98-101
• /
• 2003

To classify desired and undesired documents on the web according to each user's view, FOCUS (Fuzzy dOCUment ordering System) is developed based on fuzzy concept extraction, fuzzy fish eye matching, and fuzzy selection. Experiments are done using the concept-system-dictionary by EDR (Electronic Dictionary Research Institute) including 140,000 words and web-based documents related to movie.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2865-2867
• /
• 2000

In machine vision fields around FA, there have been demands for functions to capture high speed moving objects as blur-free images. By electronic shutters, progressive scan cameras can do it. This paper develops a module to connect a progressive scan camera, XC-55.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.02a
• /
• pp.29-29
• /
• 2010

기존의 반도체 공정을 기반으로 하는 소자구조는 주로 평면의 웨이퍼상에 만들어져왔다. 그러나, 제작된 소자 어레이를 늘림이 가능한 (stretchable) 폴리머 기판에 프린팅 전이하는 방식을 이용하면 어떤 형태의 곡면에도 소자 제작이 가능해진다. 이러한 프린팅 방식으로, 다양한 곡면에 실리콘 소자 어레이를 제작한 연구결과를 발표하고자 한다. 한 응용 예로 사람의 눈과 같은 반구형 표면에 실리콘 나노 리본으로 만든 광다이오드 어레이를 배열하여 전자 눈 카메라를 제작하여 성능을 확인하였다. 또한 수차를 최소화할 수 있는 포물면에 전자눈 카메라를 제작하여 평면카메라에 비해 이미지의 균일성이 우수함을 보여주고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.145-148
• /
• 2010

본 논문에서는 3차원 스테레오 영상에서의 시각적 피로도와 안구의 운동량과의 상관관계를 도출하고 시각적 피로도 측정 시스템을 제안한다. 제안한 측정 방법은 3차원 스테레오 영상 시청자의 피로도가 누적되었을 때, 안구의 단속성 운동(saccade)이 감소할 것이라는 가정에 기반을 둔다. 액티브 셔터글라스 방식의 3D 안경을 착용한 시청자의 동공을 검출하고 추적하기 위해 적외선 광원 및 적외선 카메라를 이용한다. 획득한 영상에 대해 이진 임계화를 적용하고 타원 피팅을 수행하여 동공의 위치를 검출한다. 피팅된 타원의 이심률과 크기 및 위치를 제한하여 검출 오류를 줄인다. 검출된 동공의 위치를 바탕으로 안구의 단속성 운동량을 측정한다. 실험에는 변이 정도가 크지 않아 편안하게 시청 가능한 스테레오 영상과 과도한 변이를 가져 시청하는데 불편한 영상이 분리되어 사용되었다. 이들 영상에 대해 각각 실험자의 단속성 운동량을 측정하였다. 실험 결과에서 안구의 단속성 운동량이 변이가 큰 영상에서 그렇지 않은 영상에 비해 감소하는 경향이 나타났다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.696-699
• /
• 2018

This paper introduces a system that enables pupillary tracing and communication with patients with amyotrophic lateral sclerosis (ALS) who can not move free. Face and pupil are tracked using OpenCV, and eye movements are detected using DE1-SoC board. We use the webcam, track the pupil, identify the pupil's movement according to the pupil coordinate value, and select the character according to the user's intention. We propose a system that can use relatively low development cost and FPGA can be reusable, and can select a text easily to mobile phone by using Bluetooth.