http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김지훈,이대식,이민호,Kim, Jihun,Lee, Daesik,Lee, Minho 대한임베디드공학회 2016 대한임베디드공학회논문지 Vol.11 No.3
Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC
4차산업혁명기반 건설자동화를 통한 초고층 건축물 유지관리 로봇시스템 개발
김지훈 ( Kim Jihun ),우미소 ( Woo Miso ),이동운 ( Lee Dongoun ) 한국건축시공학회 2020 한국건축시공학회 학술발표대회 논문집 Vol.20 No.1
Domestic and foreign high-rise buildings are expected to continue to increase in the future. In addition, recently, residents and landlords are demanding maintenance necessary to secure the performance of sustainable buildings, so an effective management plan is needed. Therefore, this study aims to develop customized technologies that can be effectively applied to building structures by comprehensively analyzing existing technology-based research cases. As a result, it is expected that this will serve as a stepping stone to present a s+ample of future technology development along with a reduction in labor dependency on maintenance and quality improvement.
김지훈(Kim Jihun) 대한의학유전학회 2014 대한의학유전학회 학술대회 논문집 Vol.1 No.1
태아 염색체이상의 산전선별검사(prenatal screening)는 침습적 검사와 비침습적 검사가 사용된다. 침습적 검사로는 양수천자(Amniocentesis), 융모막 융모 검사(Chorionic Villus Sampling) 등이 있고 높은 정확성으로 확진검사로 사용되나, 태아손실(1-2%) 위험성이 있다.
피스톤 경량화에 따른 가솔린 가관에서의 성능 및 배출가스 특성에 관한 연구
김지훈(Jihun Kim),이성욱(Seangwock Lee),조용석(Yongseok Cho),임규철(Kyuchul Lim),유연설(Younsul Yoo) 한국자동차공학회 2010 한국자동차공학회 부문종합 학술대회 Vol.2010 No.5
Heavy air pollution is an increasing concern as well as global warming, which requires strict reduction of GHG(greenhouse gas) emission. CO₂ is a main contribution to global warming, responsible for over 90 percent of total GHG emission. The amount of CO₂ is closely related to fuel consumption rate. So, CO₂ emission can be reduced by improving fuel consumption rate of the vehicle. In this research, commercially manufactured gasoline engine was equipped with light weight piston, torque and power of the engine were tested and compared with reference engine. Also, in order to deprive the results, emission analyzer was used to measure emission level and flowmeter was equipped to calculate the fuel consumption rate characteristic. Thus, this research may provide the fundamental data for making strategies of emission level reduction through piston weight lightening.