http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
송현철,이균혁,심덕선,최광남 제어·로봇·시스템학회 2018 International Journal of Control, Automation, and Vol.16 No.2
Intelligent Systems for autonomous vehicles including drone, robot vision, and video surveillance, need to distinguish pedestrian from other object. Pedestrian detection is an essential and significant research topic due to its diverse applications. In this paper, a new visual distinctiveness detection method for pedestrian is proposed based on the statistically weighting probabilistic latent semantic analysis. We detect the distinctiveness by integrating three steps as follows: first representing the co-ocurrence matrix of images, which were vectorized using the bag of visual words (BoVW) framework; then calculating the weights through the histograms of visual words of each class; and finally applying the weights to the test images as the distinctiveness of visual words. The probabilistic latent semantic analysis (PLSA) was used as classification method in our system. We extracted the weighted visual words by sampling the patches from the current image. The proposed method was compared to the PLSA using the Caltech 256 datasets. The classes used include pedestrians, cars, motorbikes, airplanes and horses. The results of the experiment show that the proposed method outperforms current methods in predicting pedestrians and transportation objects.
Febry-Perot 간섭계를 이용한 강유전 P(VDF-TrFE) 폴리머 열광학 특성평가
송현철,김진상,윤석진,정대용,Song, Hyun-Cheol,Kim, Jin-Sang,Yoon, Seok-Jin,Jeong, Dae-Yong 한국재료학회 2009 한국재료학회지 Vol.19 No.4
Phase transition in ferroelectric polymer is very interesting behavior and has been widely studied for real device applications, such as actuators and sensors. Through the phase transition, there is structural change resulting in the change of electrical and optical properties. In this study, we fabricated the Febry-Perot interferometer with the thin film of ferroelectric P(VDF-TrFE) 50/50 mol% copolymer, and thermo-optical properties were investigated. The effective thermo-optical coefficient of P(VDF-TrFE) was obtained as $2.3{\sim}3.8{\times}10^{-4}/K$ in the ferroelectric temperature region ($45^{\circ}C{\sim}65^{\circ}C$) and $6.0{\times}10^{-4}/K$ in the phase transition temperature region ($65^{\circ}C{\sim}85^{\circ}C$), which is a larger than optical silica-fiber and PMMA. The resonance transmission peak of P(VDF-TrFE) with the variation of temperature showed hysteretic variation and the phase transition temperature of the polymer in heating condition was higher than in the cooling condition. The elimination of the hysteretic phase transition of P(VDF-TrFE) is necessary for practical applications of optical devices.
적외선 카메라 영상에서의 마스크 R-CNN기반 발열객체검출
송현철,강민식,김태은 한국디지털콘텐츠학회 2018 한국디지털콘텐츠학회논문지 Vol.19 No.6
최근 비전분야에 소개된 Mask R-CNN은 객체 인스턴스 세분화를위한 개념적으로 간단하고 유연하며 일반적인 프레임 워크를 제시한다. 이 논문에서는 열적외선 카메라로부터 획득한 열감지영상에서 발열체인 인스턴스에 대해 발열부위의 세그멘테이션 마스크를 생성하는 동시에 이미지 내의 오브젝트 발열부분을 효율적으로 탐색하는 알고리즘을 제안한다. Mask R-CNN 기법은 바운딩 박스 인식을 위해 기존 브랜치와 병렬로 객체 마스크를 예측하기 위한 브랜치를 추가함으로써 Faster R-CNN을 확장한 알고리즘이다. Mask R-CNN은 훈련이 간단하고 빠르게 실행하는 고속 R-CNN에 추가된다. 더욱이, Mask R-CNN은 다른 작업으로 일반화하기 용이하다. 본 연구에서는 이 R-CNN기반 적외선 영상 검출알고리즘을 제안하여 RGB영상에서 구별할 수 없는 발열체를 탐지하였다. 실험결과 Mask R-CNN에서 변별하지 못하는 발열객체를 성공적으로 검출하였다. Recently introduced Mask R - CNN presents a conceptually simple, flexible, general framework for instance segmentation of objects. In this paper, we propose an algorithm for efficiently searching objects of images, while creating a segmentation mask of heat generation part for an instance which is a heating element in a heat sensed image acquired from a thermal infrared camera. This method called a mask R - CNN is an algorithm that extends Faster R - CNN by adding a branch for predicting an object mask in parallel with an existing branch for recognition of a bounding box. The mask R - CNN is added to the high - speed R - CNN which training is easy and fast to execute. Also, it is easy to generalize the mask R - CNN to other tasks. In this research, we propose an infrared image detection algorithm based on R - CNN and detect heating elements which can not be distinguished by RGB images. As a result of the experiment, a heat-generating object which can not be discriminated from Mask R-CNN was detected normally.
송현철,박기택 국민대학교 2003 기초과학연구소 논문집 Vol.22 No.-
국소밀도 근사를 이용한 범밀도 함수법을 기초로 한 Full Potential Linear Augmented Plane Wave(FLAPW) 방법을 이용하여 spinel 구조를 갖는 MnFe₂O₄, CoFe₂O₄, FeCr₂O₄의 전자구조 및 자기적 성질을 연구하였다. 그리고 LDA+U 방법을 사용하여 LDA 방법과의 비교를 수행하였다. 계산 결과 MnFe₂O₄에서 Fe 원자는 high spin 상태를 보여 주지 않았다. 이러한 문제는 LDA 계산에서, 특히 철산화물에서 Fe 원자와 O 원자 사이의 결합이 너무 강해 일어 나는 것으로 보여진다. 이러한 문제점을 해결하기 위해 강상관 관계를 가진 철 산화물에서의 개선된 방법이 요구되고 있다. CoFe₂O₄는 정스피넬 구조로 계산을 한 결과 LDA 방법에서는 4.2μ_B, LDA+U 방법에서는 7μ_B의 자기 모멘트를 가졌다. FeCr₂O₄는 절연체 성질을 보이는데 LDA계산을 통한 결과는 금속 성질을 보였다. 이것은 얀-텔러 변환을 고려한 계산을 통하여 절연체의 성질을 설명할 수 있으며, 또 다른 원인으로는 불충분한 전자상관관계를 LDA+U 계산을 통하여 절연체적 성질을 얻어낼 수 있었다. We have studied electronic structures and magnetic properties of MnFe₂O₄, CoFe₂O₄, FeCr₂O₄with spinel structure using Full Potential Linearized Augmented Plane Wave(FLAPW) method based on LDA and LDA+U method. LDA and LDA+U calculation results show that Fe atom does not show high spin state in MnFe₂O₄. It seems to be strong hybridization between Fe and 0 atoms in LDA and LDA+U calculation. It needs improved method in iron oxides with strong correlation. CoFe₂O₄is known to have a inverse spinel structures. The results of calculation with normal spinel structure shows magnetic moment of 4.2μa in LDA, 7μa in LDA+U method. FeCr₂O₄ is insulator, but the LDA calculation result shows the metallic nature. It could be explained by Jahn-Teller effect. However the other factor of insulating nature comes from the Coulomb interaction between electrons. The calculation result of LDA+U shows the insulating gab and orbital ordering of 3y^2-r^2d orbital character.