• 한국측량학회지
• /
• 제38권6호
• /
• pp.635-644
• /
• 2020

딥러닝(DL)을 이용한 객체인식, 탐지 및 분할하는 연구는 여러 분야에서 활용되고 있으며, 주로 영상을 DL 모델의 학습 데이터로 사용하고 있지만, 본 논문은 영상뿐 아니라 공간정보 특성을 포함하는 다양한 학습 데이터(multimodal training data)를 향상된 영역기반 합성곱 신경망(R-CNN)인 Detectron2 모델 학습에 사용하여 객체를 분할하고 건물을 탐지하는 것이 목적이다. 이를 위하여 적외선 항공영상과 라이다 데이터의 내재된 객체의 윤곽 및 통계적 질감정보인 Haralick feature와 같은 여러 특성을 추출하였다. DL 모델의 학습 성능은 데이터의 수량과 특성뿐 아니라 융합방법에 의해 좌우된다. 초기융합(early fusion)과 후기융합(late fusion)의 혼용방식인 하이브리드 융합(hybrid fusion)을 적용한 결과 33%의 건물을 추가적으로 탐지 할 수 있다. 이와 같은 실험 결과는 서로 다른 특성 데이터의 복합적 학습과 융합에 의한 상호보완적 효과를 입증하였다고 판단된다.

• Fibers and Polymers
• /
• 제6권3호
• /
• pp.186-199
• /
• 2005

A selection of commercially available poly(ethy1ene terephtha1ate) fibers with different degrees of molecular alignment and crystallinity have been investigated utilizing a wide range of techniques including optical microscopy, infrared spectroscopy together with thermal and wide-angle X-ray diffraction techniques. Annealing experiments showed increased molecular alignment and crystallinity as shown by the increased values of birefringence and melting enthalpies. Crystallinity values determined from thermal analysis, density, unpolarized infrared spectroscopy and X-ray diffraction are compared and discussed in terms of the inherent capabilities and limitations of each measurement technique. The birefringence and refractive index values obtained from optical microscopy are found to decrease with increasing wavelength of light used in the experiments. The wide-angle X-ray diffraction analysis shows that the samples with relatively low orientation possess oriented non-crystalline array of chains whereas those with high molecular orientation possess well defined and oriented crystalline array of chains along the fiber axis direction. X-ray analysis showed increasing crystallite size trend with increasing molecular orientation. SEM images showed micro-cracks on low oriented fiber surfaces becoming smooth on highly oriented fiber surfaces. Excellent bending characteristics were observed with knotted fibers implying relatively easy fabric formation.

• 한국전자통신학회논문지
• /
• 제19권1호
• /
• pp.327-334
• /
• 2024

본 논문에서는 라즈베리파이 기반으로 손바닥 정맥혈관 이미지를 획득하기 위하여 950nm파장을 가지는 근적외선 LED 광원 장치와 손금을 획득하기 위한 백색 LED 광원 장치를 가지는 시스템을 개발하였다. 또한 획득한 정맥 및 손금 이미지에 대하여 영상 전처리 과정(흑백화, 평활화, 이진화, 블러링, 세선화 등)을 통하여 정맥과 손금이 혼합된 위조 방지 및 보안이 강화된 고유 패턴이 추출 가능한 영상처리 기술을 구현하여 보안성이 강화된 시스템에서 활용할 수 있는 원천 기술을 확보하였다.

• 한국멀티미디어학회논문지
• /
• 제22권8호
• /
• pp.844-851
• /
• 2019

In this paper, we propose a loss function in CNN that introduces inter-class amplitudes to increase inter-class loss and reduce intra-class loss to increase of face recognition performance. This loss function increases the distance between the classes and decreases the distance in the class, thereby improving the performance of the face recognition finally. It is confirmed that the accuracy of face recognition for visible light image of proposed loss function is 99.62%, which is better than other loss functions. We also applied it to face recognition of visible and near-infrared complex images to obtain satisfactory results of 99.76%.

• 대한의용생체공학회:의공학회지
• /
• 제27권5호
• /
• pp.250-259
• /
• 2006

The information of eye movement is used in various fields such as psychology, ophthalmology, physiology, rehabilitation medicine, web design, HMI(human-machine interface), and so on. Various devices to detect the eye movement have been developed but they are too expensive. The general methods of eye movement tracking are EOG(electro-oculograph), Purkinje image tracker, scleral search coil technique, and video-oculograph(VOG). The purpose of this study is to embody the algorithm which tracks the location of the gazing point at a pupil. Two kinds of location data were compared to track the gazing point. One is the reference points(infrared LEDs) which is effected from the globe. Another is the center point of the pupil which is gained with a CCD camera. The reference point was captured with the CCD camera and infrared lights which were not recognized by human eyes. Both of images which were thrown and were not thrown an infrared light on the globe were captured and saved. The reflected reference points were detected with the brightness difference between the two saved images. In conclusion, the circumcenter theory of a triangle was used to look for the center of the pupil. The location of the gazing point was relatively indicated with the each center of the pupil and the reference point.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권2호
• /
• pp.149-154
• /
• 2015

Biometric techniques for authentication using body parts such as a fingerprint, face, iris, voice, finger-vein and also photoplethysmography have become increasingly important in the personal security field, including door access control, finance security, electronic passport, and mobile device. Finger-vein images are now used to human identification, however, difficulties in recognizing finger-vein images are caused by capturing under various conditions, such as different temperatures and illumination, and noise in the acquisition camera. The human photoplethysmography is also important signal for human identification. In this paper To increase the recognition rate, we develop camera based identification method by combining finger vein image and photoplethysmography signal. We use a compact CMOS camera with a penetrating infrared LED light source to acquire images of finger vein and photoplethysmography signal. In addition, we suggest a simple pattern matching method to reduce the calculation time for embedded environments. The experimental results show that our simple system has good results in terms of speed and accuracy for personal identification compared to the result of only finger vein images.

• 천문학회보
• /
• 제40권1호
• /
• pp.61.3-62
• /
• 2015

Remote-sensing observation is one of the observation methods that provide valuable information, such as composition and surface physical conditions of solar system objects. The Hayabusa spacecraft succeeded in the first sample returning from a near-Earth asteroid, (25143) Itokawa. It has established a ground truth technique to connect between ordinary chondrite meteorites and S-type asteroids. One of the scientific observation instruments that Hayabusa carried, Asteroid Multi-band Imaging Camera(AMICA) has seven optical-near infrared filters (ul, b, v, w, x, p, and zs), taking more than 1400 images of Itokawa during the rendezvous phase. The reflectance of planetary body can provide valuable information of the surface properties, such as the optical aspect of asteroid surface at near zero phase angle (i.e. Sun-asteroid-observer's angle is nearly zero), light scattering on the surface, and surface roughness. However, only little information of the phase angle dependences of the reflectance of the asteroid is known so far. In this study, we investigated the phase angle dependences of Itokawa's surface to understand the surface properties in the solar phase angle of $0^{\circ}-40^{\circ}$ using AMICA images. About 700 images at the Hayabusa rendezvous phase were used for this study. In addition, we compared our result with those of several photometry models, Minnaert model, Lommel-Seeliger model, and Hapke model. At this conference, we focus on the AMICA's v-band data to compare with previous ground-based observation researches.

• 한국환경과학회지
• /
• 제26권4호
• /
• pp.543-547
• /
• 2017

Normalized Difference Vegetation Index (NDVI) has played an important role in assessing green plant biomass through remote sensing on global scale since the early 1970s. The concept of NDVI is based on the fact that green plants show higher reflection in near-infrared region than in visible region of the electromagnetic spectrum. However, it is well known that the relocation of chloroplasts in plant leaf cells may dramatically change the optical properties of plant leaves. In this study I traced the changes in the reflectance and transmittance properties of Tobacco leaves at the wavelengths of 660 and 800 nm after a sudden increase in light intensity. The results showed that NDVI of leaves gradually decreased from 72.7% to 69.9% when exposed to a sudden increase in light intensity from 30 to $1,200{\mu}mol/m^2{\cdot}s$. This means that the error resulting from the physiological status of the plant should be accounted for a more precise understanding of ground truth corresponding to the data from the remotely acquired images.

• 한국해양공학회지
• /
• 제26권5호
• /
• pp.25-30
• /
• 2012

This study examined the use of LIT (lock-in infrared thermography) to detect defects in the welded parts of ships and offshore structures. A quantitative analysis was used with the filtering and texture measurement of image processing techniques to find the optimized experimental condition. We verified the reliability of our methods by applying image processing techniques in order to normalize the evaluations of comparative images that showed a phase difference. In addition, it was found that a low to mid-range intensity of light exposure on the surface showed good results, whereas high exposure did not provide significant results. A lock-in frequency of around 0.1 Hz was satisfactory regardless of the intensity of the light source. In addition, making the integration time of the thermography camera inversely proportional to the intensity of the exposed light source during the experiment provided good results.

• 한국멀티미디어학회논문지
• /
• 제14권9호
• /
• pp.1125-1137
• /
• 2011

최근, 휴대성과 이동성이 뛰어난 모바일 단말기 환경에 홍채 인식 기술을 도입하여 신원을 확인하는 연구가 진행 되었는데, 이러한 모바일 홍채 인식 시스템은 취득된 홍채 영상 품질에 따라 인식률이 좌우된다. 홍채 영상은 취득 시 조명환경에 영향을 많이 받게 되는데, 기존의 시스템은 태양광이 없는 실내에서는 높은 인식률을 보이나, 실외 태양광 환경에서는 외부태양광이 홍채 영역에 투사되어 입력 영상 내에서 홍채 패턴의 그레이 레벨 변화, 고스트(Ghost region) 및 속눈썹 그림자(Eyelash shading region) 발생 등의 요인으로 인식 성능 저하를 초래하는 문제가 있었다. 이를 해결하기 위하여, 본 연구에서는 850nm 근적외선 조명과 850nm 대역 밴드 패스 필터를 장착한 홍채 카메라 시스템을 제안한다. 성능 평가를 위해 기존의 홍채 인식시스템과 제안하는 홍채 인식 시스템을 사용하여 실내 및 실외 태양광 환경에서 취득한 홍채 영상으로부터 홍채코드를 추출한 후 타인 수락률(False Acceptance Rate), 본인 거부율 (False Rejection Rate)을 통한 균등 에러율(EER, Equal Error Rate)을 측정하였다. 실험 결과 기존의 시스템 보다 제안하는 시스템의 EER이 실내 정면 조명일 때 약 0.96%, 실외 정면 조명일 때 약 4.94%, 실외 측면 조명일 때 약 9.24%, 실외 후면 조명일 때 약 7% 낮아지는 개선된 성능을 보였다.