• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.224-241
• /
• 2015

Multiview plus depth (MVD) videos are widely used in free-viewpoint TV systems. The best-known technique to determine depth information is based on stereo vision. In this paper, we propose a novel local stereo matching algorithm which is radiometric invariant. The key idea is to use a combined matching cost of intensity and gradient based similarity measure. In addition, we realize an adaptive cost aggregation scheme by constructing an adaptive support window for each pixel, which can solve the boundary and low texture problems. In the disparity refinement process, we propose a four-step post-processing technique to handle outliers and occlusions. Moreover, we conduct stereo reconstruction tests to verify the performance of the algorithm more intuitively. Experimental results show that the proposed method is effective and robust against local radiometric distortion. It has an average error of 5.93% on the Middlebury benchmark and is compatible to the state-of-art local methods.

• 한국조경학회지
• /
• 제20권3호
• /
• pp.33-43
• /
• 1992

The perceptual characteristic on the slope scenery around highway is very similar as the general perceptual characteristic in the landscape. This process determines by the relationship between the scenery observers and the characteristics of its place. It is very important to have a analysis on highway slope scenery in our particular culture in Korea since our country's highways are done by cutting mountains : therefore, we have a lot of slopes around highways. The physical characteristics on the highway scenery determines how we should build scenery around highway to a satisfactory level. The results drawn from this research work are as follow: 1) The satisfaction for slope scene had been affected by sex, native and experience of travel. I thought that the slope scene having peculiar form will offer the highest satisfaction. 2) Psychological factor, reflected satisfaction of slope scene, 몽 a grip of three factors as the factor of evaluation, texture, formation, and presumption formula is : Satisfaction=1.04(Evauluation factor)+0.83(Texture factor)+0.15(Formation factor)+4.28)R2=0.69). 3) Vine among the vegetation componeents of slope scene highly correlated with the evaluation factor and grass, shrub correlated with the texture factor. 4) Rock among the structual components of slope scene highly correlated with the formation factor, and stockade, lattice correlated with the evalution factor. 5) Gradient among the properties which determined slope form, highly correlated with the formation factor.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.485-488
• /
• 2005

Most metals are polycrystalline material whose deformation is dominated by the slip system. During the deformation process, orientation of slip systems is rearranged with preferred orientations, leading to deformation-induced crystallographic texture which is called deformation texture. Depending on the texture development, the property of material can be changed. The rate-independent crystal plasticity which is based on the Schmid law as a yield function causes a non-uniqueness in the choice of active slip systems. In this work, to avoid the slip system ambiguity problem, rate-independent crystal plasticity model based on the smooth yield surface with rounded-off corners is adopted. In order to simulate the polycrystalline material under plastic deformation, we employ the Taylor model of polycrystal behavior that all the grains are assumed to be subjected to the macroscopic velocity gradient. Rigid-plastic finite element program based on this rate-independent crystal plasticity is developed to predict the grain-level deformation behavior of FCC metals during metal forming processes. In the finite element calculation, one integration point is considered as a crystalline aggregate which has a number of crystals. Macroscopic behavior of material can be deduced from the behavior of aggregates. As applications, the extrusion processes are simulated and the changes of mechanical properties are predicted.

• 인지과학
• /
• 제17권4호
• /
• pp.287-301
• /
• 2006

깊이정보가 이차원 자극의 형태 판단에 미치는 효과를 알아보기 위하여 Posner 등(1969)의 물리적 대응과제를 이용한 두 실험을 실시하였다. 두 실험 모두 연속적으로 제시되는 두 문자나 도형이 물리적으로 동일한 형태인지 여부를 신속 정확하게 판단하는데 있어서 배경의 깊이정보가 미치는 영향에 초점을 맞추었다. 실험 1에서는 인공적으로 구성한 선형조망 단서와 결기울기 단서를, 실험 2에서는 실제 장면인 도로를 이용한 단서들을 사용하였다. 두 실험의 결과는 모두 깊이단서가 제공하는 깊이정보가 이차원 자극의 형태지각에 영향을 미치는 것으로 나타났다. 즉, 물리적으로는 형태가 동일하더라도 두 번째 대상이 깊이단서에 의해 다른 형태로 지각될 가능성이 있는 경우에는 "같다"는 물리적 대응반응의 정확도가 낮아지고 반응시간이 증가하며, 물리적으로는 형태가 다르더라도 깊이단서에 의해 동일한 형태로 지각될 가능성이 있는 경우에는 '다르다'는 정확반응이 낮아지고 반응시간이 증가하는 것으로 나타났다. 이 결과를 모양 항등성에 대한 선행연구들의 개념적 방법론적 문제점 그리고 향후 수행해야 할 연구방향의 측면에서 논의하였다.

• 한국컴퓨터정보학회논문지
• /
• 제17권7호
• /
• pp.45-52
• /
• 2012

본 논문에서는 다중 클래스 아다부스트 기반의 분류기를 이용하여 엘리베이터 내 군집 밀도를 추정하는 방법을 제안한다. SOM을 사용하는 기존의 방법은 재현성이 떨어지며 충분한 성능을 내지 못한다. 제안한 방법은 GLDM(Grey-Level Dependency Matrix)과 GGDM(Grey-Gradient Dependency Matrix)의 텍스처 특징과 다중 클래스 아다부스트 기반의 분류기를 통해 실내 군집 밀도를 추정한다. 다중 클래스를 분류하기 위해 기존의 아다부스트 알고리즘에서 웨이트 업데이트 식을 변형하여 더 높은 성능의 약한 분류기를 생성하도록 하였다. 군집 밀도는 인원수에 따라 0명, 1~2명, 3~4명, 5명 이상 등 네 가지 클래스로 구분하였다. 엘리베이터 내 영상을 이용한 모의 실험 결과 제안된 방법은 기존의 방법보다 약 20% 정도의 검출률 향상을 나타내었다.

• 한국환경복원기술학회지
• /
• 제2권3호
• /
• pp.83-92
• /
• 1999

To investigate the influence of forest road characteristics and site conditions on the stability of forest-road in granite area, four forest roads had been selected in Kyongbuk regions. The total of 13 road characteristic variables were evaluated by the discriminant analysis. The factors influencing the stability of forest road were bed rock, slope length, coverage, hardness, side-ditch erosion and road width. But aspect and soil texture were not significant for the stability in this area. In the correlation between forest environment and road structure, hardness and bed rock was highly significant in stability group, and coverage and side-ditch erosion was highly significant in instability group. 75 of 175 segments were instable whereas the others were stable. The centroids value by discriminant function in the stability and instability were estimated to 3.0585 and -1.9116, respectively. The stability criterion of forest road was discriminated from the centroids value of the each group. The main factors contributing the stability of forest road were significant in order of side-ditch erosion, coverage, soil texture, elevation, gradient, slope length and construction year. The prediction rate of discriminant function for stability evaluation of forest road was as high as 97.44%. In conclusion, the forest road structure factors such as length, coverage and slope gradient were controlled by construction techniques. If the factors like those should be considered in design, construction and forest road management, the stability of forest road may increase more. And also, it is necessary to take slope protection measures like small terraces and retaining walls for stability of cut slope.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1807-1823
• /
• 2016

Local Binary Pattern (LBP) and its variants have powerful discriminative capabilities but most of them just consider each LBP code independently. In this paper, we propose sub oriented histograms of LBP for smoke detection and image classification. We first extract LBP codes from an image, compute the gradient of LBP codes, and then calculate sub oriented histograms to capture spatial relations of LBP codes. Since an LBP code is just a label without any numerical meaning, we use Hamming distance to estimate the gradient of LBP codes instead of Euclidean distance. We propose to use two coordinates systems to compute two orientations, which are quantized into discrete bins. For each pair of the two discrete orientations, we generate a sub LBP code map from the original LBP code map, and compute sub oriented histograms for all sub LBP code maps. Finally, all the sub oriented histograms are concatenated together to form a robust feature vector, which is input into SVM for training and classifying. Experiments show that our approach not only has better performance than existing methods in smoke detection, but also has good performance in texture classification.

• 전자공학회논문지CI
• /
• 제40권6호
• /
• pp.95-105
• /
• 2003

본 논문에서는 지문인증 시스템에서 인증 성능을 향상시키기 위한 기준점 검출 알고리즘과 특징 추출에 있어서 새로운 filterbank방법을 제안한다. 제안한 기준점 검출 알고리즘 GPM(Gradient Probabilistic Method)은 4개의 방향성분을 추출하여 방향성분을 가장 균일하게 가지는 지점을 검출하는 방법이며, 기존의 Poincare index방법과 달리 수학적 통계적 방법을 사용하기 때문에 지문의 융선에 대한 세부적이고 세밀한 전처리 과정이 불필요하며, arch형태 지문의 기준점 검출에 대한 단점을 해결한다. 또한, 제안한 filterbank방법은 기존filterbank방법에서 특징의 불균일한 분포로 생기는 단점을 균일한 분포로 만들어 추출함으로써 해결한다. 제안한 GPM의 실험결과 기존의 Poincare index방법에 비해서, 일반환경뿐 아니라 잡음환경에서의 특징 추출 시간과 인증률에서 우수함을 보여준다. 특히, 제안한 GPM은 Poincare index방법에 비해서, arch type의 지문에 대한 FAR은 일반 환경에서 49%, 밝기 잡음환경에서 39.2%, salt and pepper 잡음환경에서 15.7%의 향상을 보여준다. 또한, 기준점 검출시간에 있어서, 제안한 GPM방법은 기존의 Poincare index방법보다 0.07초의 감소를 보여주며, 특징추출 시간에 있어서도 제안한 filterbank 알고리즘은 기존의 filterbank 방법에 비해서 0.06sec의 감소를 보여준다.

• Korean Journal of Radiology
• /
• 제23권12호
• /
• pp.1281-1289
• /
• 2022

Objective: Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods: A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results: The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion: Radiomic models using MRI were able to differentiate JME from HCs.

• 한국멀티미디어학회논문지
• /
• 제11권5호
• /
• pp.623-632
• /
• 2008

본 논문에서는 영상 볼륨 데이터의 내부 3차원 객체들을 표현하기 위하여 색상 전이함수와 불투명도 전이함수를 사용하였다. 대체로 전이함수에서 경계부분이 만나는 지점의 값 설정이 모호하므로 볼륨 렌더링의 대상이 되는 시각 객체를 구분하기 위하여 영상이 가지는 특징들과 각 객체들 사이의 분할방법으로 객체 경계의 특징값 추출에 역점을 두었다. 따라서 공간상의 영상 기울기 특징 값을 추출하였으며 GPU의 효율을 증대시켜서 다차원 전이함수를 생성하였다. 그러므로 이 함수들을 그래픽 하드웨어 기반에 3차원 질감사상의 객체 경계 가시화 방법을 수행함으로써 좋은 연구결과를 얻게 되었다.