• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.1-7
• /
• 2016

ADAS (Advanced Driver Assistance Systems) requires not only real-time robust lane detection, both straight and curved, but also predicting upcoming steering direction by detecting the curvature of lanes. In this paper, a curvature lane detection algorithm is proposed to enhance the accuracy and detection rate based on using inverse perspective images and Gaussian Mixture Model (GMM) to segment the lanes from the background under various illumination condition. To increase the speed and accuracy of the lane detection, this paper used template matching, RANSAC and proposed post processing method. Through experiments, it is validated that the proposed algorithm can detect both straight and curved lanes as well as predicting the upcoming direction with 92.95% of detection accuracy and 50fps speed.

• Journal of Multimedia Information System
• /
• v.2 no.4
• /
• pp.303-310
• /
• 2015

Vulnerable road users such as bike, motorcycle, small automobiles, and etc. are easily attacked or threatened with bigger vehicles than them. So this paper suggests a new approach two-wheelers detection system riding on people based on modified histogram of oriented gradients (HOGs) which is weighted by curvature and local correlation coefficient. This correlation coefficient between two variables, in which one is the person riding a bike and other is its background, can represent correlation relation. First, we extract edge vectors using the curvature of Gaussian and Histogram of Oriented Gradients (HOG) which includes gradient information and differential magnitude as cell based. And then, the value, which is calculated by the correlation coefficient between the area of each cell and one of bike, can be used as the weighting factor in process for normalizing the HOG cell. This paper applied the Adaboost algorithm to make a strong classification from weak classification. The experimental results validate the effectiveness of our proposed algorithm show higher than that of the traditional method and under challenging, such as various two-wheeler postures, complex background, and even conclusion.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.5
• /
• pp.757-766
• /
• 1990

In this paper a new knowledge based vision system using orientation information on each surface of the 3-dimensional object is discussed. The measurement of the orientation information is performed by photometric stereo method. And then the obtained orientations are segmented using Gaussian curvature and mean curvature. A hierarchical knowledge base which is based on the characteristics, shape, area and length of the surface is built up, and then the knowledge based system infers by the condition interprete system (CIS). As the results, an easier and more accurate 3-D object recognition system is implemented, because it uses the characteristics and shapes as units of the surface in the recognition process.

• Honam Mathematical Journal
• /
• v.39 no.3
• /
• pp.363-377
• /
• 2017

In the present study we consider the generalized rotational surfaces in Euclidean spaces. Firstly, we consider generalized spherical curves in Euclidean (n + 1)-space ${\mathbb{E}}^{n+1}$. Further, we introduce some kind of generalized spherical surfaces in Euclidean spaces ${\mathbb{E}}^3$ and ${\mathbb{E}}^4$ respectively. We have shown that the generalized spherical surfaces of first kind in ${\mathbb{E}}^4$ are known as rotational surfaces, and the second kind generalized spherical surfaces are known as meridian surfaces in ${\mathbb{E}}^4$. We have also calculated the Gaussian, normal and mean curvatures of these kind of surfaces. Finally, we give some examples.

• Korean Journal of Optics and Photonics
• /
• v.9 no.3
• /
• pp.151-155
• /
• 1998

A new Fabry-Perot tunable filter has been built with simple construction, which does not require any additional aligning and/or beam-confining components for the reduction of the diffraction loss. For this feature, one of the two fibers for the filter is processed to have a concave mirror whose curvature is the same as that of the wavefront of the Gaussian beam from the first fiber. After high reflection coatings, the two fibers are aligned to result in an FP filter whose bandwidth, free spectral range, and insertion loss is 1.47nm, 52nm, 5.6dB respectively.

• Journal of the Society of Naval Architects of Korea
• /
• v.28 no.2
• /
• pp.21-27
• /
• 1991

This paper outlines the method of formulating the bi-cubic B-spline surface of ship hull, employing the open uniform knot vector as well as the periodic uniform knot vector. An appropriate set of B-spline control vertices to generate the B-spline surface is determined by obtaining the pseudoinverse matrix of basis functions. The comparison between the given offsets and the resulting coordinates from the generated ship hull surface shows a good agreement. To check the fairness of the surface Gaussian curvature is calculated on many small subpatches and displayed on the black-and-white plot of the isoparametric net of the surface.

• Journal of the Society of Naval Architects of Korea
• /
• v.29 no.3
• /
• pp.15-20
• /
• 1992

This paper outlines the methods of visualizing 3-dimensional free form surfaces employing the Painter's algorithm, especially for the ship hull forms which are defined as open uniform Bi-cubic B-spline surfaces. The computer graphic codes are developed for the transparent wire-frame, the hidden surface removal and the shading visualization techniques, The codes are applied to the ship hull 3-dimensional surface visualization and the color graphic figures are displayed. Also Gaussian curvature is displayed on the color plots of the isoparametric net of the ship hull surface.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1579-1580
• /
• 2015

본 논문에서는 3차원 메쉬 모델의 중요 영역을 표현하는 메쉬 돌출맵(mesh saliency map)을 생성하기 위하여 다중 스케일 평균 곡률 (multi-scale mean curvature)을 기반으로 정의된 전역 희소치(global rarity)를 이용하는 방법을 제안한다. 제안 방법에서는 우선, 메쉬 모델의 지역 영역 특성을 정의하기 위하여 기존 관련 연구들에서 많이 사용하고 있는 가우시안 가중치 평균곡률(Gaussian-weighted mean curvature)을 5단계 서로 다른 스케일에서 정의하고, 메쉬의 각 정점(vertex)에 대하여 중심주변 연산자(center-surround operator)를 적용하여 5단계 지역 돌출특성(local saliency)을 정의한다. 주어진 메쉬 모델의 전역 희소치를 구하기 위하여 메쉬의 모든 정점쌍 (vertex pair)에 대하여 5단계 지역 돌출 특성 공간에서의 거리를 계산하고, 각 정점별로 5단계 지역 돌출 특성 공간에서의 다른 정점과의 거리의 합으로 전역 희소치를 정의한다. 이러한 전역 희소치를 각 정점의 메쉬 돌출치로 정의한다. 서로 다른 형태의 3차원 모델에 대하여 제안방법에 의한 메쉬 돌출맵과 지역 특성만을 고려한 기존 메쉬 돌출맵을 생성하여 중요 영역 표현 결과를 비교 분석한다.

• Bulletin of the Korean Mathematical Society
• /
• v.49 no.5
• /
• pp.1101-1129
• /
• 2012

We study the geometry of the images of 1-dimensional homogeneous submersions for each of the model spaces X of the eight 3-dimensional geometries. In particular, We shall calculate the group of isometries and the curvatures of the base surfaces for each of the model spaces of 3-dimensional geometries, with respect to every closed subgroup of the isometries of X acting freely.

• Journal for History of Mathematics
• /
• v.20 no.4
• /
• pp.49-60
• /
• 2007

In this article, the concept of rigidity of smooth surfaces in the three dimensional Euclidean space which naturally arises in elementary geometry is introduced, and the natural process of the development of rigidity theory for compact surfaces and its generalizations are investigated.