• 한국컴퓨터정보학회논문지
• /
• 제15권10호
• /
• pp.35-47
• /
• 2010

본 논문은 에지를 이용한 차량 검출 시 검출률 향상을 위해 부정확한 에지 정보를 보완하는 확장 에지 분석 기법을 제안한다. 차량은 영상에서 차량이 지면과 닺는 경계면과 좌우 경계선을 이용하여 검출한다. 제안하는 확장 에지 분석기법은 차량과 지면의 경계선을 표현하는 수평 에지가 조명이나 잡음 등으로 인해 부정확하게 얻어지는 문제를 해결하기 위해 수평에지를 양방향으로 확장하여 차량 양쪽의 경계선인 두 개의 수직에지 성분과 교차하는 점을 찾는 방법이다. 즉, 미리 설정된 관심영역 내에서 인접한 수평에지 정보를 이용하여 에지를 융합하거나 분리하는 방법을 통해 수평에지를 추출하고 추출된 수평에지 영역에서 차량 그림자 영역을 검출하여 차량 바닥선을 결정한다. 차량의 폭은 수평에지와 교차하는 수직에지들 중에서 좌우 대칭을 형성할 수 있는 에지들과 차간 거리를 고려하여 결정한다. 확장 에지 분석기반 차량 검출 기법은 복잡한 배경을 갖는 도로 영상에서 기존의 에지 정보를 이용한 차량 검출 방식보다 효율적이다. 본 논문에서 제안하는 차량 검출 기법의 우수성은 복잡한 도로 영상에서 차량 검출 실험을 통해 검증하였다.

• 한국표면공학회지
• /
• 제46권3호
• /
• pp.133-138
• /
• 2013

We have developed a 2D axi-symmetric numerical model for an inductively coupled plasma system in order to analyze gas mixing effect through a narrow gap shower head. For frictional flow, holes of 0.5 mm diameter and 2 mm length are approximately modeled in 2D. Gas velocity distribution 10 mm below the shower head showed 2 times difference between the center and the edge at 10 mTorr. At 10 mm above the wafer, it was increased to 6 times difference due to the pumping duct effect. The model with a 5 mm height buffer region of a shower head showed reasonable behavior of Ar discharge. The density of Ar metastable showed additional peak inside the buffer region around the edge holes.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.41.1-41
• /
• 2002

This paper describes a robust landmark matching method to reduce ambiguity of candidate of landmark. General robot system acquires the candidate of landmark through vision sensor in outdoor environment. Our robot uses the omnidirectional vision system to get all around the view. Thus, the robot obtains more candidates of landmark than the conventional vision system. To obtain the candidates of landmark, robot uses the two types of feature. They are vertical edge and merged region of vertical edges. The former is to extract the vertical line of building, street lamp, etc. The latter is to reduce ambiguity of vertical edge in similar region. It is difficult to match the candidates of landmark...

• 한국결정성장학회지
• /
• 제18권1호
• /
• pp.1-4
• /
• 2008

The growth of composite-structured Nd:$GdVO_4$ single crystal rods by the double die EFG method is reported. Two crucibles are combined with an outer and inner die for ascending of different melt. The composite-structured Nd:$GdVO_4$ single crystal rods with a length of 50 mm and an outer diameter of 5 mm including of inner Nd-doped core region with diameter 3 mm were grown successfully. Nd distribution in the, radial direction has graded profile from result of EPMA. Absorption coefficient in the core region at 808 nm was $42cm^{-1}$. Finally, we demonstrated the laser oscillation using our composite crystal and 2-W output was obtained.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2003년도 춘계학술발표대회논문집
• /
• pp.431-434
• /
• 2003

In this paper, we propose an efficient method not only f3r producing accurate region segmentation, solving the over-segmentation problem of watershed algorithm but also f3r reducing post-processing time by reducing computation loads. Through this proposed method, region segmentation of neighboring objects and discrimination of similar intensities were effectively obtained. Input image of watershed algorithm has used the derivative-based detectors such as Sobel and Canny. But proposed method uses the pixels-similarity-based detector, that is, SUSAN. By adopting this proposed method, we can reduce the noise problem and solve the problem of over-segmentation and not lose the edge information of objects. We also propose Zero-Crossing SUSAN. With Zero-Crossing SUSAN, the edge localization, times and computation loads can be improved over those obtained from existing SUSAN

• 대한원격탐사학회지
• /
• 제11권1호
• /
• pp.47-64
• /
• 1995

In this paper, an algorithm that finds man-made structures in a praylevel aerial images is proposed to perform stereo matching. An extracted contour of buildings must have a high accuracy in order to get a good feature-based stereo matching result. Therefore this study focuses on the use of edge following in the original image rather than use of ordinary edge filters. The Algorithm is composed of two main categories; one is to find candidate regions in the whole image and the other is to extract exact contours of each building which each candidate region.. The region growing method using the centroid linkage method of variance value is used to find candidate regions of building and the contour line tracing algorithm based on an adge following method is used to extract exact contours. The result shows that the almost contours of building composed of line segments are extracted.

• 전기의세계
• /
• 제30권12호
• /
• pp.811-816
• /
• 1981

In this paper, the finite element method is applied to find the flux distribution of the magnetic field in the end region of the tubular motor. In order to analyze two-dimensional flux distribution, the r-z domain to be analyzed is subdivided into 56 nodes, 84 elements. In the case of wt=O and .pi./2, the flux distribution is shifted to the edge with frequency (w) and time (t) increase in the edge and the air gap. It is proved that this study does fit the actual phenomena.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.7-10
• /
• 2003

This paper proposes the multiple objects focusing algorithm. Given multiple objects at different distances from a camera, we assume that one object is well-focused and the others are out-of-focused. The proposed auto-focusing algorithm is summarized as follows: (i) detects edges from an input image, (ⅱ) estimates the radius of PSF (Point Spread Function) across the edge, (ⅲ) gather edge points having same radius of PSF, (ⅳ) segments the image into regions with the same radius of PSF, and (ⅴ) restores the each segmented region using the corresponding PSF.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.105-108
• /
• 2002

This paper proposes a new watermarking algorithm to embed data in 1-bit images using edges for protecting illegal copies or modifications. This method is based on edge detection to decide the most invisible region. This paper also introduces a new shuffling method which embeds data in each blocks uniformly and finds Positions under the limited attacks. In experiment, we compare the proposed shuffling method with M. Wu's method.

• 전자공학회논문지B
• /
• 제31B권12호
• /
• pp.72-80
• /
• 1994

In this paper, we present a digital image data compression method using vector quantization preserving edges. A new vector quantization algorithm is proposed using a new sampling method and edge region extraction. The codebook generation time is faster than existing algorithms and the quality of decompressed images is much improved. Extrimental results suggest that the resultant compression ratio and PSNR are better than those of BPVQ and HMVQ methods.