• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.141-143
• /
• 2004

This paper represents 3D line segment extraction method, which can be used in generating 3D rooftop model. The core of our method is that 3D line segment is extracted by using line fitting of elevation data on 2D line coordinates of ortho-image. In order to use elevations in line fitting, the elevations should be reliable. To measure the reliability of elevation, in this paper, we employed the concept of self-consistency. We carry out the experiment of 3D line extraction using synthetic images generated from Avenches data set of Ascona aerial images.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권3호
• /
• pp.174-179
• /
• 2005

This paper presents 3D line segment extraction method, which can be used in generating 3D rooftop model. The core of our method is that 3D line segment is extracted by using line fitting of elevation data on 2D line coordinates of ortho-image. In order to use elevations in line fitting, the elevations should be reliable. To measure the reliability of elevation, in this paper, we employ the concept of self-consistency. We test the effectiveness of the proposed method with a quantitative accuracy analysis using synthetic images generated from Avenches data set of Ascona aerial images. Experimental results indicate that the proposed method shows average 30 line errors of .16 - .30 meters, which are about $10\%$ of the conventional area-based method.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.59-64
• /
• 2002

This paper presents a method for line segment extraction for 3-d building reconstruction. Building roofs are described as a set of planar polygonal patches, each of which is extracted by watershed-based image segmentation, line segment matching and coplanar grouping. Coplanar grouping and polygonal patch formation are performed per region by selecting 3-d line segments that are matched using epipolar geometry and flight information. The algorithm has been applied to high resolution aerial images and the results show accurate 3-d building reconstruction.

• 전기전자학회논문지
• /
• 제13권2호
• /
• pp.181-185
• /
• 2009

In this paper, we are concerned with a 3D line segment extraction method by area-based stereo matching technique. The main idea is based on line fitting of elevation data on 2D line coordinates of ortho-image. Elevation data and ortho-image can be obtained by well-known area-based stereo matching technique. In order to use elevation in line fitting, the elevation itself should be reliable. To measure the reliability of elevation, in this paper, we employ the concept of self-consistency. We test the effectiveness of the proposed method with a quantitative accuracy analysis using synthetic images generated from Avenches data set of Ascona aerial images. Experimental results indicate that our method generates 3D line segments almost 7.5 times more accurate than raw elevations obtained by area-based method.

• 대한전자공학회논문지
• /
• 제27권3호
• /
• pp.116-123
• /
• 1990

3D computer vision에서 일치성 문제를 해결하기 위한 많은 논문이 epipolar line이 수평하다는 가정을 사용한다. 그러나 실제로 그러한 상황을 만들기에는 어려운 점이 있다. 본 논문은 epipolar line이 수평하지 않은 상태에서 적용할 수 있으며 line matching에 근거를 둔 binocular-stereo matching 알고리듬을 제안한다. 본 논문의 방법은 주어진 line segment 의 끝점에서의 epipolar line 들과 그점에서 maximum disparity에 의해서 결정되어지는 line searching window를 사용한다. 정합시에는 line segment들의 방향과 edge의 세기, cross-correlation들을 사용하였으며. 실험에 의해서 일치성 문제를 해결하기 위한 유용한 방법임을 알 수 있었다.

• Journal of Medicine and Life Science
• /
• 제16권1호
• /
• pp.1-5
• /
• 2019

Our purpose was to evaluate usefulness of the contrast-enhanced 3 dimensional fluid attenuated inversion recovery (3D-FLAIR) technique of half brain volume to diagnose the patients with facial neuritis based on segment-based analysis. We assessed retrospectively 17 consecutive patients who underwent brain MR imaging at 3 tesla for facial neuritis: 11 patients with idiopathic facial neuritis and 6 with herpes zoster oticus. Contrast enhanced 3D-FLAIR sequences of the half brain volume were analyzed and 3D T1-weighted sequence of the full brain volume were used as the base-line exam. Enhancement of the facial nerve was determined in each segment of 5 facial nerve segments by two radiologists. Sensitivity, specificity and accuracy of enhancement of each segment were assessed. The authors experienced a prompt fuzzy CSF enhancement in the fundus of the internal auditory canal in patients with enhancement of the canalicular segment. Interobserver agreement of CE 3D-FLAIR was excellent(${\kappa}$-value 0.885). Sensitivity, specificity, and accuracy of each segment are 1.0, 0.823, 0.912 in the canalicular segment; 0.118, 1.0, 0.559 in the labyrinthine segment; 0.823, 0.294, 0.559 in the anterior genu; 0.823, 0.529, 0.676 in the tympanic segment; 0.823, 0.235, 0.529 in the mastoid segment, respectively. In addition, those of prompt fuzzy enhancement were 0.647, 1.0, and 0.824, respectively. Incidence of prompt fuzzy enhancement with enhancement of the canalicular segment was 11 sites(55%): 6 (54.5%) in idiopathic facial neuritis and 5 (83.3%) in herpes zoster. Enhancement of the canalicular segment and prompt fuzzy enhancement on CE 3D-FLAIR was significantly correlated with occurrence of facial neuritis (p<0.001). CE 3D-FLAIR technique of the half brain volume is useful to evaluate the patients with facial neuritis as an adjunct sequence in addition to contrast-enhanced 3D T1-weighted sequence. On segment-based analysis, contrast enhancement of the canalicular segment is the most reliable. Prompt fuzzy enhancement is seen in not only herpes zoster, but in idiopathic facial neuritis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.40-43
• /
• 1997

This paper presents a 3D object recognition method for generation of 3D environmental map or obstacle recognition of mobile robots. An active light source projects a stripe pattern of light onto the object surface, while the camera observes the projected pattern from its offset point. The system consists of a laser unit and a camera on a pan/tilt device. The line segment in 2D camera image implies an object surface plane. The scaling, filtering, edge extraction, object extraction and line thinning are used for the enhancement of the light stripe image. We can get faithful depth informations of the object surface from the line segment interpretation. The performance of the proposed method has demonstrated in detail through the experiments for varies type objects. Experimental results show that the method has a good position accuracy, effectively eliminates optical noises in the image, greatly reduces memory requirement, and also greatly cut down the image processing time for the 3D object recognition compared to the conventional object recognition.

• 제어로봇시스템학회논문지
• /
• 제20권11호
• /
• pp.1153-1163
• /
• 2014

An efficient 3D SLAM (Simultaneous Localization and Map Building) method is developed for urban building environments using a tilted 2D LRF (Laser Range Finder), in which a 3D map is composed of perpendicular/horizontal planar polygons. While the mobile robot is moving, from the LRF scan distance data in each scan period, line segments on the scan plane are successively extracted. We propose an "expected line segment" concept for matching: to add each of these scan line segments to the most suitable line segment group for each perpendicular/horizontal planar polygon in the 3D map. After performing 2D localization to determine the pose of the mobile robot, we construct updated perpendicular/horizontal infinite planes and then determine their boundaries to obtain the perpendicular/horizontal planar polygons which constitute our 3D map. Finally, the proposed SLAM algorithm is validated via extensive simulations and experiments.

• 제어로봇시스템학회논문지
• /
• 제16권1호
• /
• pp.40-47
• /
• 2010

This paper presents a simultaneous localization and mapping (SLAM) of an indoor hallway environment using Rao-Blackwellized particle filter (RBPF) along with a line segment as a landmark. Based on the fact that fluent line features can be extracted around the ceiling and side walls of hallway using vision sensor, a horizontal line segment is extracted from an edge image using Hough transform and is also tracked continuously by an optical flow method. A successive observation of a line segment gives initial state of the line in 3D space. For data association, registered feature and observed feature are matched in image space through a degree of overlap, an orientation of line, and a distance between two lines. Experiments show that a compact environmental map can be constructed with small number of horizontal line features in real-time.

• 대한전자공학회논문지SP
• /
• 제37권4호
• /
• pp.46-55
• /
• 2000

본 논문에서는 스테레오 항공 영상으로부터 영상에 포함된 건물의 3차원 복원을 위해 건물 형태에 대한 모델을 생성하고 건물 모델을 구성하는 선소를 찾아 건물을 복원하는 알고리듬에 대해 다루고 있다. 건물을 검출하기 위해 일반적으로 필요한 에지 검출, 에지의 직선화, 선소의 연결 등의 복잡한 과정을 거치지 않고 복원하는 건물을 몇 개의 파라미터값으로 표현하고 건물 모델을 이용하여 원영상에서 건물의 선소들을 직접 검출하는 새로운 방법을 제안하였다. 선소 검출시 건물을 구성하는 각각의 선소에 대해 선소 측정 함수를 동시에 적용하여 독립적인 선소 검출 방법보다 건물 검출의 정확도를 높였다. 제안한 알고리듬을 스테레오 항공 영상에 적용한 결과, 건물의 정확한 검출 및 복원 결과를 얻을 수 있었다.