• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.190-192
• /
• 2003

본 논문은 캘리브레이션 정보를 모르는 카메라로부터 얻은 시퀀스 영상에서 공간상에서 평면인 물체의영상 정보를 이용하여 카메라 내부 및 외부 파라미터를 추정하고, 이를 이용하여 가상의 3D 그래픽을 시퀀스 영상에 정합하는 방법을 제안한다. 제안된 방법은 기존의 방법에 비해 손쉽게 이미지에 가상의 3D 그래픽 오브젝트를 정합할 수 있으며, 눈에 보이는 정합오차를 최소화하며 DirectX와 같은 3D 그래픽 툴과 쉽게 연동이 되는 장정이 있다. 본 연구는 비디오와 같은 영상에 3D 영상을 합성하는 대화형 비디오 컨텐트 개발에 활용할 수 있을 것으로 기대된다.

• ETRI Journal
• /
• v.28 no.2
• /
• pp.162-174
• /
• 2006

Several photogrammetric and geographic information system applications such as surface matching, object recognition, city modeling, environmental monitoring, and change detection deal with multiple versions of the same surface that have been derived from different sources and/or at different times. Surface registration is a necessary procedure prior to the manipulation of these 3D datasets. This need is also applicable in the field of medical imaging, where imaging modalities such as magnetic resonance imaging (MRI) can provide temporal 3D imagery for monitoring disease progression. This paper will present a general automated surface registration procedure that can establish correspondences between conjugate surface elements. Experimental results using light detection and ranging (LIDAR) and MRI data will verify the feasibility, robustness, and accuracy of this approach.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.11a
• /
• pp.201-206
• /
• 2003

In clinical practice, CT Angiography is a powerful technique for the visualziation of blood flow in arterial vessels throughout the body. However CT Angiography images of blood vessels anywhere in the body may be fuzzy if the patient moves during the exam. In this paper, we propose a novel technique for removing global motion artifacts in the 3D space. The proposed methods are based on the two key ideas as follows. First, the method involves the extraction of a set of feature points by using a 3D edge detection technique based on image gradient of the mask volume where enhanced vessels cannot be expected to appear, Second, the corresponding set of feature points in the contrast volume are determined by correlation-based registration. The proposed method has been successfully applied to pre- and post-contrast CTA brain dataset. Since the registration for motion correction estimates correlation between feature points extracted from skull area in mask and contrast volume, it offers an accelerated technique to accurately visualize blood vessels of the brain.

• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.85-97
• /
• 2003

Medical tomography images like CT, MRI, PET, SPECT, fMRI, ett have been widely used for diagnosis and treatment of a patient and for clinical study in hospital. In many cases, tomography images are scanned in several different modalities or with time intervals for a single subject for extracting complementary information and comparing one another. 3D image registration is mapping two sets of images for comparison onto common 3D coordinate space, and may be categorized to marker -based matching and feature-based matching. 3D registration of brain images has an important role for visual and quantitative analysis in localization of treatment area of a brain, brain functional research, brain mapping research, and so on. In this article, marker-based and feature-based matching methods which are often used are introduced.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.89-90
• /
• 2021

본 논문에서는 3D(dimensional) 스켈레톤을 이용하여 멀티 뷰 RGB-D 카메라를 캘리브레이션 하는 새로운 기법을 제안하고자 한다. 멀티 뷰 카메라를 캘리브레이션 하기 위해서는 일관성 있는 특징점이 필요하다. 우리는 다시점 카메라를 캘리브레이션 하기 위한 특징점으로 사람의 스켈레톤을 사용한다. 사람의 스켈레톤은 최신의 자세 추정(pose estimation) 알고리즘들을 이용하여 쉽게 구할 수 있게 되었다. 우리는 자세 추정 알고리즘을 통해서 획득된 3D 스켈레톤의 관절 좌표를 특징점으로 사용하는 RGB-D 기반의 캘리브레이션 알고리즘을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.454-456
• /
• 2001

본 논문에서는 비디오 영상열 내에 컴퓨터가 생성한 가상의 3D 영상을 이음새 없이 추가하기 위한 문제에 초점을 맞추고 있다. 2단계의 견고한 통계적인 메소드는 추적된 커브들의 모델-영상 대응점으로부터 보다 정확한 자세를 평가하기 위하여 자세 계산을 위해 사용되었다. 또한, 관점의 정확성 향상을 위하여 두 개의 연속하는 영상들간에 매치될 수 있는 핵심점을 카메라 움직임에 대한 상관관계 함수로 사용하여 매칭 에러와 reprojection 에러를 포함한 비용함수를 최소화함에 의해 관점을 향상시킨다. 비디오 영상내 객체 영상과 가상의 3D 영상간에 발생하는 폐색 공간문제를 해결하기 위하여 반 자동 알고리즘을 제안하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.11C
• /
• pp.896-900
• /
• 2010

We investigate the bit error rate against signal-to-noise ratio performance corresponding to track mis-registration for patterned media storage. The patterned media channels with and without soft underlayer are implemented, and we simulate using one-dimensional Viterbi detector and two-dimensional soft output Viterbi detector (SOVA) when the track mis-registration is 0% (on-track), 10%, 20%, 30%, and 40%. While the BER performance degrades approximate 0.3 ~ 0.5 dB at 10% track mis-registration, it degrades severe over 10% track mis-registration.

• Spatial Information Research
• /
• v.14 no.1 s.36
• /
• pp.67-83
• /
• 2006

The cadastral system of our country is same as Japanese 2D-cadastral system. Recently, not only surface but ground and underground is became the developable space, so today the management of cadastre becomes more difficult to preserve each ownership of properties and to manage the nation lade efficiently. Consequently, we are in need of the 3D-cadastral information system for handle with whole cadastre information. In this paper, we propose the efficiently registrating strategies and more stabile construction technique for the 3D-cadastral information system.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.303-314
• /
• 2023

This study aimed to assess the practical feasibility of advanced deformable image registration (DIR) algorithms in radiotherapy by employing two distinct datasets. The first dataset included 14 4D lung CT scans and 31 head and neck CT scans. In the 4D lung CT dataset, we employed the DIR algorithm to register organs at risk and tumors based on respiratory phases. The second dataset comprised pre-, mid-, and post-treatment CT images of the head and neck region, along with organ at risk and tumor delineations. These images underwent registration using the DIR algorithm, and Dice similarity coefficients (DSCs) were compared. In the 4D lung CT dataset, registration accuracy was evaluated for the spinal cord, lung, lung nodules, esophagus, and tumors. The average DSCs for the non-learning-based SyN and NiftyReg algorithms were 0.92±0.07 and 0.88±0.09, respectively. Deep learning methods, namely Voxelmorph, Cyclemorph, and Transmorph, achieved average DSCs of 0.90±0.07, 0.91±0.04, and 0.89±0.05, respectively. For the head and neck CT dataset, the average DSCs for SyN and NiftyReg were 0.82±0.04 and 0.79±0.05, respectively, while Voxelmorph, Cyclemorph, and Transmorph showed average DSCs of 0.80±0.08, 0.78±0.11, and 0.78±0.09, respectively. Additionally, the deep learning DIR algorithms demonstrated faster transformation times compared to other models, including commercial and conventional mathematical algorithms (Voxelmorph: 0.36 sec/images, Cyclemorph: 0.3 sec/images, Transmorph: 5.1 sec/images, SyN: 140 sec/images, NiftyReg: 40.2 sec/images). In conclusion, this study highlights the varying clinical applicability of deep learning-based DIR methods in different anatomical regions. While challenges were encountered in head and neck CT registrations, 4D lung CT registrations exhibited favorable results, indicating the potential for clinical implementation. Further research and development in DIR algorithms tailored to specific anatomical regions are warranted to improve the overall clinical utility of these methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.5
• /
• pp.375-381
• /
• 2007

A novel method to register images onto 3D data, such as 3D point cloud, 3D vectors, and 3D surfaces, is proposed. The proposed method estimates the exterior orientation of a camera with respective to the 3D data though fitting pairs of the normal vectors of two planes passing a focal point and 2D and 3D lines extracted from an image and the 3D data, respectively. The fitting condition is that the angle between each pair of the normal vectors has to be zero. This condition can be represented as a numerical formula using the inner product of the normal vectors. This paper demonstrates the proposed method can estimate the exterior orientation for the image registration as simulation tests.