• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.237-240
• /
• 2001

본 논문은 단일 뷰-포인트 카메라 모델을 이용하여 무-특징 환경 (non-feature environment)에서의 영상 모자이킹 알고리즘을 제안한다. 특징 환경에서 영상의 기하구조를 만들어 내고 이 기하구조를 무-특징 환경에 적용시켜 모자이크 영상을 얻는다.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.405-408
• /
• 2017

Based on the fact that high similarities exist between viewpoints of multi-view images, MV-HEVC achieves high encoding efficiency by performing conventional temporal direction prediction in a single viewpoint as well as inter-view prediction between viewpoints. In this paper, we propose to integrate SHVC and MVC (Multi-view Video Coding) to implement scalable multi-view video encoder using HEVC as a base layer. According to experimental results, it is verified that the BD-PSNR improvement reaches up to 1.5dB while reducing the BD-Bitrate by around 50~60%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.835-836
• /
• 2009

본 연구는 스케치기반의 인터페이슬 통해 큐빅스플라인 곡선을 자동으로 생성하는 방법을 제시한다. 또한 탐색항해에서 많이 발생하는 이동중 관심영역으로의 뷰포인트를 자동으로 변환하기 위한 방법을 제시한다. 스케치기반 인터페이스는 일반인에게 친숙한 종이환경과 유사한 인터페이스를 통해 가상환경의 탐색항해를 위한 투어패스를 설정하고 관심영역을 중심으로 뷰포인트가 자동적으로 변환하는 기법을 제시함으로써 가상환경에 전문적인 지식이 없거나 전문개발자에게도 시간과 노력을 절약할 수 있는 방법을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.660-662
• /
• 2023

3차원 포인트 클라우드의 의미적 분할은 환경을 구성하는 물체 단위로 포인트 클라우드를 분할하는 작업으로서, 환경의 3차원적 구성을 이해하고 환경과 상호작용에 필수적인 시각 지능을 요구한다. 본 논문에서는 포인트 클라우드에서 추출하는 3차원 기하학적 특징과 함께 멀티-뷰 영상에서 추출하는 2차원 시각적 특징들도 활용하는 새로운 3차원 포인트 클라우드 의미적 분할 모델 MFNet을 제안한다. 제안 모델은 서로 이질적인 2차원 시각적 특징과 3차원 기하학적 특징의 효과적인 융합을 위해, 새로운 중기 융합 전략과 멀티-모달 교차 주의집중을 이용한다. 본 논문에서는 ScanNetV2 벤치마크 데이터 집합을 이용한 다양한 실험들을 통해, 제안 모델 MFNet의 우수성을 입증한다.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.10
• /
• pp.1767-1772
• /
• 2006

Computer-generated integral imaging system is an auto-stereoscopic display system that users can see and feel the stereoscopic images when they see the pre-rendered elemental images through a lens array. The process of constructing elemental images using computer graphics is called image mapping. Viewpoint vector rendering (VVR) method is one of the image mapping algorithm specially designed for real-time graphics applications, which would not be affected by the size of the rendered objects or the number of elemental lenses used in the integral imaging system. This paper describes a new VVR framework which improved its rendering performance considerably. It also compares the previous VVR implementation with the new VVR work utilizing GPU and shows that newer implementation shows pretty big improvements over the old method.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.191-201
• /
• 2005

In this paper, we propose a method to calculate camera motion parameter, which is based on efficient invariant features irrelevant to the camera veiwpoint. As feature information in previous research is variant to camera viewpoint. information content is increased, therefore, extraction of accurate features is difficult. LM(Levenberg-Marquardt) method for camera extrinsic parameter converges on the goat value exactly, but it has also drawback to take long time because of minimization process by small step size. Therefore, in this paper, we propose the extracting method of invariant features to camera viewpoint and two-stage calculation method of camera motion parameter which enhances accuracy and convergent degree by using camera motion parameter by 2D homography to the initial value of LM method. The proposed method are composed of features extraction stage, matching stage and calculation stage of motion parameter. In the experiments, we compare and analyse the proposed method with existing methods by using various indoor images to demonstrate the superiority of the proposed algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.173-182
• /
• 2005

In this paper, we propose a landmark recognition method which is irrelevant to the camera viewpoint on the navigation for localization. Features in previous research is variable to camera viewpoint, therefore due to the wealth of information, extraction of visual landmarks for positioning is not an easy task. The proposed method in this paper, has the three following stages; first, extraction of features, second, learning and recognition, third, matching. In the feature extraction stage, we set the interest areas of the image. where we extract the corner points. And then, we extract features more accurate and resistant to noise through statistical analysis of a small eigenvalue. In learning and recognition stage, we form robust feature models by testing whether the feature model consisted of five corner points is an invariant feature irrelevant to viewpoint. In the matching stage, we reduce time complexity and find correspondence accurately by matching method using similarity evaluation function and Graham search method. In the experiments, we compare and analyse the proposed method with existing methods by using various indoor images to demonstrate the superiority of the proposed methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.505-518
• /
• 2023

3D point cloud semantic segmentation is a computer vision task that involves dividing the point cloud into different objects and regions by predicting the class label of each point. Existing 3D semantic segmentation models have some limitations in performing sufficient fusion of multi-modal features while ensuring both characteristics of 2D visual features extracted from RGB images and 3D geometric features extracted from point cloud. Therefore, in this paper, we propose MMCA-Net, a novel 3D semantic segmentation model using 2D-3D multi-modal features. The proposed model effectively fuses two heterogeneous 2D visual features and 3D geometric features by using an intermediate fusion strategy and a multi-modal cross attention-based fusion operation. Also, the proposed model extracts context-rich 3D geometric features from input point cloud consisting of irregularly distributed points by adopting PTv2 as 3D geometric encoder. In this paper, we conducted both quantitative and qualitative experiments with the benchmark dataset, ScanNetv2 in order to analyze the performance of the proposed model. In terms of the metric mIoU, the proposed model showed a 9.2% performance improvement over the PTv2 model using only 3D geometric features, and a 12.12% performance improvement over the MVPNet model using 2D-3D multi-modal features. As a result, we proved the effectiveness and usefulness of the proposed model.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.107-114
• /
• 2010

A nonlinear story is generated through the interactivity with users using the interactive storytelling system. In a play or movie, audiences can watch one scene at a time, and in order to watch next scene, they should wait for the end of current scene. In the real world, however, various events can simultaneously happen at different places, and even those events performed by characters may dramatically affect the flow of the story. This paper suggests Constraint Based narrative structure to create such story, known as "Simultaneous Story Arcs", and "Multi Viewpoint" to simultaneously lead the direction of the stories in each place.