• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.242-245
• /
• 2021

시청자의 시점 위치를 선택하여 360VR 콘텐츠를 경험하는 다중시점 또는 자유시점 360VR 콘텐츠의 전송은 매우 높은 대역폭을 소비하게 된다. 특히 다중 사용자가 존재하는 셀룰러 환경에서는 특정 사용자에게 한정된 대역폭만을 할당할 수 있으므로 불가피하게 전송 품질 악화 또는 전송 지연을 겪게 된다. 다중시점(multi-viewpoint) 360VR 콘텐츠의 경우 시청자가 시점의 위치를 변경하면 해당 위치의 콘텐츠를 전송하므로, 한정된 대역폭이 주어지는 통신환경에서 시점을 이동할 때 마다 큰 전송 지연을 겪게되어 사용자 경험이 매우 떨어지는 것을 예상할 수 있다. 본 논문에서는 다시점 360 비디오에서 시점 변경을 시도할 때 전송지연을 줄이기 위하여 주변 위치의 영상을 적절히 Pre-Loading 하는 전송방식을 고려하고, 실질적인 5G 네트워크 환경에서 시점 변환에 따른 지연시간 성능을 분석하였다. 특정 수준 이하로 지연시간을 낮추기 위해서는 사용자 이동패턴에 대한 적절한 예측 기법이 요구되며, 정확도에 따른 지연시간 감소를 실험을 통하여 확인하였다.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.954-964
• /
• 2020

In immersive media, the most important factor that provides immersion is depth information. Therefore, it is essential to obtain high quality depth information in order to produce high quality immersive media. In this paper we propose an algorithm to improve depth map, considering the segmentation of images and the relationship between multiple views in multi-view systems. The proposed algorithm uses a super-pixel segmentation technique to divide the depth map of the reference view into several segments, and project each segment into adjacent view. Subsequently, the depth map of the adjacent view is improved using plane estimation using the information of the projected segment, and then reversed to the reference view. This process is repeated for several adjacent views to improve the reference depth map by updating the values of the improved adjacent views and the initial depth map of the reference view. Through simulation, the proposed algorithm is shown to surpass the conventional algorithm subjectively and objectively.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.47-55
• /
• 2012

In this paper, we propose a method to reconstruct accurate 3D shape object by using multi-view images which are disturbed by motion blur. In multi-view deblurring, more precise PSF estimation can be done by using the geometric relationship between multi-view images. The proposed method first estimates initial 2D PSFs from individual input images. Then 3D PSF candidates are projected on the input images one by one to find the best one which are mostly consistent with the initial 2D PSFs. 3D PSF consists with direction and density and it represents the 3D trajectory of object motion. 야to restore 3D shape by using multi-view images computes the similarity map and estimates the position of 3D point. The estimated 3D PSF is again projected to input images and they replaces the intial 2D PSFs which are finally used in image deblurring. Experimental result shows that the quality of image deblurring and 3D reconstruction improves significantly compared with the result when the input images are independently deblurred.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.31-33
• /
• 2012

MPEG 3DV 그룹에서는 재생되는 시점 수 보다 적은 시점의 다시점 비디오와 그에 대응하는 깊이영상 및 관련 파라미터를 하나의 비트스트림으로 부호화하는 다시점 및 깊이영상 부호화(MVD: Multiview Video plus Depth) 표준화가 진행 중에 있다. 본 논문은 3DV MVD 비트스트림 포맷을 MPEG-2 TS 로 다중화하기 위한 TS 다중화 확장기법을 제안한다. 또한, MVD 재현 시나리오에 따른 효율적인 TS 전송 구조를 제시하고, TS 다중화 SW 툴의 설계 및 구현을 통하여 그 장단점을 고찰한다. 제안된 기법은 프로그램 및 ES 에 대한 정보를 함께 다중화하여 MVD 의 다양한 재현 시나리오 적응 및 효율적인 복호화 및 가상시점 합성을 지원할 수 있다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.228-237
• /
• 2013

In this paper, we propose a normalized cross correlation(NCC)-based multiview background subtraction method which is robust when an object and background have similar color. When the background of the capturing environment is not artificially composed, the regions in the background images which would be occluded by an object tends to have difference colors. The colors of those regions, however, becomes similar when an object enters the capturing environment. Based on this assumption, this paper proposes a concept of GoNCC(Graph of Normalized Cross Correlation). GoNCC is the distribution of NCC between a pixel in an image and pixels related by epipolar constraints with the pixel. The proposed multiview background subtraction method is performed by comparing GoNCC of the current images with the background images. To reduce computational complexity, we perform multiview background subtraction only to the pixels undetermined by single view background subtraction. Experimental results show that the proposed method is more robust to color similarity between an object and background than a single-view background subtraction method and a previous multiview background subtraction method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.273-275
• /
• 2011

최근 교통량이 증가함에 따라 자동차 사고피해도 비례하여 증가하고 있으며, 이로 인해 CCTV 등과 같이 교통사고 예방에 소모되는 비용이 막대하게 지출되고 있다. 단일시점 카메라의 시스템은 객체들의 겹침, 카메라각도에 의한 인식오류 등으로 오차율이 높은 단점이 있다. 이를 보완하기 위해 다중시점의 협업기반 자동 상황인지 시스템을 제안한다. 제안하는 방법은먼저 영상데이터로부터 차량, 사람 등의 객체를 추출하고 이들 객체 쌍의 특징 정보를 계산한다. 이를 바탕으로 각 카메라 센서노드의 규칙기반 시스템을 이용하여 객체간의 사고여부를 가려낸다. 각 센서노드의 사고여부 정보는 메인서버로 수집되고, 수집된 정보는 상위 규칙에 의해 최종 사고 여부가 판단된다. 본 논문에서는 실제 교차로에 설치된세대의 카메라를 이용한 실험을 통해 제안하는 시스템의 성능을 검증하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.1 s.31
• /
• pp.37-43
• /
• 2005

GPS has been increasingly used in high precision positioning thanks to rapid advances of GPS technology. In order to acquire precise coordinates from GPS, it is important to solve accurately integer ambiguity inherent in GPS signals. The previous methods to solve this ambiguity were mostly based on multi-epoch data but recently a method based on single-epoch data has been developed. In this study, we selected three sets of software based on these methods, applied them to GPS baseline processing, and analyzed the experimental results. From these analyses, we have also verified the potential of their uses in real time precision positioning.

• Journal of Convergence for Information Technology
• /
• v.9 no.4
• /
• pp.146-151
• /
• 2019

In this paper, we developed a multi-view video content based on real-world technology and a pilot using the production technology, and provided realistic contents production technology that can select a desired direction at a user 's view point by providing users with various viewpoint images. We also created multi-view video contents that can indirectly experience local cultural tourism resources and produced cyber tour contents based on multi-view video (realistic technology). This technology development can be used to create 3D interactive real-world contents that are used in all public education fields such as libraries, kindergartens, elementary schools, middle schools, elderly universities, housewives classrooms, lifelong education centers, The domestic VR market is still in it's infancy, and it's expected to develop in combination with the 3D market related to games and shopping malls. As the domestic educational trend and the demand for social public education system are growing, it is expected to increase gradually.

• Journal of Korean Society of Transportation
• /
• v.16 no.4
• /
• pp.21-32
• /
• 1998

인공신경망을 이용하여 고속도로 교통량을 예측함에 있어, 입력요소에 따른 예측력의 차이를 분석하였다. 입력요소의 차이는 크게 공간적 지점의 차이와 시간적 시점의 차이로 구분하였다. 우선 공간적 지점에 관한 입력요소로는 두 가지 경우를 가정하였는 바, 그 하나는 상류지점의 교통량만을 입력요소로 사용한 경우이며, 나머지는 목표지점에 대한 상.하류지점의 교통량을 입력요소로 사용한 경우이다. 시간적 시점의 관점에서는 단일시점과 다중시점으로 입력요소를 구분하였다. 경부고속도로 FTMS자료를 이용하여 분석한 사례연구의 결과, 미래 시점의 교통량을 예측할 때 모형의 입력요소로 상류지점의 교통량만을 단독으로 사용했을 때보다 상.하류지점의 자료를 사용했을 때 예측력은 훨씬 높아지는 것으로 분석되었다.