• 인터넷정보학회논문지
• /
• 제11권1호
• /
• pp.103-116
• /
• 2010

본 논문은 에이전트 기반의 시뮬레이션을 이용하여 최적의 카메라 배치 방법을 제안한다. 공간 중요도를 분석하고 공간을 효율적으로 커버하기 위해, 공간분류와 이동하는 사람의 패턴 분석기반으로 에이전트 기반의 시뮬레이션을 수행하였다. 에이전트 기반의 카메라 배치 기법은 카메라 성능뿐만 아니라 경로탐색 알고리즘으로부터 추출한 공간 중요도를 고려하여 개발하였다. 이 기법은 설치비용을 고려하여 최적의 카메라 수를 결정할 뿐만 아니라 카메라의 위치와 방향을 조정한다는 것을 보인다. 제안한 방법을 검증하기 위해 시뮬레이션 결과를 실제 영상과 비교하였으며, 특정 공간에서 시뮬레이션한 실험 결과를 보인다.

• 스마트미디어저널
• /
• 제11권9호
• /
• pp.75-80
• /
• 2022

최근 현실감 있는 경험을 제공하기 위한 몰입형 가상현실(VR) 기술에 대한 연구 개발이 활발하게 진행되고 있다. 가상현실 참여자에게 실제와 유사한 실감적인 가상현실 체험을 제공하기 위해서는 실제 현실 공간에 존재하는 환경 및 객체의 정보를 정밀하게 캡처 및 복원하여 가상 환경 시스템의 모델 데이터로 적용한 시스템 구성이 필요하다. 이러한 가상 환경 구성에 필요한 실 데이터를 획득하기 위해서는 다수의 비정형 카메라를 활용한 셋업으로 이루어진다. 하지만, 다수의 비정형 위치의 카메라를 활용해 실제 공간에서의 3차원으로 구성된 정보를 획득할 경우 카메라의 개수 및 위치가 최적화되지 않아 복원의 오류가 발생할 수 있다. 또한, 정밀한 객체 복원을 위해 과도한 양의 비정형 카메라가 배치될 경우 비정형 카메라 배치에 따른 자원의 낭비 또한 발생할 수 있어 적절한 개수의 비정형 카메라가 배치되어야 한다. 본 논문에서는 3차원 공간 데이터를 복원 시 필요한 정보를 얻기 위해 배치되는 다수의 비정형 카메라를 최적화할 수 있는 최적 카메라 배치(Optimal Camera Placement) 학습 기법을 제안한다. 본 논문에서 제안한 방법을 통해 실제 환경 정보 획득 시 정확한 형태의 복원 데이터를 이용하여 가상 환경을 생성하고, 더욱 몰입도 높은 실감형 콘텐츠 시스템을 사용자에게 제공할 수 있다.

• 조명전기설비학회논문지
• /
• 제29권11호
• /
• pp.96-101
• /
• 2015

In recent years, researches regarding optimal placement of CCTV(Closed-circuit Television) cameras via architecture modeling has been conducted. However, for analyzing surveillance coverage through actual human movement, the application of VA(Video Analytics) function of IP(Internet Protocol) cameras has not been studied. This paper compares two methods using data captured from real-world cameras and data acquired from a virtual environment. In using real cameras, we develop GUI(Graphical User Interface) to be used as a logfile which is stored hourly and daily through VA functions and to be used commercially for placement of products inside a shop. The virtual environment was constructed to emulate an real world such as the building structure and the camera with its specifications. Moreover, suitable placement of the camera is done by recognizing obstacles and the number of people counted within the camera's range of view. This research aims to solve time and economic constraints of actual installation of surveillance cameras in real-world environment and to do feasibility study of virtual environment.

• 한국생산제조학회지
• /
• 제26권1호
• /
• pp.50-58
• /
• 2017

This paper proposes a real-time robotic vision control scheme using the weighting matrix to efficiently process the vision data obtained during robotic movement to a target. This scheme is based on the vision system model that can actively control the camera parameter and robotic position change over previous studies. The vision control algorithm involves parameter estimation, joint angle estimation, and weighting matrix models. To demonstrate the effectiveness of the proposed control scheme, this study is divided into two parts: not applying the weighting matrix and applying the weighting matrix to the vision data obtained while the camera is moving towards the target. Finally, the position accuracy of the two cases is compared by performing the slender bar placement task experimentally.

• Journal of Gynecologic Oncology
• /
• 제29권6호
• /
• pp.87.1-87.4
• /
• 2018

Objective: Upper paraaortic lymph node dissection (UPALD) to the infrarenal level is one of the most challenging robotic procedures. Because robotic system has the limitation in robotic arm mobility. This surgical video introduces a novel robotic approach, lower pelvic port placement (LP3), to perform optimally and simultaneously both UPALD and pelvic procedures in gynecologic cancer patients using da Vinci Xi system. Methods: The patient presented with high-grade endometrial cancer. She underwent robotic surgical staging operation. For the setup of the LP3, a line was drown between both anterior superior iliac spines. At 3 cm below this line, another line was drown and four robotic ports were placed on this line. Results: After paraaortic lymph node dissection (PALD) was completed, the boom of robotic system was rotated $180^{\circ}$ to retarget for the pelvic lateral displacement. Robotic ports were placed and docked again. The operation was completed robotically without any complication. Conclusion: The LP3 was feasible for performing simultaneously optimal PALD as well as procedures in pelvic cavity in gynecologic cancer patients. The advantage of LP3 technique is the robotic port placement that affords for multi-quadrant surgery, abdominal and pelvic dissection. The LP3 is facilitated by utilizing advanced technology of Xi system, including the patient clearance function, the rotating boom, and 'port hopping' that allows using every ports for a camera. The LP3 will enable surgeons to extend the surgical indication of robotic surgical system in the gynecologic oncologic field.

• 한국정보컨버전스학회:학술대회논문집
• /
• 한국정보컨버전스학회 2008년도 International conference on information convergence
• /
• pp.145-150
• /
• 2008

This thesis explores the problem of reconstructing a three-dimensional(3D) scene given a set of images or image sequences of the scene. It describes efficient methods for the 3D reconstruction of static and dynamic scenes from stereo images, stereo image sequences, and images captured from multiple viewpoints. Novel methods for image-based and volumetric modelling approaches to 3D reconstruction are presented, with an emphasis on the development of efficient algorithm which produce high quality and accurate reconstructions. For image-based 3D reconstruction a novel energy minimisation scheme, Iterated Dynamic Programming, is presented for the efficient computation of strong local minima of discontinuity preserving energyy functions. Coupled with a novel morphological decomposition method and subregioning schemes for the efficient computation of a narrowband matching cost volume. the minimisation framework is applied to solve problems in stereo matching, stereo-temporal reconstruction, motion estimation, 2D image registration and 3D image registration. This thesis establishes Iterated Dynamic Programming as an efficient and effective energy minimisation scheme suitable for computer vision problems which involve finding correspondences across images. For 3D reconstruction from multiple view images with arbitrary camera placement, a novel volumetric modelling technique, Embedded Voxel Colouring, is presented that efficiently embeds all reconstructions of a 3D scene into a single output in a single scan of the volumetric space under exact visibility. An adaptive thresholding framework is also introduced for the computation of the optimal set of thresholds to obtain high quality 3D reconstructions. This thesis establishes the Embedded Voxel Colouring framework as a fast, efficient and effective method for 3D reconstruction from multiple view images.

• International Journal of Internet, Broadcasting and Communication
• /
• 제9권3호
• /
• pp.1-8
• /
• 2017

Recently, the development of the head mounted display (HMD) device has attracted a great deal of attention to the actual contents. Especially, Augmented Reality (AR), which is a mixture of actual information and virtual world information, is focused on. AR HMD is able to interact by arranging virtual objects in real space through spatial recognition using depth camera. In order to naturally mix virtual space with real space, it is necessary to develop a technology for realizing spatial mapping information with high accuracy. The purpose of this paper is to evaluate the optimal configuration of augmented reality application program by realizing accurate spatial mapping information when mapping a real space and an object placement environment using HoloLens. To do this, we changed the spatial mapping information in real space to three levels, which are the number of meshes used in cubic meters to scan step by step. After that, it was compared with the 3D model obtained by changing the actual space and mesh number. Experimental result shows that the higher the number of meshes used in cubic meters, the higher the accuracy between real space and spatial mapping. This paper is expected to be applied to augmented reality application programs that require scanning of highly mapped spatial mapping information.