• 한국공간정보시스템학회:학술대회논문집
• /
• 1999.06a
• /
• pp.217-228
• /
• 1999

최근 범국가적인 GIS구축사업을 위한 효율적인 지형공간정보취득기법에 대한 요구가 날로 증가하고 있다. 이는 HW, SW 및 데이터로 구성되는 GIS구축에서 지형자료가 차지하는 비중과 이의 취득에 필요한 노력이 매우 중요함을 반증하고 있다. 이에 부응하여 국내에서도 재래식측량기법의 자동화/현대화에서부터 GPS측량기술의 도입, Airborne-항공사진측량기법의 개발 및 고해상도위성영상의 활용방안에 이르기까지 새로운 측량기술에 대한 다양한 연구와 기술축적을 서두르고 있는 실정이다. 그러나 위의 어떠한 측량기법도 단독으로는 정확도, 신속성, 경제성, 현재성 등 GIS 자료취득의 모든 요구조건을 만족하는 Total Solution이 되지 못하고 있다. 따라서 본 연구에서는 매핑과 GIS-자료취득에 활용되고 있는 여러 가지 항공측량기술의 현황과 장단점을 살펴보았다. 또한 위성에 의한 위치결정시스템인 GPS와 관성항행장치인 INS를 결합하여 항공측량 분야에 필요한 센서의 위치와 회전각을 결정하므로서 시너지(Synergy)효과를 높이는 기법을 소개한다.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2009.04a
• /
• pp.91-94
• /
• 2009

The Aerial photographic mission is working of taking picture at appropriate point at operating aircraft. Specially, because multi-looking camera system for 3D spatial data construction don't use large size CCD camera, do use middle size or small size CCD camera, Exterior parameter can't be calculated because of not enough overlap, if taking picture at inappropriate position. Therefore, we can construct 3D spatial modeling data by taking picture at planned points using GPS Positioning information

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.154-162
• /
• 2012

Facial expression and gesture of the actors can be magnified or understated depending on the size of the camera framing. The direction, quality, and quantity of the lighting can also make the actors look different. That's why we have to deliberate how to photograph the actors who will be projected on the screen. This thesis shows the way of improving performance and emphasizing each character with camera and lighting. You will also find out how visual elements influence the actors and their performances.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.899-902
• /
• 2004

얼굴인식의 신뢰도를 높이기 위하여 현재 입력되어지는 상황정보를 활용하여 현 상황에 맞도록 구성된 처리를 수행하는 방법을 연구한다. 사용자로부터 획득된 조명, 포즈, 표정등의 상황정보를 바탕으로 수행하기위한 순서 및 파라메터 값들을 학습을 통하여 구성하며, 해당 Data는 Knowledge Base를 구성하며, 추후 추가되는 상황정보를 받아들일 수 있도록 구성한다. 상황 정보를 추출하여 얼굴인식에 활용하게 된다면, 현재 얼굴인식 및 영상정보를 활용하여 인식을 수행하는 모든 요소에서 사용자에게 실뢰성 있는 결과를 제공할 수 있을 것이다. 또한 본 논문에서는 조명 환경을 9개의 상태로 구분하고 이를 검출하는 상황판단을 실험하였으며, 구성한 조명상황을 정확히 추출하는 실험결과를 도출하였다.

• 한국정보통신설비학회:학술대회논문집
• /
• 2008.08a
• /
• pp.478-481
• /
• 2008

오늘날 비즈니스의 글로벌화, 사업장의 분산화는 필연적으로 영상회의의 활성화를 가져왔으나, 기 구축된 SD(Standard Definition)급 화질의 영상회의는 실감성 및 장시간 사용시 피로감 등에 따른 이용율 저조로 기대 만큼의 성화를 이루지 못하였다. 또한 기존 영상회의 시스템에서의 dec는 보조적 채널, 시스템 조작과 운영의 복잡성, 낮은 해상도로 인한 표정 및 눈짓 등의 요소 포착이 어려운 한계를 극복하지 못하였고, 기업들은 기업 내부 및 국내외 타기업들과의 협업을 위해 막대한 비용과 시간이 요구되고 있는 실정이다. KT는 기존 영상회의 문제 극복을 위해 서울<->대전 연구소간 전용선 연결, 비용 및 여러 site 확장을 위한 VPN으로의 전환 방안등 최상의 영상회의 구축을 위한 검토를 통해 Full HD실감 화질의 영상회의를 구축하였으며, 향후에는 Full HD 데이터 압축 기술 향상 및 데이터 전송 방안에 대한 더 많은 연구가 필요하다고 판단된다. 본 고에서는 KT에서 구축한 영상회의 사례를 중심으로 기본적인 기술과 구조, 국내외 시장의 현황 및 활용 방안에 대해 논하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.244-247
• /
• 2018

본 논문에서는 시니어를 위한 라이프 데이터 수집 및 행동분석 프레임 워크를 설명하고, 이의 부분적 구현을 자세히 설명한다. 본 연구는 시니어를 위한 라이프 데이터를 바탕으로 보호자가 없는 시니어를 보살핌과 동시에, 보호자가 미처 인지하지 못하는 시니어의 비정상적인 상태를 분석하여 판단하는 시스템을 연구한다. 먼저, 시니어가 시간을 많이 소요하는 TV 앞 상황을 가정하고, 방영되는 TV 콘텐츠와 TV 카메라를 이용한 시니어의 영상/음성 정보로 이상상태와 감정상태, TV 콘텐츠에 대한 반응과 반응속도를 체크한다. 구체적으로는 딥 러닝 기반의 API 와 멀티미디어 데이터 분석에서 사용되는 오픈 패키지를 바탕으로, 영상/음성의 키 프레임을 추출하여 감정 및 분위기를 분석하고 시니어의 얼굴 표정 인식, 행동 인식, 음성 인식을 수행한다.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.773-779
• /
• 2003

Locating exact position of facial components is a key preprocessing for realizing highly accurate and reliable face recognition schemes. In this paper, we propose a simple but powerful method for detecting isolated facial components such as eyebrows, eyes, and a mouth, which are horizontally oriented and have relatively dark gray levels. The method is based on the shape-resolving locally optimum thresholding that may guarantee isolated detection of each component. We show that pure facial regions can be determined by grouping facial features satisfying simple geometric constraints on unique facial structure. In the test for over 1000 images in the AR -face database, pure facial regions were detected correctly for each face image without wearing glasses. Very few errors occurred in the face images wearing glasses with a thick frame because of the occluded eyebrow -pairs. The proposed scheme may be best suited for the later stage of classification using either the mappings or a template matching, because of its capability of handling rotational and translational variations.

• Korean Journal of Remote Sensing
• /
• v.17 no.1
• /
• pp.33-44
• /
• 2001

The paper presents several satellite models and satellite image decomposition methods for inaccessible area where ground control points can hardly acquired in conventional ways. First, 10 different satellite sensor models, which were extended from collinearity condition equations, were developed and then behavior of each sensor model was investigated. Secondly, satellite images were decomposed and also pseudo images were generated. The satellite sensor model extended from collinearity equations was represented by the six exterior orientation parameters in $1^{st}$, $2^{nd}$ and $3^{rd}$ order function of satellite image row. Among them, the rotational angle parameters such as $\omega$(omega) and $\Phi$(phi) correlated highly with positional parameters could be assigned to constant values. For inaccessible area, satellite images were decomposed, which means that two consecutive images were combined as one image, The combined image consists of one satellite image with ground control points and the other without ground control points. In addition, a pseudo image which is an imaginary image, was prepared from one satellite image with ground control points and the other without ground control points. In other words, the pseudo image is an arbitrary image bridging two consecutive images. For the experiments, SPOT satellite images exposed to the similar area in different pass were used. Conclusively, it was found that 10 different satellite sensor models and 5 different decomposed methods delivered different levels of accuracy. Among them, the satellite camera model with 1st order function of image row for positional orientation parameters and rotational angle parameter of kappa, and constant rotational angle parameter omega and phi provided the best 60m maximum error at check point with pseudo images arrangement.

• Korean Journal of Remote Sensing
• /
• v.33 no.2
• /
• pp.231-242
• /
• 2017

Monitoring of facilities such as roads, dams and bridges is important for their long-term sustainable usage. It has usually suffered with safety and cost problems, which makes more frequent monitoring difficult. As an efficient and economicalsolution to these problems, one may consider the use of smartphone to capture the status of the facilities. To derive quantitative analysis results with the smartphone images for facility monitoring, one should first rectify the images in a way as automatic and economical as possible. In thisstudy, we propose such a rectification method, which rectifiessmartphone images acquired from arbitrary locations based on reference images.In the proposed method, we determine the camera extrinsic parameters of each smartphone images using the reference imagesrather than ground control points, and project the image to the target surface of the facility based on the determined camera parameters. The method were applied to test data acquired from a small dam toward water-area facility monitoring. The experimental results showed that the camera extrinsic parameters were determined with the accuracy of 5 cm and $0.28^{\circ}$ in the position and attitude. The accuracy of the distance measured from the rectified image was evaluated to 10 cm. With the rectified images, one can accurately determine the location and length of the target objects required for facility monitoring.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.895-905
• /
• 2019

Commercial Unmanned Aerial Vehicle (UAV) image processing software products currently used in the industry provides camera calibration information and block bundle adjustment accuracy. However, they provide mapping accuracy achievable out of input UAV images. In this paper, the quality of mapping is calculated by using orientation parameters from UAV image processing software. We apply the orientation parameters to the digital photogrammetric workstation (DPW) for verifying the reliability of the mapping quality calculated. The quality of mapping accuracy was defined as three types of accuracy: Y-parallax, relative model and absolute model accuracy. The Y-parallax is an accuracy capable of determining stereo viewing between stereo pairs. The Relative model accuracy is the relative bundle adjustment accuracy between stereo pairs on the model coordinates system. The absolute model accuracy is the bundle adjustment accuracy on the absolute coordinate system. For the experimental data, we used 723 images of GSD 5 cm obtained from the rotary wing UAV over an urban area and analyzed the accuracy of mapping quality. The quality of the relative model accuracy predicted by the proposed technique and the maximum error observed from the DPW showed precise results with less than 0.11 m. Similarly, the maximum error of the absolute model accuracy predicted by the proposed technique was less than 0.16 m.