• Cartoon and Animation Studies
• /
• s.41
• /
• pp.253-277
• /
• 2015

When was launched in 2014, it was immediately ranked 2nd in English gross sales record in the first half of 2014, attracting huge attention from avid game users. Colin Moriarty(2014) states that the worldwide popular game, , lies on the alternative history assumption, 'what if Nazi Germany won the second world war? In regard to this, this research addresses how the characteristics of alternative history was adopted and visually represented in FPS game trailer. In terms of research method, firstly, literatures will be reviewed about definition of alternative history and some of the previous examples where alternative history was applied in novels, films and games. Secondly, narrative composition of alternative history is categorized as three sequential phases, (1) borrowing real history material, (2) connection between real and fictional history and (3) reconstruction of history through reinterpretation. Thirdly, the live-action game trailer will be analysed by three sequential phases of narrative composition, and CG game character and background will be analysed by spatial background, characters and props. The phase of 'borrowing' has used the historic images related to the World War II, and the phase of "connection' has composited by "connection through circumstantial events". The phase of 'reconstruction' has unfolded its fictional narrative in the form of "limited fictional history" In addition to this, has constructed dystopia world through composing of historic images and CG characters by SF design. In the light of this, the narrative composition of alternative history successfully extends to game area.

• International Journal of Highway Engineering
• /
• v.10 no.2
• /
• pp.159-166
• /
• 2008

Video image processing systems (VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on a wide-area detection algorithm provide traffic parameters such as flow and velocity as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. However, unlike human vision, VIPS cameras have difficulty in recognizing vehicle movements over a detection zone longer than 100 meters. Over such a distance, the camera operators need to zoom in to recognize objects. As a result, vehicle tracking with a single camera is limited to detection zones under 100m. This paper develops a methodology capable of monitoring individual vehicle trajectories based on image processing. To improve traffic flow surveillance, a long distance tracking algorithm for use over 200m is developed with multi-closed circuit television (CCTV) cameras. The algorithm is capable of recognizing individual vehicle maneuvers and increasing the effectiveness of incident detection.

• Journal of Internet Computing and Services
• /
• v.10 no.6
• /
• pp.99-111
• /
• 2009

The result of Image segmentation, an indispensable process in image processing, significantly affects the analysis of an image. Despite the significance of image segmentation, it produces some problems when the variation of pixel values is large, or the boundary between background and an object is not clear. Also, these problems occur frequently when many objects in an image are placed very close by. In this paper, when the shape of objects in an image is circular, we proposed an algorithm which segment an each object in an image using the geometric characteristic of circular shape. The proposed algorithm is composed of 4 steps. First is the boundary edge extraction of whole object. Second step is to find the candidate points for further segmentation using the boundary edge in the first step. Calculating the representative circles using the candidate points is the third step. Final step is to draw the line connecting the overlapped points produced by the several erosions and dilations of the representative circles. To verify the efficiency of the proposed algorithm, the algorithm is compared with the three well-known cell segmentation algorithms. Comparison is conducted by the number of segmented region and the correctness of the inner segment line. As the result, the proposed algorithm is better than the well-known algorithms in both the number of segmented region and the correctness of the inner segment line by 16.7% and 21.8%, respectively.

• Journal of Advanced Navigation Technology
• /
• v.5 no.1
• /
• pp.26-36
• /
• 2001

One of the most important problems in time-varying image sequences is the automatic target tracking. This paper proposes a position prediction and tracking technique of moving object using fuzzy prediction. First, the object is segmented from background of the image using accumulative difference image technique. Then centroid of the segmented object is extracted by using the centroid method, and we propose to apply variable size searching window to the object in order to increase the tracking performance. Also, non-linear prediction is required for efficient object tracking. Therefore, in this paper, fuzzy prediction method is proposed for predicting the location of the moving object at next frame. An experimental result shows that the proposed fuzzy prediction system tracks the moving object in stable under various conditions.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.2
• /
• pp.88-94
• /
• 2003

In this paper, we propose a hierarchical triangular mesh generation method based on the motion information and a fast rude convergence method. From the variance of Image difference we decide the region that subdivision is required and perform the adequate triangulation method that is possible to yield a successive hierarchical triangulation. For fast node convergence, in initial search, we use the refinement method that separate the backgroung and object region and maintain the mesh connection by using the bilinear interpolation. The simulation result demonstrate that proposed triangulation method have performance in PSNR than the conventional BMA or order mesh based method and refinement is appropriate for the case of the mesh size is small.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.137-140
• /
• 2009

본 논문에서는 Spatial Edge와 Temporal Edge를 이용한 이동 객체의 윤곽선 검출 방법을 제안한다. 카메라로부터 연속적으로 입력되는 영상에서 이동 객체의 윤곽선이 존재하는 후보 영역을 검출하기 위해, 새로운 방법의 Temporal Edge를 제안한다. Temporal Edge를 통해 검출된 후보 영역을 중심으로 Spatial Edge를 구하고, 후처리 과정을 통해 노이즈를 제거한 후 최종적으로 이동 객체의 윤곽선을 검출한다. 제안한 방법은 실험을 통해 그 성능을 확인하였고, 배경 차 방법과 비교 하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.532-534
• /
• 2001

본 논문에서는 다양한 배경을 가지는 얼굴 영상에서 눈의 위치를 추출하고 누의 개폐 상태를 인식하는 방법에 대하여 제시한다. 얼굴 요소 중에서 눈은 얼굴 인식 분야에 있어서 주요한 특징을 나타내는 주 요소이며, 눈의 개폐 상태 인식은 인간의 물리적, 생체적 신호 감지 및 표정인식에도 유용하게 사용될 수 있다. 본 논문에서는 후부영역을 강조하기 위한 전처리 과정을 수행하고 템플릿 매칭 방법을 사용하여 후부 영역을 추출한다. 추출된 1차 후부 영역들은 설정된 병합식을 사용하여 병합되며, 기하학적 사전지식과 Matching Value를 기반으로 최종 눈후보 영역을 추출한다. 검출된 눈 후보 영역은 검출영역 전처리와 특징점 산출 과정을 거쳐 최종적으로 개폐 판별식을 통해 눈의 개폐상태를 인식하게 된다. 제안한 방법은 눈위치 추출과 개폐인식에서 모두 높은 인식률을 보였으며 향후 운전자의 졸음인식 및 환자 감시장치 등 여러 응용에서 사용될 수 있다.

• Electronics and Telecommunications Trends
• /
• v.20 no.4 s.94
• /
• pp.16-28
• /
• 2005

최근 컴퓨터비전 기술을 이용하는 새로운 패러다임의 마커프리 모션캡처 기술이 미국의 MIT, CMU, MS, 일본의 ATR, MERL, 영국의 Oxford 대학 등에서 개발되고 있다. 마커프리 모션캡처는 연기자의 몸에 마커나 센서를 부착하지 않으며 특별한 조명이 필요 없으므로, 애니메이션 제작뿐만 아니라 일반인을 대상으로 하는 동작 인터페이스분야로의 확대 적용이 가능한 모션캡처 방식이다. ETRI에서는 여러 응용 분야에 모션인터페이스로 활용할 수 있는 환경 변화에 강인한 마커프리 모션캡처 시스템을 개발하고 있다. 몸에 마커나 센서를 부착하지 않은 자유 복장 상태의 동작자에 대해 조명 조건 변화 및 배경 변화에 강건하게 실시간 모션캡처 할 수 있는 기술 개발을 목표로 한다. 본 연구 개발이 성공한다면, 2007년에 876억 달러 규모로 확대될 전망인 영화, 방송물, 게임 등을 포함한 세계 영상 콘텐츠 시장에서 핵심 요소 기술 역할을 할 것이다. 그리고, 차세대 3D OS에서는 직관적 3D 포인팅 수단으로 활용될 수 있을 것이며, 2004년에 18,600만 대가 출고된 PC 시장을 고려하면 폭발적 수요가 예측된다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.243-249
• /
• 2013

In waste repository environment, we can process the waste history efficiently for reuse by recording the history trajectory of the vehicle which loaded waste and the dumping position of the waste vehicle. By mapping the unloaded waste to 3D and by extracting the dumping point, a new method was implemented so as to record the final dumping position and the waste content under various experiments. In this paper, we developed the algorithm which tracking the vehicle and deciding the moment of dumping in landfills. We first trace the position of vehicle using the difference image between current image and background image and then we decide the stop point from the shape of vehicle route and detect the dumping point by comparing the dumping image with the image that vehicle is stopping. From the camera parameters, The transform method between screen coordinate and real coordinate of landfills is proposed.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.1-10
• /
• 2018

Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology to a livestock management system to minimize the damage resulting from such anomalies. Nonetheless, detecting each pig in a crowed pigsty is still challenging problem. In this paper, we propose a new Kinect camera and deep learning-based monitoring system for the detection of the individual pigs. The proposed system is characterized as follows. 1) The background subtraction method and depth-threshold are used to detect only standing-pigs in the Kinect-depth image. 2) The standing-pigs are detected by using YOLO (You Only Look Once) which is the fastest and most accurate model in deep learning algorithms. Our experimental results show that this method is effective for detecting individual pigs in real time in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (average 99.40% detection accuracies).