• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.171-182
• /
• 2007

We propose a simple method for tracking a nonparameterized subject contour in a single video stream with a moving camera and changing background. Then we present a method to eliminate the tracked contour object by replacing with the background scene we get from other frame. First we track the object using LOD (Level-of-Detail) canny edge maps, then we generate background of each image frame and replace the tracked object in a scene by a background image from other frame that is not occluded by the tracked object. Our tracking method is based on level-of-detail (LOD) modified Canny edge maps and graph-based routing operations on the LOD maps. We get more edge pixels along LOD hierarchy. Our accurate tracking is based on reducing effects from irrelevant edges by selecting the stronger edge pixels, thereby relying on the current frame edge pixel as much as possible. The first frame background scene is determined by camera motion, camera movement between two image frames, and other background scenes are computed from the previous background scenes. The computed background scenes are used to eliminate the tracked object from the scene. In order to remove the tracked object, we generate approximated background for the first frame. Background images for subsequent frames are based on the first frame background or previous frame images. This approach is based on computing camera motion. Our experimental results show that our method works nice for moderate camera movement with small object shape changes.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.74-86
• /
• 2006

This paper proposes a robust and computationally efficient algorithm for automatic video object segmentation. For implementing the spatio-temporal segmentation, which aims for efficient combination of the motion segmentation and the color segmentation, an SOM-based hierarchical clustering method in which the segmentation process is regarded as clustering of feature vectors is employed. As results, problems of high computational complexity which required for obtaining exact segmentation results in conventional video object segmentation methods, and the performance degradation due to noise are significantly reduced. A measure of motion vector reliability which employs MRF-based MAP estimation scheme has been introduced to minimize the influence from the motion estimation error. In addition, a noise elimination scheme based on the motion reliability histogram and a clustering validity index for automatically identifying the number of objects in the scene have been applied. A cross projection method for effective object tracking and a dynamic memory to maintain temporal coherency have been introduced as well. A set of experiments has been conducted over several video sequences to evaluate the proposed algorithm, and the efficiency in terms of computational complexity, robustness from noise, and higher segmentation accuracy of the proposed algorithm have been proved.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Journal of Computing Science and Engineering
• /
• v.2 no.1
• /
• pp.98-108
• /
• 2008

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a novel framework for generating the geometry of landscapes from extremely noisy point cloud datasets obtained via limited resolution techniques, particularly optical flow based vision algorithms applied to live-action video plates. Our contribution is a new statistical approach to remove erroneous tracks ('outliers') by employing a unique combination of well established techniques-including Gaussian Mixture Models (GMMs) for robust parameter estimation and Radial Basis Functions (REFs) for scattered data interpolation-to exploit the natural constraints of this problem. Our algorithm offsets the tremendously laborious task of modeling these landscapes by hand, automatically generating a visually consistent, camera position dependent, thin-shell surface mesh within seconds for a typical tracking shot.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.100-103
• /
• 2010

In this paper we propose a method of detecting moving object in H.264/AVC bitstream by representing the $4{\times}4$ block partition units as nodes of graph. By constructing hierarchical graph by taking into account the relation between nodes and the spatial-temporal relations between graphs in frames, we are able to track small objects, distinguish two occluded objects, and identify objects that move and stop alternatively.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.21-24
• /
• 2000

기체에 대한 영상처리 기술은 그 응용 분야가 매우 넓고, 그에 따른 산업적 · 경제적 중요성도 증가되게된다 한 예로서 자동으로 공장오염 감시나 산불감시등에 사용되는 영상기기에 곧바로 기체에 대한 영상처리 기술들이 필요하다. 그러나 기체는 고체와는 다른 다음과 같은 특성들을 가지고 있다. 첫째, 고체의 경우 물체의 경계선이 비교적 분명하지만, 기체의 경우 하나의 기체 내에서도 밀도 분포가 다르기 때문에 그 경계선에서도 밀도가 불규칙하여서 기체의 경계선을 정확히 정의하기 힘들다. 둘째, 기체 분석을 위한 영상들은 대체로 잡음이 많고, 기체의 크기에 비하여 해상도가 낮다. 따라서 기체 영상은 픽셀(Pixel) 단위로 분석 처리하기가 어렵다. 위와 같은 기체가 가지는 특성 때문에 고체에 대한 영상 처리 기술을 기체에 직접적으로 적용하기는 불가능하다. 본 연구에서는 화상 데이터에서 기체를 감지하여 추적하는 시스템을 개발하고자 한다.

• Electronics and Telecommunications Trends
• /
• v.31 no.3
• /
• pp.1-8
• /
• 2016

최근 개인화된 미디어의 출현과 더불어 방송통신 미디어 분야에서 개인별 맞춤형 방송 서비스에 대한 관심과 지원이 빠르게 확산되는 추세다. 특히, 다중 카메라를 이용한 관심 인물에 대한 다각도 영상과 같은 차별화된 영상을 제공하려는 수요가 꾸준히 증가하고 있다. 객체 중심의 영상을 생성하기 위한 관련 기술의 발전 및 수요 변화에 발맞춰 본고에서는 관련 기술의 개요 및 연구동향을 살펴보고, ETRI에서 개발 중인 객체 추적 기반의 다중 Pan-Tilt-Zoom(PTZ) 카메라 제어를 통한 객체 중심 다각도 영상 획득 기술을 소개하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.697-700
• /
• 2006

본 논문에서는 동작에 근거한 새로운 비디오 편집 방법을 제안한다. 강의 비디오에서 전자 슬라이드 내용을 자동으로 검출하고 비디오와 동기화한다. 각 동기화된 표제의 동작을 연속적으로 추적 및 인식한 후, 등록된 화면과 슬라이드에서 변환 내용을 찾아 동작이 일어 나는 영역을 확인한다. 인식된 동작과 등록된 지점에서 슬라이드의 정보를 추출하여 슬라이드 영역을 부분적으로 확대한다거나 원본 비디오를 자동으로 편집함으로써 비디오의 질을 향상 시킬 수가 있다. 2 개의 비디오 가지고 실험한 결과 각각 95.5, 96.4%의 동작 인식 결과를 얻을 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.300-301
• /
• 2016

본 논문에서는 동영상에서 제한된 종류의 동적 객체를 자동적으로 검출하여 추적하는 기법을 제안한다. 제안하는 기법은 객체 검출 기법[1]과 객체 추적 기법[2]의 협업을 통해 이를 수행한다. 검출기는 매 장면마다 객체들을 검출하고 이 중 높은 신뢰도의 객체에 대해 추적을 시작한다. 추적기는 이전 장면에서 학습된 분류기에 기반하여 객체를 추적한다. 추적 결과와 겹치는 검출 결과를 분석하여 현재 장면에서 객체의 정확한 위치와 모양을 추정한다. 겹치는 검출 결과가 없을 때는 검출기로 부터 추적 결과의 신뢰도를 측정하고 문턱값에 따라 추적을 계속 진행하거나 종료한다. 실험 결과를 통해 제안하는 기법이 기존 검출 기법에 비해 우수한 검출 성능을 보임을 확인한다.

• Journal of the Ergonomics Society of Korea
• /
• v.16 no.3
• /
• pp.71-75
• /
• 1997

This paper presents the development of videobased 3-dimensional tracking system. Measurement of human motion is important in the application of ertonomics. The system uses advanced direct video measurement technology. Passive retro-reflecting markers are attached to a subject and movements of markers are observed by two CCD cameras. Infrared light emitted near the CCD cameras is reflected by the markers and is detected by the cameras. The images are captured by Samsung MVB302 board and the centers of markers are calculated by DSP program. The positions of markers are transferred from MVB02 board to the computer through AT bus. The computer then tracks the position of each marker and saves the data. This system has dynamic accuracy with 0.7% average error and 4.2% maximum error, and the sampling rate to 6 .approx. 10 Hz, and this system can analyse the trajectory and speed of the marker. The results of this study can be used for operator's motion analysis, task analysis, and hand movement characteristic analysis.