• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.399-409
• /
• 2019

Three-dimensional (3D) human pose reconstruction from single-view image is a difficult and challenging topic. Existing approaches mostly process frame-by-frame independently while inter-frames are highly correlated in a sequence. In contrast, we introduce a novel spatial-temporal 3D human pose reconstruction framework that leverages both intra and inter-frame relationships in consecutive 2D pose sequences. Orthogonal matching pursuit (OMP) algorithm, pre-trained pose-angle limits and temporal models have been implemented. Several quantitative comparisons between our proposed framework and recent works have been studied on CMU motion capture dataset and Vietnamese traditional dance sequences. Our framework outperforms others by 10% lower of Euclidean reconstruction error and more robust against Gaussian noise. Additionally, it is also important to mention that our reconstructed 3D pose sequences are more natural and smoother than others.

• 한국통신학회논문지
• /
• 제35권12C호
• /
• pp.984-994
• /
• 2010

Pose variation is a critical problem in face recognition. Three-dimensional(3D) face recognition techniques have been proposed, as 3D data contains depth information that may allow problems of pose variation to be handled more effectively than with 2D face recognition methods. This paper proposes a pose-normalized 3D face modeling method that translates and rotates any pose angle to a frontal pose using a plane fitting method by Singular Value Decomposition(SVD). First, we reconstruct 3D face data with stereo vision method. Second, nose peak point is estimated by depth information and then the angle of pose is estimated by a facial plane fitting algorithm using four facial features. Next, using the estimated pose angle, the 3D face is translated and rotated to a frontal pose. To demonstrate the effectiveness of the proposed method, we designed 2D and 3D face recognition experiments. The experimental results show that the performance of the normalized 3D face recognition method is superior to that of an un-normalized 3D face recognition method for overcoming the problems of pose variation.

• 한국지능시스템학회논문지
• /
• 제22권6호
• /
• pp.748-753
• /
• 2012

본 논문에서는 최적 pRBFNNs 패턴분류기 기반 3차원 스캐너를 이용한 얼굴인식 알고리즘을 설계한다. 일반적으로 2차원 영상을 이용한 얼굴인식 시스템은 사진의 명암도를 이용하여 얼굴의 특징을 추출하게 된다. 그렇기 때문에 빛이나 조명, 또는 얼굴 포즈와 같은 환경 변화들은 시스템의 성능을 저하시킨다. 따라서 본 논문에서 제안된 얼굴인식 알고리즘은 2차원 얼굴인식 시스템의 한계를 극복하기 위하여 3차원 스캐너를 사용하여 설계한다. 먼저 3차원 스캐너를 이용하여 얼굴 형상을 스캔하고 스캔된 얼굴 형상은 포즈 보상 과정을 통하여 정면으로 변환된다. 그 후에 Point Signature 기법을 사용하여 얼굴의 깊이 정보를 추출하고 마지막으로 고차원 패턴인식 문제에 대한 해결을 위하여 최적화된 pRBFNNs (Polynomial-based Radial Basis Function Neural Networks) 모델을 사용하여 인식성능을 확인한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2000-2003
• /
• 2003

This paper presents a three-dimensional (3D) head pose estimation algorithm for robust face recognition. Given a 3D input image, we automatically extract several important 3D facial feature points based on the facial geometry. To estimate 3D head pose accurately, we propose an Error Compensated-SVD (EC-SVD) algorithm. We estimate the initial 3D head pose of an input image using Singular Value Decomposition (SVD) method, and then perform a Pose refinement procedure in the normalized face space to compensate for the error for each axis. Experimental results show that the proposed method is capable of estimating pose accurately, therefore suitable for 3D face recognition.

• 전기학회논문지
• /
• 제59권2호
• /
• pp.429-435
• /
• 2010

Three dimensional (3-D) object detection and pose estimation from a single view query image has been an important issue in various fields such as medical applications, robot vision, and manufacturing automation. However, most of the existing methods are not appropriate in a real time environment since object detection and pose estimation requires extensive information and computation. In this paper, we present a fast 3-D object detection and pose estimation scheme based on surrounding camera view-changed images of objects. Our scheme has two parts. First, we detect images similar to the query image from the database based on the shape feature, and calculate candidate poses. Second, we perform accurate pose estimation for the candidate poses using the scale invariant feature transform (SIFT) method. We earned out extensive experiments on our prototype system and achieved excellent performance, and we report some of the results.

• 한국차세대컴퓨팅학회논문지
• /
• 제15권5호
• /
• pp.31-42
• /
• 2019

최근 딥러닝 기술이 발전함에 따라 많은 컴퓨터 비전 연구 분야에서 주목할 만한 성과들이 지속적으로 나오고 있다. 단일 이미지를 기반으로 사람의 2차원 및 3차원 포즈를 추정하는 연구에서도 비약적인 성능향상을 보여주고 있으며, 많은 연구자들이 문제의 범위를 확장하며 활발한 연구 활동을 진행하고 있다. 사람의 포즈 추정은 다양한 응용 분야가 존재하고, 특히 이미지나 비디오 분석에서 사람의 포즈는 행동 및 상태, 의도 파악을 위한 핵심 요소가 되기 때문에 상당히 중요한 연구 분야이다. 이러한 배경에 따라 본 논문은 단일 이미지를 기반으로 한 사람의 포즈 추정 기술에 대한 연구 동향을 살펴보고자 한다. 강인하고 정확한 문제 해결을 위해 다양한 연구 활동 결과가 존재한다는 점에서 본 논문에서는 사람의 포즈 추정 연구를 2차원 및 3차원 포즈 추정에 대해서 나누어 살펴보고자 한다. 끝으로 연구에 필요한 데이터 세트 및 사람의 포즈 추정 기술을 적용하는 다양한 연구 사례를 살펴볼 것이다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1887-1890
• /
• 2003

This paper presents a three-dimensional (3D) head pose estimation algorithm using the stereo image. Given a pair of stereo image, we automatically extract several important facial feature points using the disparity map, the gabor filter and the canny edge detector. To detect the facial feature region , we propose a region dividing method using the disparity map. On the indoor head & shoulder stereo image, a face region has a larger disparity than a background. So we separate a face region from a background by a divergence of disparity. To estimate 3D head pose, we propose a 2D-3D Error Compensated-SVD (EC-SVD) algorithm. We estimate the 3D coordinates of the facial features using the correspondence of a stereo image. We can estimate the head pose of an input image using Error Compensated-SVD (EC-SVD) method. Experimental results show that the proposed method is capable of estimating pose accurately.

• 한국정밀공학회지
• /
• 제21권8호
• /
• pp.50-56
• /
• 2004

The directional ability of an automobile has an influence on driver directly, and hence it must be given most priority. Alignment factors of automobile such as the camber, caster and toe directly affect the directional ability of a vehicle. The above mentioned factors are determined by the pose of interlinks in the assembly of an automobile front chassis module. Measuring the position of center point of ball joints in the front lower arm is very difficult. A method to determine this position is suggested in this paper. Pose estimation for front chassis module and dimensional evaluation to find the rotational characteristics of front lower arm were developed based on fundamental geometric techniques. To interpret the inspection data obtained for front chassis module, 3-D best fit method is needed. The best fit method determines the relationship between the nominal design coordinate system and the corresponding feature coordinate system. The least squares method based on singular value decomposition is used in this paper.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.303-310
• /
• 2023

A single vision system limits the ability to accurately understand the spatial constraints and interactions between robots and dynamic workers caused by gantry robots and collaborative robots during production manufacturing. In this paper, we propose a 3D pose registration method for dynamic workers based on a multi-domain vision system for safety monitoring in manufacturing environments. This method uses OpenPose, a deep learning-based posture estimation model, to estimate the worker's dynamic two-dimensional posture in real-time and reconstruct it into three-dimensional coordinates. The 3D coordinates of the reconstructed multi-domain vision system were aligned using the ICP algorithm and then registered to a single 3D coordinate system. The proposed method showed effective performance in a manufacturing process environment with an average registration error of 0.0664 m and an average frame rate of 14.597 per second.

• 한국지능시스템학회논문지
• /
• 제23권6호
• /
• pp.539-544
• /
• 2013

본 논문에서는 다항식 기반 RBFNNs를 이용하여 3차원 얼굴인식 알고리즘을 설계하고 인식률을 산출하는 방법을 제시한다. 2차원 얼굴인식의 경우 얼굴 포즈, 조명 등과 같은 외부 환경에 의해 인식률이 저하된다. 이러한 단점을 보완하기 위해 3차원 영상을 획득하여 얼굴인식을 수행한다. 얼굴인식을 수행하기 전에 3D스캐너를 통해 얻은 얼굴영상의 포즈 보상을 실시하고 얼굴의 형상을 정면으로 향하게 한다. 그리고 Point Signature 기법을 이용하여 얼굴의 깊이 값을 추출하게 된다. 추출된 데이터는 고차원 데이터로서 학습 및 인식을 수행함에 있어 문제가 생길 수 있기 때문에 PCA알고리즘을 수행하여 차원을 축소한 데이터를 사용한다. 효율적인 학습을 위해 최적화 알고리즘을 통해 파라미터 최적화를 수행하며 PSO, DE, GA 알고리즘을 사용하여 인식 성능을 확인한다.