|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Markerless human motion capture by Markov random field and dynamic graph cuts with color constraints显示文摘Currently,many vision-based motion capture systems require passive markers attached to key loca-tions on the human body. However,such systems are intrusive with limited application. The algorithm that we use for human motion capture in this paper is based on Markov random field (MRF) and dynamic graph cuts. It takes full account of the impact of 3D reconstruction error and integrates human motion capture and 3D reconstruction into MRF-MAP framework. For more accurate and robust performance,we extend our algorithm by incorporating color constraints into the pose estimation process. The ad-vantages of incorporating color constraints are demonstrated by experimental results on several video sequences. | LI Jia WAN ChengKai ZHANG DianYong MIAO ZhenJiang YUAN BaoZong | 2009 | Science in China(Series F)2009，52，2： | 2 |
| 2 | A moving object segmentation algorithm for static camera via active contours and GMM显示文摘Moving object segmentation is one of the most challenging issues in computer vision. In this paper,we propose a new algorithm for static camera foreground segmentation. It combines Gaussian mix-ture model (GMM) and active contours method,and produces much better results than conventional background subtraction methods. It formulates foreground segmentation as an energy minimization problem and minimizes the energy function using curve evolution method. Our algorithm integrates the GMM background model,shadow elimination term and curve evolution edge stopping term into energy function. It achieves more accurate segmentation than existing methods of the same type. Promising results on real images demonstrate the potential of the presented method. | WAN ChengKai YUAN BaoZong MIAO ZhenJiang | 2009 | Science in China(Series F)2009，52，2： | 2 |
| 3 | 2D-LDA:A statistical linear discriminant analysis for image matrix显示文摘 | Li Ming Yuan Baozong | 2005 | Pattern Recognition Letters2005，26，5： | 1 |
| 4 | Image compression using fractals and discrete cosine transform显示文摘 | Zhao Yao Yuan Baozong | 1994 | Electronics Letters1994，30，6： | 1 |
| 5 | 2D-LDA:A Statistical Linear Discriminant Analysis for Image Matrix显示文摘 | LIMing YUAN Baozong YUAN Baozong | | 0，，05： | 1 |
| 6 | 2DLDA:A statistical linear discriminant analy- sis for image matrix显示文摘 | Liming Yuan baozong | 2005 | Pattern Recognition Letters2005，26，5： | 1 |
| 7 | A novel approach forhuman face detection from color images under complexbackground显示文摘 | Wang Yangjiang Yuan Baozong | 2001 | Pattern Recognition2001，34，10： | 1 |
| 8 | A novel approach for human face detection from color images under complex background显示文摘 | Wang Yanjiang Yuan Baozong | 2001 | Pattern Recognition2001，34，： | 1 |
| 9 | A Novel Approach for Human Face Detection from Color Images under Complex Background显示文摘 | Yangjiang Wang Baozong Yuan | 2001 | Pattern Recognition2001，34，10： | 1 |
| 10 | Segmentation method for face detection in complex background显示文摘 | Wang Yanjiang Yuan Baozong | 2000 | Electronics Letters2000，36，3： | 1 |
| 11 | 2D-LDA : a statistical linear discrimi- nant analysis for image matrix 显示文摘 | Li Ming Yuan Baozong | 2005 | Pattern Recognition Let- ters2005，26，5： | 1 |
| 12 | 2D-LDA: A Statistical Linear Discri- minant Analysis for Image Matrix显示文摘 | Li Ming Yuan Baozong | 2005 | Pattern Recognition Letters2005，26，5： | 1 |
| 13 | A novel approach for human face detection from color images under complex background显示文摘 | Yangjiang Wang Baozong Yuan | 2001 | Pattern Recognition2001，34，： | 1 |
| 14 | FACE RECOGNITION USING TWO DIMENSIONAL LAPLACIAN EIGENMAP显示文摘Recently,some research efforts have shown that face images possibly reside on a nonlinear sub-manifold.Though Laplacianfaces method considered the manifold structures of the face images,it has limits to solve face recognition problem.This paper proposes a new feature extraction method,Two Dimensional Laplacian EigenMap(2DLEM),which especially considers the manifold structures of the face images,and extracts the proper features from face image matrix directly by using a linear transformation.As opposed to Laplacianfaces,2DLEM extracts features directly from 2D images without a vectorization preprocessing.To test 2DLEM and evaluate its performance,a series of ex-periments are performed on the ORL database and the Yale database.Moreover,several experiments are performed to compare the performance of three 2D methods.The experiments show that 2DLEM achieves the best performance. | Chen Jiangfeng Yuan Baozong Pei Bingnan | 2008 | Journal of Electronics(China)2008，25，5： | 1 |
| 15 | 2D-LDA: A statistical linear discriminant analysis for image matrix 显示文摘 | LIMING YUAN BAOZONG | 2005 | Pattern Recognition Letters2005，26，5： | 1 |
| 16 | A more efficient branch and bound algorithm for feature selection显示文摘 | YU Bin YUAN Baozong | | 0，，06： | 1 |
| 17 | A hybrid image compression scheme combining block-based fractal coding and DCT 显示文摘 | ZHAO Yao YUAN Baozong | 1996 | Signal Processing: Image Communieation1996，8，2： | 1 |
| 18 | 2D-LDA: A novel statistical linear discriminant analysis for image matrix 显示文摘 | LIMing YUAN Baozong | 2005 | Pattern Rec- ognition Letter2005，26，5： | 1 |
| 19 | 2D-LDA: A Statistical Linear Discriminant Analysis for Image Matrix显示文摘 | Li Ming Yuan Baozong | 2005 | Pattern Recognition Letters2005，26，5： | 1 |
| 20 | 2D-LDA:A statistical linear discriminant analysis for image matrix显示文摘 | Li Ming Yuan Baozong | 2005 | Pattern Recognition Letters2005，26，5： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员