To obtain an accurate 3 D object configuration from images,the essential perspective characteristics must be considered. Several new inverse transformation relations of the perspective image lines are given. Utiliz...To obtain an accurate 3 D object configuration from images,the essential perspective characteristics must be considered. Several new inverse transformation relations of the perspective image lines are given. Utilizing the analytic transformation relations, an optimization procedure for obtaining the unknown camera parameters of images is presented in this paper. A 3 D reproduction method and examples are introduced.展开更多
This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject...This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject to Poisson-Markov distribution, then constructing the projecting convex based on MAP. According to the characteristics of compressed video, two different convexes are constructed based on integrating the inter-frame and intra-frame information in the wavelet-domain. The results of the experiment demonstrate that the new method not only outperforms the traditional algorithms on the aspects of PSNR (Peak Signal-to-Noise Ratio), MSE (Mean Square Error) and reconstruction vision effect, but also has the advantages of rapid convergence and easy extension.展开更多
文摘To obtain an accurate 3 D object configuration from images,the essential perspective characteristics must be considered. Several new inverse transformation relations of the perspective image lines are given. Utilizing the analytic transformation relations, an optimization procedure for obtaining the unknown camera parameters of images is presented in this paper. A 3 D reproduction method and examples are introduced.
基金Supported by the Natural Science Foundation of Jiangsu Province (No. BK2004151).
文摘This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject to Poisson-Markov distribution, then constructing the projecting convex based on MAP. According to the characteristics of compressed video, two different convexes are constructed based on integrating the inter-frame and intra-frame information in the wavelet-domain. The results of the experiment demonstrate that the new method not only outperforms the traditional algorithms on the aspects of PSNR (Peak Signal-to-Noise Ratio), MSE (Mean Square Error) and reconstruction vision effect, but also has the advantages of rapid convergence and easy extension.
