TY - GEN
T1 - 3D dynamic reconstruction of rigid object using space-time correlation in multi-view
AU - Xiuxiu, Li
AU - Jiangbin, Zheng
AU - Yanning, Zhang
AU - Ning, Chen
PY - 2012
Y1 - 2012
N2 - A three dimensional (3D) dynamic reconstruction algorithm for rigid objects in multiview is presented. In this algorithm, the space-time correlation is utilized to fill larger holes due to the insufficiency of viewpoints. For this purpose, firstly, an improved generalized voxel coloring GVC is used to reconstruct the initial 3D shape using the frame images in multiview at different time based on the color constraints, and a new voxel space can be obtained; secondly, the space-time correlation between obtained voxel spaces is calculated at different time using the features motion parameters and iterative closest points; finally, the dynamic reconstruction is implemented by combining the obtained voxel space of the previous frame and the current frame images using the space-time correlation. Owing to the space-time correlation, all information of frame images can be combined to reconstruct the 3D shape of an object, and most holes are filled. Experiments are given to demonstrate the efficiency of this reconstruction algorithm.
AB - A three dimensional (3D) dynamic reconstruction algorithm for rigid objects in multiview is presented. In this algorithm, the space-time correlation is utilized to fill larger holes due to the insufficiency of viewpoints. For this purpose, firstly, an improved generalized voxel coloring GVC is used to reconstruct the initial 3D shape using the frame images in multiview at different time based on the color constraints, and a new voxel space can be obtained; secondly, the space-time correlation between obtained voxel spaces is calculated at different time using the features motion parameters and iterative closest points; finally, the dynamic reconstruction is implemented by combining the obtained voxel space of the previous frame and the current frame images using the space-time correlation. Owing to the space-time correlation, all information of frame images can be combined to reconstruct the 3D shape of an object, and most holes are filled. Experiments are given to demonstrate the efficiency of this reconstruction algorithm.
KW - A multi-view system
KW - Dynamic 3D reconstruction
KW - Hole-filling
KW - Space-time correlation
UR - https://www.scopus.com/pages/publications/84855709338
U2 - 10.1007/978-94-007-2169-2_97
DO - 10.1007/978-94-007-2169-2_97
M3 - 会议稿件
AN - SCOPUS:84855709338
SN - 9789400721685
T3 - Lecture Notes in Electrical Engineering
SP - 813
EP - 821
BT - Green Communications and Networks - Proceedings of the International Conference on Green Communications and Networks, GCN 2011
T2 - International Conference on Green Communications and Networks, GCN 2011
Y2 - 15 July 2011 through 17 July 2011
ER -