Fundamentals of digital image processing
Fundamentals of digital image processing
A Kalman filter approach for accurate 3-D motion estimation from a sequence of stereo images
CVGIP: Image Understanding
A Two-Stage Algorithm for Discontinuity-Preserving Surface Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
3-D Kalman filter for image motion estimation
IEEE Transactions on Image Processing
Object-based coding of stereo image sequences using joint 3-D motion/disparity compensation
IEEE Transactions on Circuits and Systems for Video Technology
An object-based system for stereoscopic viewpoint synthesis
IEEE Transactions on Circuits and Systems for Video Technology
3-D model-based segmentation of videoconference image sequences
IEEE Transactions on Circuits and Systems for Video Technology
Group-Valued regularization framework for motion segmentation of dynamic non-rigid shapes
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Hi-index | 0.00 |
This paper describes a 3D model-based unsupervised procedure for the segmentation of multiview image sequences using multiple sources of information. Using multiview information a 3D model representation of the scene is constructed. The articulation procedure is based on the homogeneity of parameters, such as rigid 3D motion, color and depth, estimated for each sub-object, which consists of a number of interconnected triangles of the 3D model. The rigid 3D motion of each sub-object for subsequent frames is estimated using a Kalman filtering algorithm taking into account the temporal correlation between consecutive frames. Information from all cameras is combined during the formation of the equations for the rigid 3D motion parameters. The parameter estimation for each sub-object and the 3D model segmentation procedures are interleaved and repeated iteratively until a satisfactory object segmentation emerges. The performance of the resulting segmentation method is evaluated experimentally.