Video SnapCut: robust video object cutout using localized classifiers
ACM SIGGRAPH 2009 papers
Object motion detection using information theoretic spatio-temporal saliency
Pattern Recognition
Articulated object tracking by rendering consistent appearance parts
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Multimedia Tools and Applications
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Segmenting and tracking multiple objects under occlusion using multi-label graph cut
Computers and Electrical Engineering
Robust bilayer video segmentation by adaptive propagation of global shape and local appearance
Journal of Visual Communication and Image Representation
Object tracking and segmentation in a closed loop
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I
Automatic Real-Time Video Matting Using Time-of-Flight Camera and Multichannel Poisson Equations
International Journal of Computer Vision
Pattern Recognition Letters
A clustering based feature selection method in spectro-temporal domain for speech recognition
Engineering Applications of Artificial Intelligence
Foreground objects segmentation for moving camera scenarios based on SCGMM
MUSCLE'11 Proceedings of the 2011 international conference on Computational Intelligence for Multimedia Understanding
Foreground segmentation for interactive displays
Proceedings of the 27th Conference on Image and Vision Computing New Zealand
Integrating tracking with fine object segmentation
Image and Vision Computing
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
This paper presents a new approach to segmenting monocular videos captured by static or hand-held cameras filming large moving non-rigid foreground objects. The foreground and background objects are modeled using spatialcolor Gaussian mixture models (SCGMM), and segmented using the graph cut algorithm, which minimizes a Markov random field energy function containing the SCGMM models. In view of the existence of a modeling gap between the available SCGMMs and segmentation task of a new frame, one major contribution of our paper is the introduction of a novel foreground/background SCGMM joint tracking algorithm to bridge this space, which greatly improves the segmentation performance in case of complex or rapid motion. Specifically, we propose to combine the two SCGMMs into a generative model of the whole image, and maximize the joint data likelihood using a constrained Expectation- Maximization (EM) algorithm. The effectiveness of the proposed algorithm is demonstrated on a variety of sequences.