Title :
Spatial-Temporal Fusion for High Accuracy Depth Maps Using Dynamic MRFs
Author :
Zhu, Jiejie ; Wang, Liang ; Gao, Jizhou ; Yang, Ruigang
Author_Institution :
Comput. Sci. Dept., Univ. of Central Florida, Orlando, FL, USA
fDate :
5/1/2010 12:00:00 AM
Abstract :
Time-of-flight range sensors and passive stereo have complimentary characteristics in nature. To fuse them to get high accuracy depth maps varying over time, we extend traditional spatial MRFs to dynamic MRFs with temporal coherence. This new model allows both the spatial and the temporal relationship to be propagated in local neighbors. By efficiently finding a maximum of the posterior probability using Loopy Belief Propagation, we show that our approach leads to improved accuracy and robustness of depth estimates for dynamic scenes.
Keywords :
Markov processes; image sensors; probability; sensor fusion; stereo image processing; Loopy belief propagation; Markov random field; high accuracy depth maps; passive stereo; posterior probability; spatial-temporal fusion; time-of-flight range sensors; Cameras; Fuses; Fusion power generation; Intelligent sensors; Layout; Robustness; Sensor fusion; Sensor systems; Signal to noise ratio; Stereo vision; MRFs; Stereo; data fusion; global optimization.; time-of-flight sensor; Algorithms; Artificial Intelligence; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Photogrammetry; Reproducibility of Results; Sensitivity and Specificity;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2009.68