Title :
Surfaces with occlusions from layered stereo
Author :
Lin, Michael H. ; Tomasi, Carlo
Author_Institution :
Acuity Technol., Menlo Park, CA, USA
Abstract :
We propose a new binocular stereo algorithm that estimates scene structure as a collection of smooth surface patches. The disparities within each patch are modeled by a continuous-valued spline, while the extent of each patch is represented via a pixelwise partitioning of the images. Disparities and extents are alternately estimated in an iterative, energy minimization framework. Experimental results demonstrate that, for scenes consisting of smooth surfaces, the proposed algorithm significantly improves upon the state of the art.
Keywords :
image segmentation; iterative methods; minimisation; splines (mathematics); stereo image processing; binocular stereo algorithm; continuous valued spline; energy minimisation; image segmentation; images pixelwise partitioning; iterative methods; patch modelling; scene structure estimation; smooth surface patches; surface occlusions; Calibration; Costs; Iterative algorithms; Layout; Partitioning algorithms; Pixel; Spline; Stereo vision; Surface fitting; Surface treatment; Binocular stereo vision; boundary localization; energy minimization; graph cuts; hybrid system; quantitative comparison.; sharp discontinuities; smooth surfaces; surface fitting; Algorithms; Artificial Intelligence; Computer Graphics; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated; Photogrammetry; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2004.54
