Depth from stereo is one of the most active research topics in computer vision. In this work, we present an efficient depth estimation algorithm suitable for real-time implementation on commodity PCs. The proposed algorithm is based on an MML correlation-based algorithm [R. Yang et al, 2003]. The original MML algorithm is not reliable to produce accurate depth estimation around areas of low texture complexity and depth discontinuities. We devise an effective and efficient method for background/foreground separation. By identifying background and foreground, we successfully improve the accuracy of the MML algorithm and obtain satisfactory experimental results.
A real-time multiresolutional stereo matching algorithm
IEEE International Conference on Image Processing 2005 ; 3 ; III-373
2005-01-01
450026 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A Real-Time Multiresolutional Stereo Matching Algorithm
British Library Conference Proceedings | 2005
|Object recognition by multiresolutional template matching [2606-29]
British Library Conference Proceedings | 1995
|Multiresolutional filtering using wavelet transform
IEEE | 1993
|Multiresolutional multiple-model target tracking
IEEE | 1994
|Planar Multiresolutional Antenna for Automotive Radar
British Library Conference Proceedings | 2001
|