TY - GEN
T1 - Dense structure-from-motion: an approach based on segment matching
AU - Ernst, F.
AU - Wilinski, P.
AU - Overveld, van, C.W.A.M.
PY - 2002
Y1 - 2002
N2 - For 3D video applications, dense depth maps are required. We present a segment-based structure-from-motion technique. After image segmentation, we estimate the motion of each segment. With knowledge of the camera motion, this can be translated into depth. The optimal depth is found by minimizing a suitable error norm, which can handle occlusions as well. This method combines the advantages of motion estimation on the one hand, and structure-from-motion algorithms on the other hand. The resulting depth maps are pixel-accurate due to the segmentation, and have a high accuracy: depth differences corresponding to motion differences of 1/8/sup th/ of a pixel can be recovered
AB - For 3D video applications, dense depth maps are required. We present a segment-based structure-from-motion technique. After image segmentation, we estimate the motion of each segment. With knowledge of the camera motion, this can be translated into depth. The optimal depth is found by minimizing a suitable error norm, which can handle occlusions as well. This method combines the advantages of motion estimation on the one hand, and structure-from-motion algorithms on the other hand. The resulting depth maps are pixel-accurate due to the segmentation, and have a high accuracy: depth differences corresponding to motion differences of 1/8/sup th/ of a pixel can be recovered
M3 - Conference contribution
SN - 3540437444
T3 - Lecture notes in computer science
SP - 217
EP - 231
BT - Computer Vision ECCV 2002. 7th European Conference on Computer Vision. Proceedings / Ed. Anders Heyden, Gunnar Sparr, Mads Nielsen, P. Johansen
PB - Springer
CY - Berlin, Germany
ER -