Dense Structure-from-Motion: An Approach Based on Segment Matching

Authors:
Fabian Ernst;Piotr Wilinski;Cornelius W. A. M. van Overveld
Affiliations:
-;-;-
Venue:
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Year:
2002

Citing 2
Cited 5

Multiple view geometry in computer vision

Multiple view geometry in computer vision
Hierarchical block matching for disparity estimation in stereo sequences

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol.2)-Volume 2 - Volume 2

Stereo matching using iterative reliable disparity map expansion in the color-spatial-disparity space

Pattern Recognition
Video object segmentation and tracking using region-based statistics

Image Communication
Stereo vision using two PTZ cameras

Computer Vision and Image Understanding
Occlusion boundary detection using pseudo-depth

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Stereo matching using iterated graph cuts and mean shift filtering

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

For 3-D 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 1/8th of a pixel can be recovered.