Sequential robust direct motion estimation with equal projective basis

Authors:
Jong-Eun Ha;Dong-Joong Kang;Muh-Ho Jeong
Affiliations:
Tongmyong University of Information Technology;Tongmyong University of Information Technology;Korea Institute of Science and Technology
Venue:
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part I
Year:
2004

Citing 6
Cited 0

Visual reconstruction

Visual reconstruction
Compact Representations of Videos Through Dominant and Multiple Motion Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
On the unification of line processes, outlier rejection, and robust statistics with applications in early vision

International Journal of Computer Vision
Spline-Based Image Registration

International Journal of Computer Vision
What can be seen in three dimensions with an uncalibrated stereo rig

ECCV '92 Proceedings of the Second European Conference on Computer Vision
Self-Calibration and Metric Reconstruction in spite of Varying and Unknown Internal Camera Parameters

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents sequential robust direct motion estimation algorithm for the processing of uncalibrated dynamic image sequences. Through the propagation of the projective structures of the first two frames, we guarantee projective information under an equal basis. Since proposed algorithm yields projective information under equal basis, we could directly use these outputs for the metric recovery through self-calibration and motion segmentation using trifocal tenor.