Instantaneous 3D motion from image derivatives using the Least Trimmed Square Regression
Fadi Dornaika
author
Angel Sappa
author
2009
This paper presents a new technique to the instantaneous 3D motion estimation. The main contributions are as follows. First, we show that the 3D camera or scene velocity can be retrieved from image derivatives only assuming that the scene contains a dominant plane. Second, we propose a new robust algorithm that simultaneously provides the Least Trimmed Square solution and the percentage of inliers-the non-contaminated data. Experiments on both synthetic and real image sequences demonstrated the effectiveness of the developed method. Those experiments show that the new robust approach can outperform classical robust schemes.
ADAS
exported from refbase (http://refbase.cvc.uab.es/show.php?record=1115), last updated on Thu, 19 Dec 2013 12:29:51 +0100
text
10.1016/j.patrec.2008.12.006
ADAS @ adas @ DoS2009a
Pattern Recognition Letters
PRL
2009
Elsevier Science Inc.
continuing
periodical
academic journal
30
5
535–543
0167-8655