TY  - CONF
AU  - Patricia Marquez
AU  - Debora Gil
AU  - Aura Hernandez-Sabate
A2  - ICCVW
PY  - 2011//
TI  - A Confidence Measure for Assessing Optical Flow Accuracy in the Absence of Ground Truth
BT  - IEEE International Conference on Computer Vision – Workshops
SP  - 2042
EP  - 2049
PB  - IEEE
CY  - Barcelona (Spain)
KW  - IEEE International Conference on Computer Vision – Workshops
N2  - Optical flow is a valuable tool for motion analysis in autonomous navigation systems. A reliable application requires determining the accuracy of the computed optical flow. This is a main challenge given the absence of ground truth in real world sequences. This paper introduces a measure of optical flow accuracy for Lucas-Kanade based flows in terms of the numerical stability of the data-term. We call this measure optical flow condition number. A statistical analysis over ground-truth data show a good statistical correlation between the condition number and optical flow error. Experiments on driving sequences illustrate its potential for autonomous navigation systems.
UR  - http://www.cvc.uab.es/adas/CVVT2011/
L1  - http://refbase.cvc.uab.es/files/MGH2011.pdf
UR  - http://dx.doi.org/10.1109/ICCVW.2011.6130499
N1  - IAM; ADAS
ID  - Patricia Marquez2011
ER  -