A confidence measure for assessing optical flow accuracy in the absence of ground truth
- Resource Type
- Conference
- Authors
- Marquez, Patricia; Gil, Debora; Hernandez-Sabate, Aura
- Source
- 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on. :2042-2049 Nov, 2011
- Subject
- Signal Processing and Analysis
Robotics and Control Systems
Computing and Processing
Components, Circuits, Devices and Systems
Databases
Accuracy
Correlation
Adaptive optics
Optical imaging
Measurement uncertainty
Reliability
- Language
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.