Performance of optical flow techniques
International Journal of Computer Vision
Optical flow estimation: advances and comparisons
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Experience with 3D Optical Flow on Gated MRI Cardiac Datasets
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Performance characterization in computer vision: A guide to best practices
Computer Vision and Image Understanding
| Hi-index | 0.00 |
We use 3 脳 3 脳 3 Sobel operators to compute both spatio-temporal derivatives s_x, s_y and s_t and their certainties (scalar number) in a number of image sequences and then use Lucas and Kanade's weighted least squares framework to compute optical flow (image velocity) in 5 脳 5 image neighbourhoods, where the weights are the derivative certainties. We model the certainties in the derivatives as proposed by Spies [Vision Interface 2003] and analyze them quantitatively by evaluating the flow computed using them. For a number of synthetic image sequences with the correct answer known, we perform a quantitative analysis using either weights of 1.0 or weights computed from the derivative certainties (2 ways) and show that using a good estimation of the derivative quality in an optical flow calculation leads to better quality optical flow (both more dense and more accurate).