Robust optical flow estimation using semi-invariant local features

This paper presents a robust algorithm for computation of 2-D optical flow using the principle of conservation of a set of invariant local features that are representatives of local gray-level properties in an image. Specifically, a set of rotation-invariant local orthogonal Zernike moments is used as invariant features. These are inherently integral-based features, and therefore are expected to be robust against possible variations of intensity values that may occur over a sequence of images due to sensor noise, varying illumination etc. The 2-D local optical flow field is obtained using singular value decomposition of an overdetermined set of linear equations of velocity field components, resulting from the principle of conservation of invariant features in a small neighborhood. The proposed moment-based approach is compared with two existing optical flow techniques. Experimental results with synthetic as well as real sequences are presented to demonstrate the overall robustness of the proposed approach.