 |
    |
Scale Invariant Optical Flow
Li Xu, Zhenlong Dai, and Jiaya Jia
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kongxuli@cse.cuhk.edu.hk
zldai@cse.cuhk.edu.hk
leojia@cse.cuhk.edu.hk
Abstract. Scale variation commonly arises in images/videos, which cannot be naturally dealt with by optical flow. Invariant feature matching, on the contrary, provides sparse matching and could fail for regions without conspicuous structures. We aim to establish dense correspondence between frames containing objects in different scales and contribute a new framework taking pixel-wise scales into consideration in optical flow estimation. We propose an effective numerical scheme, which iteratively optimizes discrete scale variables and continuous flow ones. This scheme notably expands the practicality of optical flow in natural scenes containing various types of object motion.
LNCS 7573, p. 385 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012