An investigation of optical flow

Questions

1. What is optical flow?

Optical flow or optic flow is the pattern of apparent motion of objects, surfaces, and edges in a visual scene caused by the relative motion between an observer and a scene. --Wiki

2. Why use optical flow in video analysis?

3. Comparing to the static RGB image, what are the advantages and disadvantages of optical flow?

4. What are the usual computing methods of optical flow? what are the advantages and disadvantages of them?

Bouguet, J. Y. (2001). Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel Corporation, 5(1-10), 4.
通过金字塔Lucas-Kanade 光流方法计算某些点集的光流（稀疏光流）

Farnebäck, G. (2003, June). Two-frame motion estimation based on polynomial expansion. In Scandinavian conference on Image analysis (pp. 363-370). Springer, Berlin, Heidelberg.

Horn, B. K., & Schunck, B. G. (1981). Determining optical flow. Artificial intelligence, 17(1-3), 185-203.

Tao, M., Bai, J., Kohli, P., & Paris, S. (2012, May). SimpleFlow: A Non‐iterative, Sublinear Optical Flow Algorithm. In Computer Graphics Forum (Vol. 31, No. 2pt1, pp. 345-353). Blackwell Publishing Ltd.

Explore

1. Is there a better representation in video ayalysis?

Attachments

A good explaination of different optical flow computing method

Uncategorized

OPTICAL FLOW

Chapter 2 Optical Flow Estimation

Optical flow modeling and computation: a survey

A Duality Based Approach for Realtime TV-L1 Optical Flow