skvideo.motion.blockMotion¶

skvideo.motion.blockMotion(videodata, method='DS', mbSize=8, p=2, **plugin_args)[source]¶

Block-based motion estimation

Given a sequence of frames, this function returns motion vectors between frames.

Parameters:	videodata : ndarray, shape (numFrames, height, width, channel) A sequence of frames method : string “ES” –> exhaustive search “3SS” –> 3-step search “N3SS” –> “new” 3-step search [1] “SE3SS” –> Simple and Efficient 3SS [2] “4SS” –> 4-step search [3] “ARPS” –> Adaptive Rood Pattern search [4] “DS” –> Diamond search [5] mbSize : int Macroblock size p : int Algorithm search distance parameter
Returns:	motionData : ndarray, shape (numFrames - 1, height/mbSize, width/mbSize, 2) The motion vectors computed from videodata. The first element of the last axis contains the y motion component, and second element contains the x motion component.

References

[1]	Renxiang Li, Bing Zeng, and Ming L. Liou, “A new three-step search algorithm for block motion estimation.” IEEE Transactions on Circuits and Systems for Video Technology, 4 (4) 438-442, Aug 1994

[2]	Jianhua Lu and Ming L. Liou, “A simple and efficient search algorithm for block-matching motion estimation.” IEEE Transactions on Circuits and Systems for Video Technology, 7 (2) 429-433, Apr 1997

[3]	Lai-Man Po and Wing-Chung Ma, “A novel four-step search algorithm for fast block motion estimation.” IEEE Transactions on Circuits and Systems for Video Technology, 6 (3) 313-317, Jun 1996

[4]	Yao Nie and Kai-Kuang Ma, “Adaptive rood pattern search for fast block-matching motion estimation.” IEEE Transactions on Image Processing, 11 (12) 1442-1448, Dec 2002

[5]	Shan Zhu and Kai-Kuang Ma, “A new diamond search algorithm for fast block-matching motion estimation.” IEEE Transactions on Image Processing, 9 (2) 287-290, Feb 2000