Motion History Images

The motion picture history (MHI) is a static picture template helps in understanding the motion location and path as it progressed. [1] In MHI, the temporal motion information is collapsed into a single image template. Thus, the MHI pixel intensity is a function of the motion history at that location, where brighter values ​​correspond to a more recent motion. Using MHI, moving parts of a video sequence can be a single image, from where one can predict the motion for the moving parts of the video action.

Some important features of the MHI representation are: [2]

  • It represents a motion sequence in a compact manner. In this case, the silhouette sequence is condensed into a grayscale image, where dominant motion information is preserved.
  • MHI can be created and implemented in low illumination conditions where the structure can not be easily detected otherwise.
  • The MHI is not so sensitive to silhouette, holes, shadows, and missing parts.
  • The gray-scale MHI is sensitive to the direction of motion because it can demonstrate the direction of the motion.
  • It keeps a history of temporal changes at each pixel location, which then decays over time.
  • The MHI expresses the motion for orbit by using the intensity of each pixel in a temporal manner.

General Algorithm 

For Each time t 
  B t : = absolute_difference ( I t , I t -1 )> threshold
 end for
for each time t 
  for each pixel (x, y) 
    if  B t (x, y) = 1
       MHI t (x, y) : = τ 
    else if  MHI t -1 ≠ 0
       MHI t (x, y) : = MHI t -1 (x, y) - 1
     else 
      MHI t (x, y) : = 0
     end if 
end for

References

  1. Jump up^ “Research: Motion History Images” . Retrieved 13 November 2014 .
  2. Jump up^ Ahad, Md Atiqur Rahman. Motion history images for action recognition and understanding. Springer Science & Business Media, 2012.

Leave a Reply

Your email address will not be published. Required fields are marked *

Copyright computerforum.eu 2018
Shale theme by Siteturner