Skip to content

Inter-frame motion calculation using inter-frame differencing and optical flow estimation

License

Notifications You must be signed in to change notification settings

rymshasaeed/motion-energy-images

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Motion Energy Images

Motion Energy Images or Motion History Images could be defined as the pixel regions of the frame where there is motion.

Inter-frame Differencing Method

The frame difference method is the common method of motion detection. This method adopts pixel-based difference to find the moving object, i.e., D(x, y, t) = I(x, y, t) - I(x, y, t-1), where I(x, y, t) is the frame intensity for frame t at pixel (x,y).

Following animations show the results for our test cases.

motion: bend
Bend

motion: skip
Skip

motion: jump
Jump

In order to clean the holes, the image can be passed through the Gaussian low pass filter or certain morphological operations.

Lucas-Kanade Method

Optical flow estimation is the method of calculating the motion vector between two frames which are taken at a specific time. The algorithm works by trying to guess in which direction an object has moved so that local changes in intensity can be explained.

Following animations show the results for our test cases.

motion: bend
Bend

motion: skip
Skip

motion: jump
Jump

Releases

No releases published

Packages

No packages published

Languages