Motion Detection in Video with Large Areas of Detail

摘要

A method for motion detection is provided that includes determining a first motion measure for a pixel based on differences between first neighboring pixels of the pixel, determining a detail measure for the pixel, wherein the detail measure is indicative of an amount of detail in second neighboring pixels of the pixel, adapting a first coring threshold and a first gain of a first transfer function based on the detail measure, and using the adapted first transfer function to map the first motion measure to a first motion parameter.