摘要 |
The present invention provides a method and apparatus for detecting motion in an input sequence of images. Each image comprises a number of lines and each line has a number of pixels. Values of a region of pixels of a current image are transformed to determine a set of representation values. The set of representation values are indicative of the region of pixels at a number of resolution levels. The set of representation values of the region of pixels of the current image are compared with a set of representation values of a corresponding region of pixels from a stored previous image. Based on the comparing step, a difference measure is determined between the region of pixels and the corresponding region of pixels that is indicative of the presence or absence of motion in the current image.
|