Image processing method and image processing apparatus using the same

摘要

The invention discloses an image processing method and an imager processing apparatus using the same. The method includes the following steps: receiving an training image; finding a minimum difference among the differences; determining whether the minimum difference is larger than a first threshold; if no, generating a first output value according to the first pixel, the background candidates and a plurality of weightings corresponding to the background candidates; updating a first background candidate corresponding to the minimum difference; updating a first weighting related to the first background candidate; if yes, adding the first pixel as a new background candidate to the background candidates and adding a new weighting corresponding to the new background candidate to the weightings; and detecting whether a moving object existing in an incoming image according to the background candidates and the weightings.

主权项

1. An image processing method, adapted to an image processing apparatus, comprising:
receiving an training image, which at least comprises a first pixel; calculating differences between the first pixel and a plurality of background candidates, wherein the background candidates are pixels respectively locating on other previously processed training images, and a coordinate of each background candidates is identical to a coordinate of the first pixel;
finding a minimum difference among the differences;determining whether the minimum difference is larger than a first threshold;
if no, generating a first output value according to the first pixel, the background candidates and a plurality of weightings corresponding to the background candidates;
updating a first background candidate corresponding to the minimum difference by adding a first factor to the first background candidate, wherein the first factor is related to the first pixel, a first learning rate and the first background candidate;updating a first weighting related to the first background candidate by adding a second factor to the first weighting, wherein the second factor is related to the first output value, a second learning rate and the first weightingif yes, adding the first pixel as a new background candidate to the background candidates and adding a new weighting corresponding to the new background candidate to the weightings; and detecting whether a moving object existing in an incoming image according to the background candidates and the weightings.