| 摘要 |
The present invention relates to a novel method for producing a background model based on the images acquired from a non-static camera. Rule-based statistical multiple image analytical method to process multiple non-overlapping background region of a scene using predetermined threshold values to identify the preferred intensity variance for modeling the background pixel. One of the advantages of the a method for modeling dynamic scene using region-based adaptive statistical learning to model dynamic background within one camera view and scene-based modeling to model multiple non-overlapping regions of the background image scene is that it provides an accurate background representation as compared to background modeling using pixel-wise scalar value. Another advantage of the method for the present invention is that a less computational cost is used as compared to background modeling using pixel-wise statistical or kernel density. Furthermore, the method for the present invention has higher sensitive foreground detection as compared to privacy mask concept (masking out dynamic region from being modeled. |
