A vibe-id foreground detection method for indoor real-time monitoring

Abstract

The invention provides a ViBe-ID foreground detection method for indoor real-time monitoring, comprising: inputting a video sequence, using a background modeling method combined with a three-frame difference method to carry out background modeling, and performing foreground extraction with a foreground detection algorithm of the ViBe algorithm , and then use the partition update strategy of the background model to complete the update of the background model, use the morphological method to improve the foreground area, and finally output the foreground area. Beneficial effects of the present invention: on the basis of not sacrificing the real-time performance and accuracy of the original ViBe algorithm for foreground detection, the method can effectively eliminate the "ghost image" and the "whitening" phenomenon caused by the sudden change of light, compared with the ViBe algorithm It is more suitable for foreground detection in indoor environments.

Description

technical field [0001] The invention relates to the field of moving target detection, in particular to a ViBe-ID foreground detection method for indoor real-time monitoring. Background technique [0002] At present, the mainstream moving target detection technologies mainly include the inter-frame difference method, the optical flow method, and the background difference method. The method of binary classification of foreground pixels and background pixels by judging whether the grayscale difference is greater than the threshold value, this method has a small amount of calculation and wide applicability, but the divided foreground area is often not complete; The optical flow field of the image sequence uses the difference between the optical flow information of the moving object in the image and the optical flow information of the background to determine the position of the moving object, and then detect the moving target. This method has high accuracy and is robust to illumi...

AI Technical Summary

Problems solved by technology

This algorithm takes advantage of the fact that pixels have similar pixel values ​​in the same area, and only selects the first frame image of the video for background initialization, but this method also has two shortcomings: (1) When there is motion in the first frame image of the video When the target is detected, the foreground pixels are considered as background pixels and integrated into the background modeling, which will cause a "ghost" phenomenon; (2) When the light intensity of the video image changes suddenly, such as the sudden change of light caused by the operation of the indoor switch light Phenomenon, most areas of the image will be detected as foreground, resulting in "whitening" phenomenon

Images