ViBe-ID foreground detection method for indoor real-time monitoring

The invention provides a ViBe-ID foreground detection method for indoor real-time monitoring, including the steps: inputting a video sequence, carrying out background modeling by using a background modeling method combined with a three-frame difference method, performing foreground extracting by using a foreground detection algorithm of a ViBe algorithm, then completing background model updating by using a partition updating strategy of the background model, perfecting a foreground region by using a morphological method, and finally outputting the foreground region, and meanwhile, inserting anillumination detection algorithm based on an inter-frame gray mean value difference in an algorithm process. The ViBe-ID foreground detection method has the advantages that on the basis that the real-time performance and accuracy of an original ViBe algorithm for foreground detection are not sacrificed, the ghosting phenomenon and the whitening phenomenon caused by sudden change of illumination are effectively eliminated