| 摘要 |
A method and apparatus for image processing to detect changes in a scene includes compressing by computing a wavelet transform of an image corresponding to the scene, thresholding coefficients associated with the transform, and comparing a subset of coefficients with values to detect and indicate a change in the image. Values such as averages and a standard deviation therefrom can be generated during training by processing N training images. Determining whether a change has occurred includes determining the value of image sets, standard deviation and training sets, and comparing these, based on the type of change to be ascertained, to statistical information.
|
