Digital video has become very important form
of information technology and is now used in many
different areas, such as teleconferencing, mobile telephone,
surveillance, and entertainment. Therefore, in this paper,
we attempt propose a hybrid system to moving object
identification in digital video clip. That system include
four stages: the first stage is opening Audio/ Video
Interleaved file (AVI) Video file which is called RIFF.
AVI, second stage is segmented one of video frames using
segmentation techniques presented in Thresholding
technique. While the third stage used Discrete Wavelet
Transform (DWT), The role of transform is to make the
frame s energy as compact as possible, which means
making just small number of transformed coefficients with
large values while the magnitude of most of the rest
coefficient is quite small, or zero. It should be noted that
transform itself does not produce any compression,
instead, its task is to produce a format, then extraction
features from wavelet transform Coefficients includes
(Momentum Features) and we used these features as
inputs to training neural network. The fourth stage which
is used to identify the moving object in digital video clip
using Radial Basis Function (RBF) Network.