PNew approch for object detection and tracking using 2D - DWT

Moving object detection is fundamental step for automated surveillance system. Generally object detection is performed by some detectors or background subtraction technique. Ultimate aim to detect an object is to detect its edges from the background. There are different methods available for the edge detection of the object. In this paper we propose an idea to detect the edges of the moving object using discrete wavelet transform. 2-D discrete wavelet transform can also be useful for storing of the input video with saving of large amount of memory as compared to the original input video in real time surveillance system. In this method the object detection is based on 2-D discrete wavelet transform error component outputs of the input video frames. For this analysis HAAR wavelet is used as reference.