Abstract: This paper presents automatic moving object detection by using the temporal information method from the capture video. This method is efficient in segmentation which is useful for real time video surveillance and object tracking. Based on the continuous symmetric difference between the adjacent frames full saliency map of current frame is generated .The moving object with higher saliency value is generated for background. The maximum entropy sum method is used for calculating threshold of area. The general common method is extracting the foreground using the Gaussian Mixture Method followed by the shadow. This method is useful for removal of noise the object is detected .In the background the removal of noise is done by pre-processing and Morphological processing.The final image is obtained by the modification of Fuzzy logic. Then the basic function of this detected target is controlled by ARM7 controller which is used to display the presence of human body or animal. Also buzzer is implemented for security purpose. GSM modem interface for providing the massages about the detection of object for security purpose. So in this proposed model we detect the moving object using the time domain information and different applications are operated for security purpose using ARM 7 controller. So in this proposed model we detect the moving object using the time domain information and different applications are operated for security purpose using ARM 7 controller.

Keywords: moving object detection, temporal information, saliency map, frame difference.