This paper presents vehicle speed detection algorithm and its application for smart surveillance system using PC workstation at the selected road lane. Typical temporal resolution of 30 ms to 40ms of conventional camera has been utilized. The resolution is limited to the frame-rate of camera where the maximum velocity that can be computed depends on two factors: the timing resolution and the displacement resolution in pixels on image. The speed estimation of car and motorcycle are obtained in real-time using frame differencing technique for moving object detection. Experimental results are presented to demonstrate the efficiency of the proposed algorithm where it has been tested on a real video sequence and the results are analyzed.