Vehicle Speed Measurement and Number Plate Detection using Real Time Embedded System

Abstract

A real time system is proposed to detect moving vehicles that violate the speed limit. A dedicated digital signal processing chip is used to exploit computationally inexpensive image-processing techniques over the video sequence captured from the fixed position video camera for estimating the speed of the moving vehicles. The moving vehicles are detected by analysing the binary image sequences that are constructed from the captured frames by employing the inter-frame difference or the background subtraction techniques. The detected moving vehicles are tracked to estimate their speeds.This project deals with the tracking and following of single object in a sequence of frames and the velocity of the object is determined. The proposed method varies from previous existing methods in tracking moving objects, velocity determination and number plate detection. From the binary image generated, the moving vehicle is tracked using image segmentation of the video frames. The segmentation process is done by using the thresholding and morphological operations on the video frames. The object is visualized and its centroid is calculated. The distance it moved between frame to frame is stored and using this velocity is calculated with the frame rate of video.The images of the speeding vehicles are further analysed to detect license plate image regions. The entire simulation is done in matlab and simulink simulation software.

Keywords:morphological;thresholding;segmentation;centroid