Vehicle Tracking and Clssification in Highways using Region and Boundary Extraction

R. Rad and M. Jamzad (Iran)


Tracking, Highway, Vehicle type, Occlu sion removal, Prediction.


Real time road traffic monitoring is one of the challeng ing problems in machine vision, especially when one is us ing commercially available PCs as the main processor. In this paper, we describe a real-time method for extracting some traffic parameters in highways such as, lane change detection, vehicle classification and vehicle counting. In addition, we will explain a real time method for multiple vehicles tracking that has the capability of occlusion detec tion. Our algorithm has three phases. Detection of pixels on moving objects, detection of a "Shape of Interest" in frame sequences, and finally determination of the relation among objects in frame sequences. Our tracing algorithm uses Kalman filter and backgrounddifferencingtechniques. We used morphological operations for vehicle contour ex traction and its recognition. Our system is implemented on a PC with Pentium II 800 MHZ CPU. Its processing speed was measured to be 11 frames per second. The accuracy of measurement was 96%.

Important Links:

Go Back