CCTV Based sensing techniques for adaptive control of traffic signals in multiprocessor architectures

Abstract

As the problem of urban traffic congestion spreads, there is a pressing need for the introduction of advanced technology and equipment to improve the state of the art of traffic control. In this context, the techniques used for sensing traffic flow information plays a vital role, ensuring accurate real time controllability. Closed Circuit Television (CCTV) has gained popularity because of its ability to provide diverse information on relatively large regions leading to opportunities for performing substantially more complex tasks than conventional detection schemes. By processing these video images, traffic parameters such as speed, traffic composition, queue length etc. can be extracted. In addition CCTV images can be further processed for other useful information such as detection of vehicle shapes, vehicle types, occurrence of traffic violations and vehicle identification numbers etc. To introduce CCTV based vehicle detection for automation of road traffic control in Sri Lanka involves an unaffordable investment cost to purchase foreign technology and equipment unless some locally developed system is introduced. This thesis presents complete design of a CCTV system, which involves multitude of design and implementational aspects. It involves development of an image grabber, a remote communication interface and detection algorithms. In addition to visual monitoring of remote road traffic scenes, the designed system is capable of assessing many different traffic parameters, which can be used for adaptive control of road traffic. The underlined project is an attempt to seek the possibility of introducing image based traffic sensing technology to Sri Lanka. Significant attention has given to reduce the cost of development throughout the project to ensure that the concept of CCTV can be realized in practice in Sri Lanka for road traffic control.