Abstract: Robustand reliable traffic surveillance system is an urgent need to improve trafficcontrol and management. Vehicle flow detection appears to be an important partin surveillance system. The traffic flow shows the traffic state in fixed timeinterval and helps to manage and control especially when there as a trafficjam. In this project, we propose a traffic surveillance system for vehiclecounting. The proposed algorithm is composed of five steps: backgroundsubtraction, blob detection, blob analysis, blob tracking and vehicle counting.A vehicle is modelled as a rectangular patch and classified via blob analysis.By analyzing the blob of vehicles, the meaningful features are extracted. Theexperimental results show that the proposed system can provide real-time anduseful information for traffic surveillance.

Keywords: Blobdetection, Background detection, Smart Traffic signal system, Traffic signalsystem using image processing.