International Journal of Advanced Research in Computer and Communication Engineering

Abstract: Efficient traffic management is a critical challenge in modern urban environments due to increasing vehicle density and dynamic traffic patterns. This paper presents a Smart Traffic Control System that integrates pixel-labeling for precise vehicle segmentation with the Simple Online and Realtime Tracking (SORT) algorithm for accurate and efficient vehicle tracking. The proposed framework leverages computer vision techniques to detect, classify, and monitor vehicles in real-time from video feeds, eliminating the need for expensive sensor-based infrastructure. Pixel-labeling enables semantic understanding of the scene by assigning class labels to each pixel, allowing robust differentiation between vehicles, pedestrians, and background elements. The SORT tracker further enhances system performance by maintaining consistent object identities across frames, even under occlusion and varying lighting conditions. Experimental evaluations demonstrate that the system achieves high detection accuracy, reduced processing latency, and improved traffic flow estimation compared to traditional methods. The results suggest that the proposed approach provides a scalable, cost-effective, and adaptive solution for intelligent traffic control in smart city applications.

Keywords: smart traffic control system, SORT Tracker, pixel labeling.

Downloads: | DOI: 10.17148/IJARCCE.2025.141119