Comparative analysis of edge detection image processing techniques for efficient traffic signal management system

Abstract

Traffic monitoring and control pose significant challenges, particularly in metropolitan areas worldwide. Traditional methods such as timers, traffic police control, and sensor-based systems have become increasingly ineffective due to escalating traffic volumes. Image processing emerges as a promising technology for enhancing traffic control systems. This research aims to address the inefficiencies of current traffic management systems (TMS) by conducting a detailed comparative analysis of conventional image processing techniques, focusing on edge-based methods. Utilizing the open source computer vision (OpenCV) Library, we evaluated various edge detection techniques based on qualitative parameters like environmental lighting, object detection, and size, as well as quantitative parameters such as average traffic density, sharpness ratio (SR), abruptness, sensitivity factors (SF), processing time, frame processing time, and average frames per second (FPS). The study finds that the Canny edge detection technique outperforms others, with an average traffic density of 30.12 across 10 frames, superior SR, and minimal processing time of 99 seconds. This makes it highly effective for traffic control applications by generating high-quality edge maps with minimal noise. Our findings suggest that improving conventional image processing techniques and integrating deep learning algorithms can further enhance TMS, leading to more efficient urban mobility and reduced environmental impact.