A Traffic Parameter Detection Algorithm Based on Double Coils

Abstract

This paper designs a detection method for real-time acquisition of traffic intersection parameters based on image processing. Firstly, two virtual coils were drawn at the beginning and the end on the acquired video stream image. Next, the presence of the vehicle was judged based on the change of the gray value in the two virtual coils. The background difference algorithm was adopted to detect and obtain various traffic parameters. The experimental video samples were collected in the actual road environment. Our algorithm relies on the first and last two coils for information processing, and completes vehicle detection, speed detection, and important parameter information acquisition of body color. Experiments show that, compared with the traditional machine vision-based traffic information detection algorithm, our traffic parameter detection method, which is based on double virtual coils, has high detection accuracy, and can detect more parameter information, while satisfying real-time performance.