Urban traffic management has become increasingly difficult due to the continuous rise in the number of vehicles. Traditional traffic signal systems operate on fixed time intervals and do not adapt to real-time traffic conditions, often leading to congestion and longer waiting times. To address this issue, this paper proposes a computer vision-based adaptive traffic signal control system that dynamically adjusts signal timings based on live traffic density. The proposed system utilizes OpenCV for video processing and a YOLO-based model for real-time vehicle detection and classification. Traffic density is estimated by counting vehicles in each lane, and signal timings are assigned proportionally to improve traffic flow. In addition, the system includes a mechanism to detect emergency vehicles and provide them with immediate signal priority. The model is implemented in Python and tested in a simulated environment. Experimental results indicate improved traffic efficiency and reduced delays compared to conventional systems. Overall, the proposed solution offers a scalable and intelligent approach for modern traffic management.
Chavan et al. (2026) studied this question.