A HYBRID ML–DL FRAMEWORK FOR REAL-TIME VEHICLE DETECTION, CLASSIFICATION, AND TRACKING IN INTELLIGENT TRAFFIC SURVEILLANCE

Abstract

The exponential rise in urban traffic has created a pressing demand for intelligent surveillance systems capable of real-time vehicle monitoring, detection, and analysis. Conventional image processing approaches often struggle to maintain accuracy in complex scenarios involving illumination changes, occlusions, and dense traffic conditions. To overcome these limitations, this study proposes a hybrid Machine Learning and Deep Learning (ML/DL) framework for efficient vehicle detection, classification, and tracking. The system employs a YOLO-based deep learning model for precise object localization, a Convolutional Neural Network (CNN) for vehicle type classification, and a multi-object tracking algorithm to ensure consistent tracking across consecutive frames. Experimental evaluations indicate that the proposed method achieves superior accuracy, robustness, and adaptability compared to traditional techniques. The outcomes of this research support the advancement of intelligent traffic surveillance systems, contributing to improved traffic management, law enforcement, and urban mobility optimization.