Visual detection and tracking of lane violations for heavy vehicles

With the rapid progress in deep learning and high-performance computing, video-based traffic monitoring systems and analysis of CCTV camera images have witnessed significant advancements. In this paper, we present a novel and automated traffic monitoring system that harnesses the power of robust deep learning models, offering a comprehensive framework for efficient traffic surveillance. Our system introduces several innovative contributions, including a novel approach for lane identity (LaneID) determination and an integrated methodology for comprehensive traffic rule violation detection. Leveraging state-of-the-art algorithms such as HybridNets, YOLOv8, and DeepSORT, carefully selected through comprehensive comparisons, our approach focuses on detecting lane violations by heavy vehicles and considers crucial factors such as vehicle type, speed, and lane positioning to ensure accurate and reliable violation recognition. By integrating LaneIDs, vehicle speed, and orientation, our system achieves more reliable and nuanced violation detection, improving overall efficiency. Through meticulous fine-tuning and training on a custom dataset, our YOLOv8-based vehicle detection achieved a mean average precision (mAP) of 95%, while our speed estimation algorithm, leveraging a combination of pixel per metric (PPM) and frame differences, demonstrated strong performance with an mAP of 93.1%. This fine-tuned and efficient system ensures real-time monitoring, immediate feedback, and accurate lane violation detection, thereby promoting responsible driving behavior. Additionally, we employed the proposed system to detect other traffic violations, achieving an overall accuracy of 94.03%, which also benefits from geometrical information as of the orientation angle.