Enhancing Traffic Sign Recognition On The Performance Based On Yolov8
This work addresses the problem of reliable traffic sign recognition for autonomous driving systems, but it is incremental as it builds upon existing YOLOv8 with specific enhancements.
The paper tackled the challenge of accurately detecting and classifying traffic signs in autonomous vehicles by enhancing YOLOv8 with data augmentation, architectural improvements, and refined loss functions, resulting in marked improvements in detection accuracy, robustness, and real-time inference on edge devices.
This paper Traffic sign recognition plays a crucial role in the development of autonomous vehicles and advanced driver-assistance systems (ADAS). Despite significant advances in deep learning and object detection, accurately detecting and classifying traffic signs remains challenging due to their small sizes, variable environmental conditions, occlusion, and class imbalance. This thesis presents an enhanced YOLOv8-based detection system that integrates advanced data augmentation techniques, novel architectural enhancements including Coordinate Attention (CA), Bidirectional Feature Pyramid Network (BiFPN), and dynamic modules such as ODConv and LSKA, along with refined loss functions (EIoU and WIoU combined with Focal Loss). Extensive experiments conducted on datasets including GTSRB, TT100K, and GTSDB demonstrate marked improvements in detection accuracy, robustness under adverse conditions, and real-time inference on edge devices. The findings contribute actionable insights for deploying reliable traffic sign recognition systems in real-world autonomous driving scenarios.