Traffic Sign Recognition
Traffic sign recognition (TSR) aims to enable automated systems, such as autonomous vehicles, to accurately identify and interpret road signs. Current research focuses on improving the robustness of TSR systems against challenging conditions (e.g., adverse weather, variations in sign appearance across regions) and adversarial attacks (e.g., physical stickers or light projections designed to mislead the system), often employing deep learning models like YOLO, Vision Transformers, and Convolutional Neural Networks. These advancements are crucial for enhancing the safety and reliability of autonomous driving and other intelligent transportation systems, contributing significantly to the broader field of computer vision and machine learning.
Papers
TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition
Guoyang Zhao, Fulong Ma, Weiqing Qi, Chenguang Zhang, Yuxuan Liu, Ming Liu, Jun Ma
FUSED-Net: Enhancing Few-Shot Traffic Sign Detection with Unfrozen Parameters, Pseudo-Support Sets, Embedding Normalization, and Domain Adaptation
Md. Atiqur Rahman, Nahian Ibn Asad, Md. Mushfiqul Haque Omi, Md. Bakhtiar Hasan, Sabbir Ahmed, Md. Hasanul Kabir