RDD4D: 4D-Attention-Guided Road Damage Detection and Classification

Road damage detection and assessment are crucial components of infrastructure maintenance. However, detecting multiple crack types in a single image remains a challenging limitation, particularly at varying scales. This is due to the lack of road datasets with various types of damage on varying scales. To address this challenge, we introduce: 1) A novel dataset called the Diverse Road Damage Dataset (DRDD) that captures multiple damage types per individual image. 2) A new detection model called RDD4D that exploits Attention4D blocks to enable better feature refinement across multiple scales. The Attention4D module processes feature maps through an attention mechanism combining positional encoding and talking head components to extract both local and global contextual features. In our comprehensive experimental analysis comparing various state-of-the-art models, our enhanced model demonstrates superior performance in detecting large-sized road cracks with an Average Precision (AP) of 0.458 and maintained competitive performance with an overall mAP of 0.446 on our proposed dataset. Moreover, we also provide results on the CrackTinyNet dataset; our model achieved around a 0.21 increase in performance. The code, model weights, dataset, and our results are publicly available at https://github.com/msaqib17/Road_Damage_Detection