Road damage detection and classification using deep neural networks

Abstract

In addressing the challenges of enhancing road damage detection efficiency and accuracy, this paper introduces an optimized YOLOv8 model suitable for embedded systems. The model significantly enhances precision, recall, and mean Average Precision (mAP), achieving 65.7% mAP on the RDD2022 dataset, thereby surpassing models such as Faster R-CNN and SSD. This advancement is attributed to the integration of a Deformable Attention Transformer, a GSConv-powered slim-neck module, and the MPDIoU loss function. These innovations not only contribute to the model's high performance but also set a new benchmark in road damage detection technology, thereby paving the way for future enhancements in the field.