DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism |
| |
| Affiliation: | 1. Beijing Key Laboratory of Intelligent Processing for Building Big Data, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;2. Department of Construction and Real Estate, School of Civil Engineering, Southeast University, Nanjing 211189, China;3. School of Engineering, Design and Built Environment, Western Sydney University, Australia;1. Department of Mechanical Engineering, National Chung Cheng University, Chiayi 62102, Taiwan;2. Advanced Institute of Manufacturing with High-tech Innovations (AIM-HI), National Chung Cheng University, Chiayi 62102, Taiwan;3. Department of Intelligent Robotics, National Pingtung University, Pingtung 90004, Taiwan;1. Smart & Sustainable Manufacturing Systems Laboratory (SMART LAB), Department of Mechanical Engineering, University of Alberta, Edmonton T6G 1H9, AB, Canada;2. School of Intelligent Manufacturing Ecosystem, Xi’an Jiaotong-Liverpool University, Suzhou 215123, PR China;1. School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, China;2. Science and Technology on Near-Surface Detection Laboratory, Wuxi 214035, China;3. Department of Science and Technology, Agricultural Bank of China Guangdong Branch, Guangzhou 511430, China;4. Department of Early Warning Technology, Air Force Early Warning Academy, Wuhan 430010, China;5. The Fifth Affiliated Hospital, Guangzhou Medical University, Guangzhou 510700, China;1. College of Power Engineering, Naval University of Engineering, Wuhan, China;2. Naval Petty Officer Academy, Bengbu, China;3. School of Naval Architecture and Ocean Engineering, Huazhong University of Science and Technology, Wuhan, China;4. College of Naval Architecture and Ocean, Naval University of Engineering, Wuhan, China;5. College of Electromechanical, Wuhan City Polytechnic, Wuhan, China |
| |
| Abstract: | Objective.Computer vision-based up-to-date accurate damage classification and localization are of decisive importance for infrastructure monitoring, safety, and the serviceability of civil infrastructure. Current state-of-the-art deep learning (DL)-based damage detection models, however, often lack superior feature extraction capability in complex and noisy environments, limiting the development of accurate and reliable object distinction.Method.To this end, we present DenseSPH-YOLOv5, a real-time DL-based high-performance damage detection model where DenseNet blocks have been integrated with the backbone to improve in preserving and reusing critical feature information. Additionally, convolutional block attention modules (CBAM) have been implemented to improve attention performance mechanisms for strong and discriminating deep spatial feature extraction that results in superior detection under various challenging environments. Moreover, an additional feature fusion layers and a Swin-Transformer Prediction Head (SPH) have been added leveraging advanced self-attention mechanism for more efficient detection of multiscale object sizes and simultaneously reducing the computational complexity.Results.Evaluating the model performance in large-scale Road Damage Dataset (RDD-2018), at a detection rate of 62.4 FPS, DenseSPH-YOLOv5 obtains a mean average precision (mAP) value of 85.25%, F1-score of 81.18%, and precision (P) value of 89.51% outperforming current state-of-the-art models.Significance.The present research provides an effective and efficient damage localization model addressing the shortcoming of existing DL-based damage detection models by providing highly accurate localized bounding box prediction. Current work constitutes a step towards an accurate and robust automated damage detection system in real-time in-field applications. |
| |
| Keywords: | Automated road damage detection You Only Look Once (YOLOv5) algorithm Swin transformer object detection Computer vision Deep learning |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
