Development of a Multi-Distress Detection System for Asphalt Pavements: Transfer Learning-Based Approach

Abstract

The major objective of this research was to develop a multi-distress detection system (MDDS) that is competent in detecting various asphalt pavement functional distresses simultaneously from video images using appropriate artificial intelligence techniques. You Only Look Once Version 4 (YOLOv4), a state-of-the-art objection detection architecture incorporated with transfer learning-based approach was utilized to quantify multiple severity-based distresses obtained from actual pavement condition images. Eighteen distress classes were defined consisting of three levels of severity pertinent to cracking, potholes, and patch deterioration. The customized MDDS algorithm was trained and tested on 1,518 images retrieved from three different datasets. During training, MDDS attained an average loss of 1.5123, and the validation mean average precision was reported to be 87.44% after 7,900 iterations. During the training process, the customized architecture transformed the training images and segmented them into two million images that potentially enhanced the probability of prediction even when the images are spatially transformed. The model detected multiple distresses in the pavement video clip at an average rate of 6.7 frames per second, which makes it suitable for real-time distress detection. It is envisioned that the novel real-time MDDS tested on diverse datasets could be used by roadway agencies to identify and quantify severity-based distress classes during the monitoring process itself, which ultimately reduces the time between data analysis, pavement forensic evaluation, and decision making on maintenance interventions.

Vision-Based Asphalt Pavement Defect Detection Using Deep CNN with BIM Integration

“…The text discusses the development of a system called Multi-Distress Detection System (MDDS) for asphalt pavements using artificial intelligence techniques. The system utilizes you only look once version 4 (YOLOv4) with transfer learning to detect various distresses like cracking, potholes, and patch deterioration from video images of pavement conditions The MDDS algorithm was trained on multiple datasets and achieved an average loss of 1.5123 during training, showing promise for real-time distress detection in pavement monitoring [6]. The text discusses the current advancements in defect detection using machine vision technology.…”

Intelligent Crack Detection in Infrastructure using Computer Vision at the Edge

“…Recent studies used different versions of YOLO to multi-distress detection systems for pavement. Ghosh and Smadi used YOLOv3 (Ghosh and Smadi, 2021), and Paeraka et al used pre-trained YOLOv4 (Peraka et al, 2021) to interpret high-resolution 3D images and videos, respectively.…”

A grid‐based classification and box‐based detection fusion model for asphalt pavement crack

“…Object detection involves the dual objective of object classification and localization. Most research on pavement crack detection directly borrows advanced models open‐sourced by pioneers in computer vision, for example, single ahot multibox detector (SSD) (Maeda et al., 2018), YOLO) v1∼v5 (Du et al., 2021; Jeong, 2020; Mandal et al., 2018; Nie & Wang, 2019; Peraka et al., 2021), and faster regoin ‐ convolutional neural network (Faster R‐CNN) (Ibragimov et al., 2020; J. Q. Li et al., 2019). A number of researchers have improved upon and adapted such classical models for pavement crack detection.…”