Road crack is one of the prominent problems that can frequently occur in highways and main roads. The manual road crack evaluation is laborious, time-consuming, inaccurate, and it has several implementation issues. Conversely, the computer vision-based solution is very challenging due to the complex ambient conditions, including illumination, shadow, dust, and crack shape. Most of the cracks exist as irregular edge patterns and are the most important features for detection purpose. Recent advances in deep learning adopt a convolutional neural network as the base model to detect and localize crack with a single RGB image. Yet, this approach has an inaccurate boundary for crack localization, resulting in thicker and blurry edges. To overcome this problem, the study proposes a novel and robust road crack detection based on deep learning which also considers the original edge of the image as the additional feature. The main contribution of this work is adapting the original image gradient with the coarse crack detection result and refining it to produce more precise crack boundaries. Extensive experimental results have shown that the proposed method outperforms the former state-of-the-art methods in terms of the detection accuracy.
BARNet: Boundary Aware Refinement Network for Crack Detection
IEEE Transactions on Intelligent Transportation Systems ; 23 , 7 ; 7343-7358
2022-07-01
7003359 byte
Article (Journal)
Electronic Resource
English
J. L. Lewis [Seltona Paper, Barnet Plates]
DataCite | 1914
The impact of a controlled parking zone in Barnet
TIBKAT | 1992
|Online State Space Refinement for Competence-Aware Systems
European Patent Office | 2023
|