Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks

Обнаружение трещин и повреждений с использованием глубокого обучения и сверточных нейронных сетей
Young‐Jin Cha, Wooram Choi, Oral Büyüköztürk
2017-03-24

Canny and Sobel edge detectioncivil infrastructure inspectionconcrete crack detectionconvolutional neural networkssliding window technique
A number of image processing techniques (IPTs) have been implemented for detecting civil infrastructure defects to partially replace human-conducted onsite inspections. These IPTs are primarily used to manipulate images to extract defect features, such as cracks in concrete and steel surfaces. However, the extensively varying real-world situations (e.g., lighting and shadow changes) can lead to challenges to the wide adoption of IPTs. To overcome these challenges, this article proposes a vision-based method using a deep architecture of convolutional neural networks (CNNs) for detecting concrete cracks without calculating the defect features. As CNNs are capable of learning image features automatically, the proposed method works without the conjugation of IPTs for extracting features. The designed CNN is trained on 40 K images of 256 × 256 pixel resolutions and, consequently, records with about 98% accuracy. The trained CNN is combined with a sliding window technique to scan any image size larger than 256 × 256 pixel resolutions. The robustness and adaptability of the proposed approach are tested on 55 images of 5,888 × 3,584 pixel resolutions taken from a different structure which is not used for training and validation processes under various conditions (e.g., strong light spot, shadows, and very thin cracks). Comparative studies are conducted to examine the performance of the proposed CNN using traditional Canny and Sobel edge detection methods. The results show that the proposed method shows quite better performances and can indeed find concrete cracks in realistic situations.
1
A deep convolutional neural network detects concrete cracks without handcrafted defect-feature extraction or conventional image-processing techniques.
2
Combining the trained CNN with a sliding-window strategy enables scanning images larger than 256 × 256 pixels.
3
Compared with traditional Canny and Sobel edge detection, the proposed approach performed substantially better in realistic inspection conditions.
4
The CNN was trained on 40,000 images at 256 × 256-pixel resolution and achieved approximately 98% accuracy.
5
The method was tested on 55 previously unseen 5,888 × 3,584-pixel images under strong lighting, shadows, and very thin cracks.

Concrete cracks in civil infrastructure surfaces under varying real-world imaging conditions

Robust and accurate image-based detection of concrete cracks, including very thin cracks under illumination and shadow variations

Publication Details
Publication Date
2017-03-24
Journal
Publisher
ISSN
Cited by
3398
Access Type
Author Information
Authors
Young‐Jin Cha
Wooram Choi
Oral Büyüköztürk
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%