Robust pixel-wise concrete crack segmentation and properties retrieval using image patches

Crack identification is an essential task in periodic inspection and maintenance of buildings. The application of deep learning based computer vision techniques is increasingly popular, but suffer from challenges of insufficient performance on highly diverse field inspection scenarios as well as a requirement for large amounts of labeled training data. To address these limitations, this paper proposes a robust crack segmentation approach using image patches to detect and support further accurate retrieval of crack properties for integrity assessment. In the proposed approach, a local region-based active contour model is integrated with a convolution neural network and several post-processing morphological operations to derive a segmented crack map. Experimental validation shows significant improvement in terms of accuracy and robustness over previous work. Data labeling requirement is also comparatively lower. This paper enhances the current concrete inspection process, and lays the foundation for more data efficient methods of crack segmentation to be explored.

Automated summary

This paper proposes a robust crack segmentation approach using image patches, which combines an active contour model, convolutional neural network, and morphological operations to accurately detect and segment cracks. Experimental validation shows significant improvement in accuracy and robustness compared to previous work, with lower data labeling requirements.