Journal
SENSORS
Volume 20, Issue 16, Pages -Publisher
MDPI
DOI: 10.3390/s20164403
Keywords
convolutional neural network; encoder-decoder architecture; semantic segmentation; feature silencing; crack detection
Funding
- U.S. National Science Foundation (NSF) [NSF-CAREER: 1846513, NSF-PFI-TT: 1919127]
- U.S. Department of Transportation, Office of the Assistant Secretary for Research and Technology (USDOT/OST-R) through INSPIRE University Transportation Center [69A3551747126]
- Vingroup Innovation Foundation (VINIF) [VINIF.2020.NCUD.DA094]
- Japan NineSigma through the Penta-Ocean Construction Ltd. Co. [SP-1800087]
Ask authors/readers for more resources
An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we present a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation, while addressing the effect of gradient vanishing problem. A feature silencing module is incorporated in the proposed framework, capable of eliminating non-discriminative feature maps from the network to improve performance. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network's robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than the state-of-the-art crack detection architectures.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available