A Bidirectional Self-Rectifying Network With Bayesian Modeling for Vision-Based Crack Detection
- 6 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (3) , 3017-3028
Abstract
Robotic vision is increasingly applied for surface inspection of built infrastructure. For this, it is essential to develop robust algorithms for semantic segmentation. This paper presents a deep learning approach using a bidirectional self-rectifying network with Bayesian modeling (BSNBM) for improving detection accuracy, in dealing with the embedded uncertainty caused by false-positive labels and nonlinearity in sequentially-convolutional blocks. For integration with residual encoders, a feature preserving branch is designed, wherein the output of previous dilated convolutional blocks (DCBs) is upsizedly or downsizedly passed on and concatenated with the following blocks recursively and bidirectionally. Further, to achieve robustness in feature representation with an acceptable level of credibility, convolutional kernels are randomized via a Bayesian model and adjusted per evidence update. As such, the network becomes less sensitive to uncertainty and redundant nonlinearity, which are inevitable in activation layers. Experimental results confirm the advantage of our BSNBM over current crack detection approaches.Keywords
This publication has 38 references indexed in Scilit:
- Deep Recurrent Neural Networks for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2017
- Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNNExpert Systems with Applications, 2017
- Variational Inference: A Review for StatisticiansJournal of the American Statistical Association, 2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Residual Learning for Image Recognition2016
- Automatic Road Crack Detection Using Random Structured ForestsIEEE Transactions on Intelligent Transportation Systems, 2016
- Holistically-Nested Edge Detection2015
- Performance measure characterization for evaluating neuroimage segmentation algorithmsNeuroImage, 2009
- Pattern Recognition and Machine Learning2006
- Monte Carlo sampling methods using Markov chains and their applicationsBiometrika, 1970