NB-FCN: Real-Time Accurate Crack Detection in Inspection Videos Using Deep Fully Convolutional Network and Parametric Data Fusion

• Published in: IEEE transactions on instrumentation and measurement Vol. 69; no. 8; pp. 5325 - 5334
• Main Authors: Chen, Fu-Chen, Jahanshahi, Mohammad R.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-08-2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Background noise; Crack detection; Cracks; data fusion; Data integration; Feature extraction; Flaw detection; fully convolutional networks (FCNs); Image processing; Inspection; Nuclear energy; nuclear power plant inspection; Nuclear power plants; Power generation; Real time; Real-time systems; real-time video analysis; Surface cracks; Training; Video; Videos
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2019.2959292

For the safe operations of nuclear power plants, it is important to inspect the reactor internal components frequently. However, current practice involves human technicians who review the inspection videos and identify cracks on metallic surfaces of underwater components, which is costly, time-consuming, and subjective. Detecting cracks on metallic surfaces from the inspection videos is challenging since the cracks are tiny and surrounded by noisy patterns in the background. While other crack detection approaches require longer processing time, this study proposes a new approach called NB-fully convolutional network (NB-FCN) that detects cracks from inspection videos in real time with high precision. An architecture design principle is introduced for FCN, where the FCN can take image patches for training without pixel-level labels. Based on the naïve Bayes (NB) probability, a parametric data fusion scheme called pNB-Fusion is proposed to fuse crack score maps from multiple video frames and outperforms other fusion schemes. The proposed NB-FCN achieves 98.6% detection average precision (AP) and requires only 0.017 s for a <inline-formula> <tex-math notation="LaTeX">720\times540 </tex-math></inline-formula> frame and 0.1 s for a <inline-formula> <tex-math notation="LaTeX">1920\times1080 </tex-math></inline-formula> frame. Based on its capability and efficiency, the proposed NB-FCN is a significant step toward real-time video processing for autonomous nuclear power plant inspection.