An Ensemble Learning Aided Computer Vision Method with Advanced Color Enhancement for Corroded Bolt Detection in Tunnels
Open Access
Abstract
Bolts, as the basic units of tunnel linings, are crucial to safe tunnel service. Caused by the moist and complex environment in the tunnel, corrosion becomes a significant defect of bolts. Computer vision technology is adopted because manual patrol inspection is inefficient and often misses the corroded bolts. However, most current studies are conducted in a laboratory with good lighting conditions, while their effects in actual practice have yet to be considered, and the accuracy also needs to be improved. In this paper, we put forward an Ensemble Learning approach combining our Improved MultiScale Retinex with Color Restoration (IMSRCR) and You Only Look Once (YOLO) based on truly acquired tunnel image data to detect corroded bolts in the lining. The IMSRCR sharpens and strengthens the features of the lining pictures, weakening the bad effect of a dim environment compared with the existing MSRCR. Furthermore, we combine models with different parameters that show different performance using the ensemble learning method, greatly improving the accuracy. Sufficient comparisons and ablation experiments based on a dataset collected from the tunnel in service are conducted to prove the superiority of our proposed algorithm.Keywords
Funding Information
- Financial Project of Beijing Municipal Engineering Research Institut (YCZ202208B003)
This publication has 28 references indexed in Scilit:
- Integrating Semantic Segmentation and Retinex Model for Low-Light Image Enhancement2020
- Anisotropic Guided FilteringIEEE Transactions on Image Processing, 2019
- Rail Surface Defect Detection Method Based on YOLOv3 Deep Learning Networks2018
- Deep faster R-CNN-based automated detection and localization of multiple types of damage2018
- A Review Paper on Looseness Detection Methods in Bolted StructuresLatin American Journal of Solids and Structures, 2017
- Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage TypesComputer-Aided Civil and Infrastructure Engineering, 2017
- Ensemble feature selection: Homogeneous and heterogeneous approachesKnowledge-Based Systems, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Guided Image FilteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012