Automated Vision-based Bridge Component Extraction Using Multiscale Convolutional Neural Networks
This addresses a domain-specific challenge for civil engineering inspections by enabling more accurate damage detection in complex scenes, though it is incremental as it builds on existing CNN and CRF methods.
The study tackled the problem of automatically recognizing and extracting bridge components from urban scene images to improve post-earthquake damage detection by reducing false positives, achieving pixel-wise classification into five component classes using multi-scale CNNs with post-processing.
Image data has a great potential of helping post-earthquake visual inspections of civil engineering structures due to the ease of data acquisition and the advantages in capturing visual information. A variety of techniques have been applied to detect damages automatically from a close-up image of a structural component. However, the application of the automatic damage detection methods become increasingly difficult when the image includes multiple components from different structures. To reduce the inaccurate false positive alarms, critical structural components need to be recognized first, and the damage alarms need to be cleaned using the component recognition results. To achieve the goal, this study aims at recognizing and extracting bridge components from images of urban scenes. The bridge component recognition begins with pixel-wise classifications of an image into 10 scene classes. Then, the original image and the scene classification results are combined to classify the image pixels into five component classes. The multi-scale convolutional neural networks (multi-scale CNNs) are used to perform pixel-wise classification, and the classification results are post-processed by averaging within superpixels and smoothing by conditional random fields (CRFs). The performance of the bridge component extraction is tested in terms of accuracy and consistency.