Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Vision‐based automated bridge component recognition with high‐level scene consistency
This research investigates vision‐based automated bridge component recognition, which is critical for automating visual inspection of bridges during initial response after earthquakes. Semantic segmentation algorithms with up to 45 convolutional layers are applied to recognize bridge components from images of complex scenes. One of the challenges in such scenarios is to get the recognition results consistent with high‐level scene structure using limited amount of training data. To impose the high‐level scene consistency, this research combines 10‐class scene classification and 5‐class bridge component classification. Three approaches are investigated to combine scene classification results into bridge component classification: (a) naïve configuration, (b) parallel configuration, and (c) sequential configuration of classifiers. The proposed approaches, sequential configuration in particular, are demonstrated to be effective in recognizing bridge components in complex scenes, showing less than 1% of accuracy loss from the naïve/parallel configuration for bridge images, and less than 1% false positives for the nonbridge images.
Vision‐based automated bridge component recognition with high‐level scene consistency
This research investigates vision‐based automated bridge component recognition, which is critical for automating visual inspection of bridges during initial response after earthquakes. Semantic segmentation algorithms with up to 45 convolutional layers are applied to recognize bridge components from images of complex scenes. One of the challenges in such scenarios is to get the recognition results consistent with high‐level scene structure using limited amount of training data. To impose the high‐level scene consistency, this research combines 10‐class scene classification and 5‐class bridge component classification. Three approaches are investigated to combine scene classification results into bridge component classification: (a) naïve configuration, (b) parallel configuration, and (c) sequential configuration of classifiers. The proposed approaches, sequential configuration in particular, are demonstrated to be effective in recognizing bridge components in complex scenes, showing less than 1% of accuracy loss from the naïve/parallel configuration for bridge images, and less than 1% false positives for the nonbridge images.
Vision‐based automated bridge component recognition with high‐level scene consistency
Narazaki, Yasutaka (Autor:in) / Hoskere, Vedhus (Autor:in) / Hoang, Tu A. (Autor:in) / Fujino, Yozo (Autor:in) / Sakurai, Akito (Autor:in) / Spencer, Billie F. Jr. (Autor:in)
Computer‐Aided Civil and Infrastructure Engineering ; 35 ; 465-482
01.05.2020
18 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Vision‐Based Automated Crack Detection for Bridge Inspection
| Wiley | 2015
Vision‐Based Automated Crack Detection for Bridge Inspection
| Online Contents | 2015
Architectural Computer Vision: Automated Recognition of Architectural Drawings
| British Library Conference Proceedings | 1993
Learning a Discriminative Distance Metric With Label Consistency for Scene Classification
| Online Contents | 2017