TY - JOUR
T1 - Vision-based navigation planning for autonomous post-earthquake inspection of reinforced concrete railway viaducts using unmanned aerial vehicles
AU - Narazaki, Yasutaka
AU - Hoskere, Vedhus
AU - Chowdhary, Girish
AU - Spencer, Billie F.
N1 - Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2022/5
Y1 - 2022/5
N2 - This research proposes an approach for vision-based autonomous navigation planning of unmanned aerial vehicles for the collection of images suitable for the rapid post-earthquake inspection of reinforced concrete railway viaducts. The proposed approach automatically recognizes and localizes critical structural components, columns in this case, and determines appropriate viewpoints for inspection relative to the identified components. Structural component recognition and localization are formulated through online detection of rectangular prismatic shapes from the parsed sparse point-cloud data, where prior knowledge of the target structural system is incorporated. The proposed approach is tested in a synthetic environment representing Japanese high-speed railway viaducts. First, the ability to detect the columns of the target viaduct is assessed. The results show that the columns are detected completely and robustly, with centimeter-level accuracy. Subsequently, the entire approach is demonstrated in the synthetic environment, showing the significant potential of collecting high-quality images for post-earthquake structural inspection efficiently.
AB - This research proposes an approach for vision-based autonomous navigation planning of unmanned aerial vehicles for the collection of images suitable for the rapid post-earthquake inspection of reinforced concrete railway viaducts. The proposed approach automatically recognizes and localizes critical structural components, columns in this case, and determines appropriate viewpoints for inspection relative to the identified components. Structural component recognition and localization are formulated through online detection of rectangular prismatic shapes from the parsed sparse point-cloud data, where prior knowledge of the target structural system is incorporated. The proposed approach is tested in a synthetic environment representing Japanese high-speed railway viaducts. First, the ability to detect the columns of the target viaduct is assessed. The results show that the columns are detected completely and robustly, with centimeter-level accuracy. Subsequently, the entire approach is demonstrated in the synthetic environment, showing the significant potential of collecting high-quality images for post-earthquake structural inspection efficiently.
KW - Autonomous structural inspection
KW - Online structural component recognition
KW - Path planning
KW - Post-earthquake inspection
KW - Semantic segmentation
KW - Unmanned Aerial Vehicles
UR - http://www.scopus.com/inward/record.url?scp=85127270827&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127270827&partnerID=8YFLogxK
U2 - 10.1016/j.autcon.2022.104214
DO - 10.1016/j.autcon.2022.104214
M3 - Article
AN - SCOPUS:85127270827
SN - 0926-5805
VL - 137
JO - Automation in Construction
JF - Automation in Construction
M1 - 104214
ER -