Title | ||
---|---|---|
Vision-based method for semantic information extraction in construction by integrating deep learning object detection and image captioning |
Abstract | ||
---|---|---|
•Proposes a novel method for semantic information extraction from images in construction engineering.•Integrates deep learning object detection and image captioning.•Achieves the Consensus-based Image Description Evaluation (CIDEr) of 1.84 in experiments.•Develops an algorithm for visualizing construction scene graph. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.aei.2022.101699 | Advanced Engineering Informatics |
Keywords | DocType | Volume |
Deep learning,Image captioning,Semantic information extraction,Object detection,Construction engineering | Journal | 53 |
ISSN | Citations | PageRank |
1474-0346 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yiheng Wang | 1 | 0 | 0.34 |
Bo Xiao | 2 | 0 | 0.34 |
Ahmed Bouferguene | 3 | 0 | 0.34 |
Mohamed Al-Hussein | 4 | 0 | 0.34 |
Heng Li | 5 | 121 | 38.18 |