Name
Title | ||
|---|---|---|
Crowdsourced reliable labeling of safety-rule violations on images of complex construction scenes for advanced vision-based workplace safety. |
Abstract | ||
|---|---|---|
•Deep learning-based workplace safety approach needs annotated images for training.•Annotating images with labels of violated safety rules by engineers is challenging.•Majority vote-based crowdsourced annotation suffers from low true-negative rate.•A Bayesian network model can significantly improve the true negative rate of annotation. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.aei.2019.101001 | Advanced Engineering Informatics |
Keywords | Field | DocType |
Crowdsourcing,Construction safety,Image annotation,Bayesian network model,Safety inspection | Construction site safety,Data mining,Data collection,False alarm,Crowdsourcing,Vision based,Computer vision algorithms,Artificial intelligence,Deep learning,Engineering,Machine learning,Consensus model | Journal |
Volume | ISSN | Citations |
42 | 1474-0346 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yanyu Wang | 1 | 0 | 0.34 |
| Pin-Chao Liao | 2 | 0 | 1.69 |
| Cheng Zhang | 3 | 211 | 40.76 |
| Yi Ren | 4 | 0 | 1.69 |
| Xinlu Sun | 5 | 0 | 0.34 |
| Pingbo Tang | 6 | 28 | 8.53 |