Crowdsourced reliable labeling of safety-rule violations on images of complex construction scenes for advanced vision-based workplace safety
- Arizona State University, Tempe, AZ (United States). Del E. Webb School of Construction
- Tsinghua Univ., Beijing (China)
- Texas A & M Univ., College Station, TX (United States)
- Arizona State Univ., Tempe, AZ (United States)
Construction workplace hazard detection requires engineers to analyze scenes manually against many safety rules, which is time-consuming, labor-intensive, and error-prone. Computer vision algorithms are yet to achieve reliable discrimination of anomalous and benign object relations underpinning safety violation detections. Recently developed deep learning-based computer vision algorithms need tens of thousands of images, including labels of the safety rules violated, in order to train deep-learning networks for acquiring spatiotemporal reasoning capacity in complex workplaces. Such training processes need human experts to label images and indicate whether the relationship between the worker, resource, and equipment in the scenes violate spatiotemporal arrangement rules for safe and productive operations. False alarms in those manual labels (labeling no-violation images as having violations) can significantly mislead the machine learning process and result in computer vision models that produce inaccurate hazard detections. Compared with false alarms, another type of mislabels, false negatives (labeling images having violations as “no violations”), seem to have fewer impacts on the reliability of the trained computer vision models.
- Research Organization:
- Arizona State Univ., Tempe, AZ (United States)
- Sponsoring Organization:
- USDOE Office of Nuclear Energy (NE)
- Grant/Contract Number:
- NE0008403
- OSTI ID:
- 1801215
- Alternate ID(s):
- OSTI ID: 1570882
- Journal Information:
- Advanced Engineering Informatics, Vol. 42, Issue C; ISSN 1474-0346
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Similar Records
Iterative self-organizing SCEne-LEvel sampling (ISOSCELES) for large-scale building extraction
Detecting damaged buildings using real-time crowdsourced images and transfer learning