Falls from heights: A computer vision-based approach for safety harness detection
© 2018 Elsevier B.V. Falls from heights (FFH) are major contributors of injuries and deaths in construction. Yet, despite workers being made aware of the dangers associated with not wearing a safety harness, many forget or purposefully do not wear them when working at heights. To address this proble...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Elsevier BV
2018
|
| Online Access: | http://hdl.handle.net/20.500.11937/67470 |
| _version_ | 1848761574354845696 |
|---|---|
| author | Fang, W. Ding, L. Luo, H. Love, Peter |
| author_facet | Fang, W. Ding, L. Luo, H. Love, Peter |
| author_sort | Fang, W. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | © 2018 Elsevier B.V. Falls from heights (FFH) are major contributors of injuries and deaths in construction. Yet, despite workers being made aware of the dangers associated with not wearing a safety harness, many forget or purposefully do not wear them when working at heights. To address this problem, this paper develops an automated computer vision-based method that uses two convolutional neural network (CNN) models to determine if workers are wearing their harness when performing tasks while working at heights. The algorithms developed are: (1) a Faster-R-CNN to detect the presence of a worker; and (2) a deep CNN model to identify the harness. A database of photographs of people working at heights was created from activities undertaken on several construction projects in Wuhan, China. The database was then used to test and train the developed networks. The precision and recall rates for the Faster R-CNN were 99% and 95%, and the CNN models 80% and 98%, respectively. The results demonstrate that the developed method can accurately detect workers not wearing their harness. Thus, the computer vision-based approach developed can be used by construction and safety managers as a mechanism to proactively identify unsafe behavior and therefore take immediate action to mitigate the likelihood of a FFH occurring. |
| first_indexed | 2025-11-14T10:33:50Z |
| format | Journal Article |
| id | curtin-20.500.11937-67470 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:33:50Z |
| publishDate | 2018 |
| publisher | Elsevier BV |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-674702018-05-18T08:05:20Z Falls from heights: A computer vision-based approach for safety harness detection Fang, W. Ding, L. Luo, H. Love, Peter © 2018 Elsevier B.V. Falls from heights (FFH) are major contributors of injuries and deaths in construction. Yet, despite workers being made aware of the dangers associated with not wearing a safety harness, many forget or purposefully do not wear them when working at heights. To address this problem, this paper develops an automated computer vision-based method that uses two convolutional neural network (CNN) models to determine if workers are wearing their harness when performing tasks while working at heights. The algorithms developed are: (1) a Faster-R-CNN to detect the presence of a worker; and (2) a deep CNN model to identify the harness. A database of photographs of people working at heights was created from activities undertaken on several construction projects in Wuhan, China. The database was then used to test and train the developed networks. The precision and recall rates for the Faster R-CNN were 99% and 95%, and the CNN models 80% and 98%, respectively. The results demonstrate that the developed method can accurately detect workers not wearing their harness. Thus, the computer vision-based approach developed can be used by construction and safety managers as a mechanism to proactively identify unsafe behavior and therefore take immediate action to mitigate the likelihood of a FFH occurring. 2018 Journal Article http://hdl.handle.net/20.500.11937/67470 10.1016/j.autcon.2018.02.018 Elsevier BV restricted |
| spellingShingle | Fang, W. Ding, L. Luo, H. Love, Peter Falls from heights: A computer vision-based approach for safety harness detection |
| title | Falls from heights: A computer vision-based approach for safety harness detection |
| title_full | Falls from heights: A computer vision-based approach for safety harness detection |
| title_fullStr | Falls from heights: A computer vision-based approach for safety harness detection |
| title_full_unstemmed | Falls from heights: A computer vision-based approach for safety harness detection |
| title_short | Falls from heights: A computer vision-based approach for safety harness detection |
| title_sort | falls from heights: a computer vision-based approach for safety harness detection |
| url | http://hdl.handle.net/20.500.11937/67470 |