Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites
Low visibility hazard detection in construction sites is a crucial task for prevention of fatal accidents. Manual monitoring of construction workers to ensure they follow the safety rules (e.g., wear high-visibility vests) is a cumbersome task and practically infeasible in many applications. Therefo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8782101/ |
| _version_ | 1818668274731188224 |
|---|---|
| author | Ammar Mansoor Kamoona Amirali Khodadadian Gostar Ruwan Tennakoon Alireza Bab-Hadiashar David Accadia Joshua Thorpe Reza Hoseinnezhad |
| author_facet | Ammar Mansoor Kamoona Amirali Khodadadian Gostar Ruwan Tennakoon Alireza Bab-Hadiashar David Accadia Joshua Thorpe Reza Hoseinnezhad |
| author_sort | Ammar Mansoor Kamoona |
| collection | DOAJ |
| description | Low visibility hazard detection in construction sites is a crucial task for prevention of fatal accidents. Manual monitoring of construction workers to ensure they follow the safety rules (e.g., wear high-visibility vests) is a cumbersome task and practically infeasible in many applications. Therefore, an automated monitoring system is of both fundamental and practical interest. This paper proposes an intelligent solution that uses live camera images to detect workers who breach safety rules by not wearing high-visibility vests. The proposed solution is formulated in the form of an anomaly detection algorithm developed in the random finite set (RFS) framework. The proposed system is comprised of three steps: 1) applying a deep neural network to extract people in the image; 2) extracting particularly engineered features from each blob returned by the deep neural network; and 3) applying the RFS-based anomaly detection algorithm to each set of detected features. The experimental results demonstrate that in terms of F1-score, the proposed solution (as the combination of the newly engineered features and RFS-based anomaly detection algorithm) significantly outperforms various combinations of common and the state-of-the-art features and anomaly detection algorithms employed in machine vision applications. |
| first_indexed | 2024-12-17T06:33:43Z |
| format | Article |
| id | doaj.art-5f81259079bd4a89bdb752585b416b02 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T06:33:43Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5f81259079bd4a89bdb752585b416b022022-12-21T22:00:04ZengIEEEIEEE Access2169-35362019-01-01710571010572010.1109/ACCESS.2019.29321378782101Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction SitesAmmar Mansoor Kamoona0Amirali Khodadadian Gostar1Ruwan Tennakoon2Alireza Bab-Hadiashar3David Accadia4Joshua Thorpe5Reza Hoseinnezhad6https://orcid.org/0000-0001-9525-1467School of Engineering, RMIT University, Melbourne, VIC, AustraliaSchool of Engineering, RMIT University, Melbourne, VIC, AustraliaSchool of Engineering, RMIT University, Melbourne, VIC, AustraliaSchool of Engineering, RMIT University, Melbourne, VIC, AustraliaCornerstone Solutions Pty., Ltd., Hawthorn, VIC, AustraliaCornerstone Solutions Pty., Ltd., Hawthorn, VIC, AustraliaSchool of Engineering, RMIT University, Melbourne, VIC, AustraliaLow visibility hazard detection in construction sites is a crucial task for prevention of fatal accidents. Manual monitoring of construction workers to ensure they follow the safety rules (e.g., wear high-visibility vests) is a cumbersome task and practically infeasible in many applications. Therefore, an automated monitoring system is of both fundamental and practical interest. This paper proposes an intelligent solution that uses live camera images to detect workers who breach safety rules by not wearing high-visibility vests. The proposed solution is formulated in the form of an anomaly detection algorithm developed in the random finite set (RFS) framework. The proposed system is comprised of three steps: 1) applying a deep neural network to extract people in the image; 2) extracting particularly engineered features from each blob returned by the deep neural network; and 3) applying the RFS-based anomaly detection algorithm to each set of detected features. The experimental results demonstrate that in terms of F1-score, the proposed solution (as the combination of the newly engineered features and RFS-based anomaly detection algorithm) significantly outperforms various combinations of common and the state-of-the-art features and anomaly detection algorithms employed in machine vision applications.https://ieeexplore.ieee.org/document/8782101/Random finite setsconstruction safetysafety monitoringPoisson point patternsIID clustersPHD filter |
| spellingShingle | Ammar Mansoor Kamoona Amirali Khodadadian Gostar Ruwan Tennakoon Alireza Bab-Hadiashar David Accadia Joshua Thorpe Reza Hoseinnezhad Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites IEEE Access Random finite sets construction safety safety monitoring Poisson point patterns IID clusters PHD filter |
| title | Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites |
| title_full | Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites |
| title_fullStr | Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites |
| title_full_unstemmed | Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites |
| title_short | Random Finite Set-Based Anomaly Detection for Safety Monitoring in Construction Sites |
| title_sort | random finite set based anomaly detection for safety monitoring in construction sites |
| topic | Random finite sets construction safety safety monitoring Poisson point patterns IID clusters PHD filter |
| url | https://ieeexplore.ieee.org/document/8782101/ |
| work_keys_str_mv | AT ammarmansoorkamoona randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites AT amiralikhodadadiangostar randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites AT ruwantennakoon randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites AT alirezababhadiashar randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites AT davidaccadia randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites AT joshuathorpe randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites AT rezahoseinnezhad randomfinitesetbasedanomalydetectionforsafetymonitoringinconstructionsites |