Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches
Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring un...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2566 |
| _version_ | 1827752142479294464 |
|---|---|
| author | Hongwei Zhu Weikang Xie Junjie Li Jihao Shi Mingfu Fu Xiaoyuan Qian He Zhang Kaikai Wang Guoming Chen |
| author_facet | Hongwei Zhu Weikang Xie Junjie Li Jihao Shi Mingfu Fu Xiaoyuan Qian He Zhang Kaikai Wang Guoming Chen |
| author_sort | Hongwei Zhu |
| collection | DOAJ |
| description | Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge labor costs and severe false alarms exist due to related operators’ operation and judgment. This study aimed to develop an advanced computer vision-based monitoring approach to achieve automatic and real-time monitoring of underwater gas leaks. A comparison analysis between the Faster Region Convolutional Neural Network (Faster R-CNN) and You Only Look Once version 4 (YOLOv4) was conducted. The results demonstrated that the Faster R-CNN model, developed with an image size of 1280 × 720 and no noise, was optimal for the automatic and real-time monitoring of underwater gas leakage. This optimal model could accurately classify small and large-shape leakage gas plumes from real-world datasets, and locate the area of these underwater gas plumes. |
| first_indexed | 2024-03-11T07:10:36Z |
| format | Article |
| id | doaj.art-8f813af763ca4d88b50cd2049ebab1c2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:36Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8f813af763ca4d88b50cd2049ebab1c22023-11-17T08:36:34ZengMDPI AGSensors1424-82202023-02-01235256610.3390/s23052566Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two ApproachesHongwei Zhu0Weikang Xie1Junjie Li2Jihao Shi3Mingfu Fu4Xiaoyuan Qian5He Zhang6Kaikai Wang7Guoming Chen8Centre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaPipeChina West Pipeline Company, Urumqi 830000, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaCentre for Offshore Engineering and Safety Technology, China University of Petroleum, Qingdao 266580, ChinaRecent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge labor costs and severe false alarms exist due to related operators’ operation and judgment. This study aimed to develop an advanced computer vision-based monitoring approach to achieve automatic and real-time monitoring of underwater gas leaks. A comparison analysis between the Faster Region Convolutional Neural Network (Faster R-CNN) and You Only Look Once version 4 (YOLOv4) was conducted. The results demonstrated that the Faster R-CNN model, developed with an image size of 1280 × 720 and no noise, was optimal for the automatic and real-time monitoring of underwater gas leakage. This optimal model could accurately classify small and large-shape leakage gas plumes from real-world datasets, and locate the area of these underwater gas plumes.https://www.mdpi.com/1424-8220/23/5/2566subsea gas leak monitoringoptical camera detectionadvanced computer visionfaster R-CNNYOLOv4 |
| spellingShingle | Hongwei Zhu Weikang Xie Junjie Li Jihao Shi Mingfu Fu Xiaoyuan Qian He Zhang Kaikai Wang Guoming Chen Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches Sensors subsea gas leak monitoring optical camera detection advanced computer vision faster R-CNN YOLOv4 |
| title | Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches |
| title_full | Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches |
| title_fullStr | Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches |
| title_full_unstemmed | Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches |
| title_short | Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches |
| title_sort | advanced computer vision based subsea gas leaks monitoring a comparison of two approaches |
| topic | subsea gas leak monitoring optical camera detection advanced computer vision faster R-CNN YOLOv4 |
| url | https://www.mdpi.com/1424-8220/23/5/2566 |
| work_keys_str_mv | AT hongweizhu advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT weikangxie advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT junjieli advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT jihaoshi advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT mingfufu advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT xiaoyuanqian advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT hezhang advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT kaikaiwang advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches AT guomingchen advancedcomputervisionbasedsubseagasleaksmonitoringacomparisonoftwoapproaches |