Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach
The efficient and reliable monitoring of the flow of water in open channels provides useful information for preventing water slow-downs due to the deposition of materials within the bed of the channel, which might lead to critical floods. A reliable monitoring system can thus help to protect propert...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/12/4197 |
| _version_ | 1797529643120590848 |
|---|---|
| author | Aimé Lay-Ekuakille John Djungha Okitadiowo Moïse Avoci Ugwiri Sabino Maggi Rita Masciale Giuseppe Passarella |
| author_facet | Aimé Lay-Ekuakille John Djungha Okitadiowo Moïse Avoci Ugwiri Sabino Maggi Rita Masciale Giuseppe Passarella |
| author_sort | Aimé Lay-Ekuakille |
| collection | DOAJ |
| description | The efficient and reliable monitoring of the flow of water in open channels provides useful information for preventing water slow-downs due to the deposition of materials within the bed of the channel, which might lead to critical floods. A reliable monitoring system can thus help to protect properties and, in the most critical cases, save lives. A sensing system capable of monitoring the flow conditions and the possible geo-environmental constraints within a channel can operate using still images or video imaging. The latter approach better supports the above two features, but the acquisition of still images can display a better accuracy. To increase the accuracy of the video imaging approach, we propose an improved particle tracking algorithm for flow hydrodynamics supported by a machine learning approach based on a convolutional neural network-evolutionary fuzzy integral (CNN-EFI), with a sub-comparison performed by multi-layer perceptron (MLP). Both algorithms have been applied to process the video signals captured from a CMOS camera, which monitors the water flow of a channel that collects rain water from an upstream area to discharge it into the sea. The channel plays a key role in avoiding upstream floods that might pose a serious threat to the neighboring infrastructures and population. This combined approach displays reliable results in the field of environmental and hydrodynamic safety. |
| first_indexed | 2024-03-10T10:16:39Z |
| format | Article |
| id | doaj.art-82a61fd47c304f95be0ddbfab6747328 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:16:39Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-82a61fd47c304f95be0ddbfab67473282023-11-22T00:44:42ZengMDPI AGSensors1424-82202021-06-012112419710.3390/s21124197Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning ApproachAimé Lay-Ekuakille0John Djungha Okitadiowo1Moïse Avoci Ugwiri2Sabino Maggi3Rita Masciale4Giuseppe Passarella5Department of Innovation Engineering, University of Salento, 73100 Lecce, ItalyDepartment of Information Engineering, Infrastructure and Sustainable Energy (DIIES), University “Mediterranean” of Reggio Calabria, 89124 Reggio Calabria, ItalyDepartment of Industrial Engineering, University of Salerno, 84084 Fisciano, ItalyCNR, National Research Council, Institute of Atmospheric Pollution Research, 70126 Bari, ItalyCNR, National Research Council, Water Research Institute, 70132 Bari, ItalyCNR, National Research Council, Water Research Institute, 70132 Bari, ItalyThe efficient and reliable monitoring of the flow of water in open channels provides useful information for preventing water slow-downs due to the deposition of materials within the bed of the channel, which might lead to critical floods. A reliable monitoring system can thus help to protect properties and, in the most critical cases, save lives. A sensing system capable of monitoring the flow conditions and the possible geo-environmental constraints within a channel can operate using still images or video imaging. The latter approach better supports the above two features, but the acquisition of still images can display a better accuracy. To increase the accuracy of the video imaging approach, we propose an improved particle tracking algorithm for flow hydrodynamics supported by a machine learning approach based on a convolutional neural network-evolutionary fuzzy integral (CNN-EFI), with a sub-comparison performed by multi-layer perceptron (MLP). Both algorithms have been applied to process the video signals captured from a CMOS camera, which monitors the water flow of a channel that collects rain water from an upstream area to discharge it into the sea. The channel plays a key role in avoiding upstream floods that might pose a serious threat to the neighboring infrastructures and population. This combined approach displays reliable results in the field of environmental and hydrodynamic safety.https://www.mdpi.com/1424-8220/21/12/4197sensorssensing systemshydrodynamic monitoringflow measurement and classificationmachine learningparticle tracking |
| spellingShingle | Aimé Lay-Ekuakille John Djungha Okitadiowo Moïse Avoci Ugwiri Sabino Maggi Rita Masciale Giuseppe Passarella Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach Sensors sensors sensing systems hydrodynamic monitoring flow measurement and classification machine learning particle tracking |
| title | Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach |
| title_full | Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach |
| title_fullStr | Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach |
| title_full_unstemmed | Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach |
| title_short | Video-Sensing Characterization for Hydrodynamic Features: Particle Tracking-Based Algorithm Supported by a Machine Learning Approach |
| title_sort | video sensing characterization for hydrodynamic features particle tracking based algorithm supported by a machine learning approach |
| topic | sensors sensing systems hydrodynamic monitoring flow measurement and classification machine learning particle tracking |
| url | https://www.mdpi.com/1424-8220/21/12/4197 |
| work_keys_str_mv | AT aimelayekuakille videosensingcharacterizationforhydrodynamicfeaturesparticletrackingbasedalgorithmsupportedbyamachinelearningapproach AT johndjunghaokitadiowo videosensingcharacterizationforhydrodynamicfeaturesparticletrackingbasedalgorithmsupportedbyamachinelearningapproach AT moiseavociugwiri videosensingcharacterizationforhydrodynamicfeaturesparticletrackingbasedalgorithmsupportedbyamachinelearningapproach AT sabinomaggi videosensingcharacterizationforhydrodynamicfeaturesparticletrackingbasedalgorithmsupportedbyamachinelearningapproach AT ritamasciale videosensingcharacterizationforhydrodynamicfeaturesparticletrackingbasedalgorithmsupportedbyamachinelearningapproach AT giuseppepassarella videosensingcharacterizationforhydrodynamicfeaturesparticletrackingbasedalgorithmsupportedbyamachinelearningapproach |