Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning
Image-based river flow measurement methods have been attracting attention because of their ease of use and safety. Among the image-based methods, the space-time image velocimetry (STIV) technique is regarded as a powerful tool for measuring the streamwise flow because of its high measurement accurac...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/15/2079 |
| _version_ | 1797525122082406400 |
|---|---|
| author | Ken Watanabe Ichiro Fujita Makiko Iguchi Makoto Hasegawa |
| author_facet | Ken Watanabe Ichiro Fujita Makiko Iguchi Makoto Hasegawa |
| author_sort | Ken Watanabe |
| collection | DOAJ |
| description | Image-based river flow measurement methods have been attracting attention because of their ease of use and safety. Among the image-based methods, the space-time image velocimetry (STIV) technique is regarded as a powerful tool for measuring the streamwise flow because of its high measurement accuracy and robustness. However, depending on the image shooting environment such as stormy weather or nighttime, the conventional automatic analysis methods may generate incorrect values, which has been a problem in building a real-time measurement system. In this study, we tried to solve this problem by incorporating the deep learning method, which has been successful in the field of image analysis in recent years, into the STIV method. The case studies for the three datasets indicated that deep learning can improve the efficiency of the STIV method and can continuously improve performance by learning additional data. The proposed method is suitable for building a real-time measurement system because it has no tuning parameters that need to be adjusted according to the shooting conditions and the calculation speed is fast enough for real-time measurement. |
| first_indexed | 2024-03-10T09:07:18Z |
| format | Article |
| id | doaj.art-7c8f1ace198246f88f3bf509d79cb56f |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T09:07:18Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-7c8f1ace198246f88f3bf509d79cb56f2023-11-22T06:20:03ZengMDPI AGWater2073-44412021-07-011315207910.3390/w13152079Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep LearningKen Watanabe0Ichiro Fujita1Makiko Iguchi2Makoto Hasegawa3Hydro Technology Institute Co., Ltd., Osaka 5306126, JapanConstruction Engineering Research Institute, Kobe 6570011, JapanHydro Technology Institute Co., Ltd., Osaka 5306126, JapanHydro Technology Institute Co., Ltd., Osaka 5306126, JapanImage-based river flow measurement methods have been attracting attention because of their ease of use and safety. Among the image-based methods, the space-time image velocimetry (STIV) technique is regarded as a powerful tool for measuring the streamwise flow because of its high measurement accuracy and robustness. However, depending on the image shooting environment such as stormy weather or nighttime, the conventional automatic analysis methods may generate incorrect values, which has been a problem in building a real-time measurement system. In this study, we tried to solve this problem by incorporating the deep learning method, which has been successful in the field of image analysis in recent years, into the STIV method. The case studies for the three datasets indicated that deep learning can improve the efficiency of the STIV method and can continuously improve performance by learning additional data. The proposed method is suitable for building a real-time measurement system because it has no tuning parameters that need to be adjusted according to the shooting conditions and the calculation speed is fast enough for real-time measurement.https://www.mdpi.com/2073-4441/13/15/2079river flow measurementsurface flowSTIVdeep learningimage analysis |
| spellingShingle | Ken Watanabe Ichiro Fujita Makiko Iguchi Makoto Hasegawa Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning Water river flow measurement surface flow STIV deep learning image analysis |
| title | Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning |
| title_full | Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning |
| title_fullStr | Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning |
| title_full_unstemmed | Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning |
| title_short | Improving Accuracy and Robustness of Space-Time Image Velocimetry (STIV) with Deep Learning |
| title_sort | improving accuracy and robustness of space time image velocimetry stiv with deep learning |
| topic | river flow measurement surface flow STIV deep learning image analysis |
| url | https://www.mdpi.com/2073-4441/13/15/2079 |
| work_keys_str_mv | AT kenwatanabe improvingaccuracyandrobustnessofspacetimeimagevelocimetrystivwithdeeplearning AT ichirofujita improvingaccuracyandrobustnessofspacetimeimagevelocimetrystivwithdeeplearning AT makikoiguchi improvingaccuracyandrobustnessofspacetimeimagevelocimetrystivwithdeeplearning AT makotohasegawa improvingaccuracyandrobustnessofspacetimeimagevelocimetrystivwithdeeplearning |