Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera
The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to ident...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/20/9691 |
| _version_ | 1797515375004352512 |
|---|---|
| author | Nur Atirah Muhadi Ahmad Fikri Abdullah Siti Khairunniza Bejo Muhammad Razif Mahadi Ana Mijic |
| author_facet | Nur Atirah Muhadi Ahmad Fikri Abdullah Siti Khairunniza Bejo Muhammad Razif Mahadi Ana Mijic |
| author_sort | Nur Atirah Muhadi |
| collection | DOAJ |
| description | The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and <i>IoU</i> metrics, and around 80% for boundary F1 score (<i>BF score</i>), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than the results from the SegNet network. Therefore, the DeepLabv3+ network was used for practical application using a set of images captured at five consecutive days in the study area. The segmentation result and water level markers extracted from light detection and ranging (LiDAR) data were overlaid to estimate river water levels and observe the water fluctuation. River water levels were predicted based on the elevation from the predefined markers. The proposed water level framework was evaluated according to Spearman’s rank-order correlation coefficient. The correlation coefficient was 0.91, which indicates a strong relationship between the estimated water level and observed water level. Based on these findings, it can be concluded that the proposed approach has high potential as an alternative monitoring system that offers water region information and water level estimation for flood management and related activities. |
| first_indexed | 2024-03-10T06:44:36Z |
| format | Article |
| id | doaj.art-b543abe48ed8417cb58963675d23c2af |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T06:44:36Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b543abe48ed8417cb58963675d23c2af2023-11-22T17:22:48ZengMDPI AGApplied Sciences2076-34172021-10-011120969110.3390/app11209691Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance CameraNur Atirah Muhadi0Ahmad Fikri Abdullah1Siti Khairunniza Bejo2Muhammad Razif Mahadi3Ana Mijic4Department of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Civil and Environmental Engineering, South Kensington Campus, Imperial College London, London SW7 2AZ, UKThe interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and <i>IoU</i> metrics, and around 80% for boundary F1 score (<i>BF score</i>), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than the results from the SegNet network. Therefore, the DeepLabv3+ network was used for practical application using a set of images captured at five consecutive days in the study area. The segmentation result and water level markers extracted from light detection and ranging (LiDAR) data were overlaid to estimate river water levels and observe the water fluctuation. River water levels were predicted based on the elevation from the predefined markers. The proposed water level framework was evaluated according to Spearman’s rank-order correlation coefficient. The correlation coefficient was 0.91, which indicates a strong relationship between the estimated water level and observed water level. Based on these findings, it can be concluded that the proposed approach has high potential as an alternative monitoring system that offers water region information and water level estimation for flood management and related activities.https://www.mdpi.com/2076-3417/11/20/9691flood detectiondeep learningwater level estimationwater segmentationCCTVCNN |
| spellingShingle | Nur Atirah Muhadi Ahmad Fikri Abdullah Siti Khairunniza Bejo Muhammad Razif Mahadi Ana Mijic Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera Applied Sciences flood detection deep learning water level estimation water segmentation CCTV CNN |
| title | Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera |
| title_full | Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera |
| title_fullStr | Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera |
| title_full_unstemmed | Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera |
| title_short | Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera |
| title_sort | deep learning semantic segmentation for water level estimation using surveillance camera |
| topic | flood detection deep learning water level estimation water segmentation CCTV CNN |
| url | https://www.mdpi.com/2076-3417/11/20/9691 |
| work_keys_str_mv | AT nuratirahmuhadi deeplearningsemanticsegmentationforwaterlevelestimationusingsurveillancecamera AT ahmadfikriabdullah deeplearningsemanticsegmentationforwaterlevelestimationusingsurveillancecamera AT sitikhairunnizabejo deeplearningsemanticsegmentationforwaterlevelestimationusingsurveillancecamera AT muhammadrazifmahadi deeplearningsemanticsegmentationforwaterlevelestimationusingsurveillancecamera AT anamijic deeplearningsemanticsegmentationforwaterlevelestimationusingsurveillancecamera |