Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method
Flood depth monitoring is crucial for flood warning systems and damage control, especially in the event of an urban flood. Existing gauge station data and remote sensing data still has limited spatial and temporal resolution and coverage. Therefore, to expand flood depth data source taking use of on...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/16/5614 |
| _version_ | 1797522025447686144 |
|---|---|
| author | Zhiqing Song Ye Tuo |
| author_facet | Zhiqing Song Ye Tuo |
| author_sort | Zhiqing Song |
| collection | DOAJ |
| description | Flood depth monitoring is crucial for flood warning systems and damage control, especially in the event of an urban flood. Existing gauge station data and remote sensing data still has limited spatial and temporal resolution and coverage. Therefore, to expand flood depth data source taking use of online image resources in an efficient manner, an automated, low-cost, and real-time working frame called FloodMask was developed to obtain flood depth from online images containing flooded traffic signs. The method was built on the deep learning framework of Mask R-CNN (regional convolutional neural network), trained by collected and manually annotated traffic sign images. Following further the proposed image processing frame, flood depth data were retrieved more efficiently than manual estimations. As the main results, the flood depth estimates from images (without any mirror reflection and other inference problems) have an average error of 0.11 m, when compared to human visual inspection measurements. This developed method can be further coupled with street CCTV cameras, social media photos, and on-board vehicle cameras to facilitate the development of a smart city with a prompt and efficient flood monitoring system. In future studies, distortion and mirror reflection should be tackled properly to increase the quality of the flood depth estimates. |
| first_indexed | 2024-03-10T08:23:42Z |
| format | Article |
| id | doaj.art-b6451f07c20048bc9c4faf420898fb14 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T08:23:42Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b6451f07c20048bc9c4faf420898fb142023-11-22T09:42:49ZengMDPI AGSensors1424-82202021-08-012116561410.3390/s21165614Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based MethodZhiqing Song0Ye Tuo1Department of Civil, Geo and Environmental Engineering, Technical University of Munich, Arcisstrasse 21, 80333 Munich, GermanyDepartment of Civil, Geo and Environmental Engineering, Technical University of Munich, Arcisstrasse 21, 80333 Munich, GermanyFlood depth monitoring is crucial for flood warning systems and damage control, especially in the event of an urban flood. Existing gauge station data and remote sensing data still has limited spatial and temporal resolution and coverage. Therefore, to expand flood depth data source taking use of online image resources in an efficient manner, an automated, low-cost, and real-time working frame called FloodMask was developed to obtain flood depth from online images containing flooded traffic signs. The method was built on the deep learning framework of Mask R-CNN (regional convolutional neural network), trained by collected and manually annotated traffic sign images. Following further the proposed image processing frame, flood depth data were retrieved more efficiently than manual estimations. As the main results, the flood depth estimates from images (without any mirror reflection and other inference problems) have an average error of 0.11 m, when compared to human visual inspection measurements. This developed method can be further coupled with street CCTV cameras, social media photos, and on-board vehicle cameras to facilitate the development of a smart city with a prompt and efficient flood monitoring system. In future studies, distortion and mirror reflection should be tackled properly to increase the quality of the flood depth estimates.https://www.mdpi.com/1424-8220/21/16/5614flood depthwater leveldeep learninginstance segmentationcomputer visionflood monitoring |
| spellingShingle | Zhiqing Song Ye Tuo Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method Sensors flood depth water level deep learning instance segmentation computer vision flood monitoring |
| title | Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method |
| title_full | Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method |
| title_fullStr | Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method |
| title_full_unstemmed | Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method |
| title_short | Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method |
| title_sort | automated flood depth estimates from online traffic sign images explorations of a convolutional neural network based method |
| topic | flood depth water level deep learning instance segmentation computer vision flood monitoring |
| url | https://www.mdpi.com/1424-8220/21/16/5614 |
| work_keys_str_mv | AT zhiqingsong automatedflooddepthestimatesfromonlinetrafficsignimagesexplorationsofaconvolutionalneuralnetworkbasedmethod AT yetuo automatedflooddepthestimatesfromonlinetrafficsignimagesexplorationsofaconvolutionalneuralnetworkbasedmethod |