Detection and Estimation of Inundation and Associated Risks using Traffic Monitoring Cameras and High-Resolution Flood Maps
| 项目名称： | Detection and Estimation of Inundation and Associated Risks using Traffic Monitoring Cameras and High-Resolution Flood Maps |
| 摘要： | During extreme flooding such as Hurricane Harvey, photo images from traffic monitoring cameras provide critical information, sometimes as the only reliable source, to identify whether or not a road is flooded. The advent of new image processing and filtering technologies has enabled us to extract extent of inundation from low-resolution photos with reasonable accuracy. Despite the high potential, however, the images from traffic monitoring systems have yet to be investigated to extract more accurate flood information using objective and automatic ways. The main objective of this project is to develop an inundation detection and evaluation framework using images from traffic monitoring cameras and high-resolution flood maps under extreme precipitation conditions. A new Bayesian filtering method will be devised to detect occurrence of flooding and extract inundation extent from low-resolution images taken by the existing traffic monitoring cameras during the extreme events. High-resolution urban flood modeling will produce street-resolving flood maps based on multiple extreme precipitation frequencies. Capability of the filtering algorithm and the flood model will be demonstrated for the past extreme event (e.g. Hurricane Harvey) at a city scale (e.g. the Downtown Houston areas). |
| 状态： | Completed |
| 资金： | 110000 |
| 资助组织： | Office of the Assistant Secretary for Research and Technology |
| 项目负责人： | Melson, Christopher |
| 执行机构： | University of Texas at Arlington |
| 开始时间： | 20190815 |
| 预计完成日期： | 20210215 |
| 主题领域： | Data and Information Technology；Highways；Operations and Traffic Management；Planning and Forecasting；Security and Emergencies |
相关文献
- Cooperating Camera Platforms for Ultra High-Resolution Tracking of Traffic
- High-Resolution Micro Traffic Data from Roadside LiDAR Sensors for Connected-Vehicles and New Traffic Applications
- A Machine Learning-Based System for Predicting Peak Flowrates of Nebraska Streams
- Investigating Relationship Between Driving Patterns and Traffic Safety Using Smartphones Based Mobile Sensor Data
- Evaluating Bridge Behavior Using Ultra-High Resolution Next-Generation Digital Image Correlation (DIC): Applications in Bridge Inspection and Damage Assessment
- FloodCast: A Framework for Enhanced Flood Event Decision Making for Transportation Resilience
检索历史
应用推荐
