Estimating the spatial-temporal distribution of urban street ponding levels from surveillance videos based on computer vision

Xin Hao, Heng Lyu (), Ze Wang, Shengnan Fu and Chi Zhang
Additional contact information
Xin Hao: Dalian University of Technology
Heng Lyu: Purdue University
Ze Wang: Dalian University of Technology
Shengnan Fu: Dalian University of Technology
Chi Zhang: Dalian University of Technology

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2022, vol. 36, issue 6, No 4, 1799-1812

Abstract: Abstract Timely and accurately estimating ponding levels during urban floods is the basis of effective disaster prevention and mitigation. Road surveillance videos record the urban flood process as images, and computer vision technology brings new opportunities for extracting ponding information from image data. This study proposes a computer vision-based method for estimating the spatial-temporal distribution of urban street ponding levels from surveillance videos. First, a dataset of sedan images compiled from three sources was collected to train an object detection algorithm, You Only Look Once vision 3 (YOLOv3). Then, the trained model was adopted to identify the ponding levels whenever and wherever sedans were detected from the videos. Second, outlier detection was employed to detect and delete the outliers of ponding levels in each time step. Finally, the ponding level distribution was estimated by inverse distance weighted from the remaining ponding level points. This method was employed for two pluvial flood events at a street crossing, Dongguan Street, in Dalian, China. The mean average precision (mAP) of the trained YOLOv3 model reached 78%, which confirmed the validity of the model. The ponding levels estimated by our method were validated with the submerged depth of a static reference, and the ponding process had a strong correlation with the rainfall time series. Outlier detection improved the accuracy of ponding level estimation in cross-validation to 88% on average. The results can be used to analyze the progress of urban flood evolution, which contributes to arranging drainage facilities and improving urban flood management.

Keywords: Urban flood; Ponding level distribution; Computer vision; Object detection; Surveillance video (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-022-03107-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:waterr:v:36:y:2022:i:6:d:10.1007_s11269-022-03107-2

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-022-03107-2

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().