Computer Vision-Based Estimation of Flood Depth in Flooded-Vehicle Images

Somin Park, Francis Baek, Jiu Sohn, Hyoungkwan Kim

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)


This study proposes a vision-based method for flood depth estimation using flooded-vehicle images with a ground-level view. The proposed method is comprised of three main processes: segmentation of vehicle objects, cross-domain image retrieval, and estimation of flood depth. First, Mask region-based convolution neural network (R-CNN) is used to detect flooded vehicles in flooding images. Second, on the basis of feature maps from VGGNets, dynamic feature space selection is employed to select a three-dimensional (3D) rendered car image most similar to the flooded object using the metric of cosine distance. Finally, the flood depth is calculated through a comparison of the flooded object and the 3D rendered image. The feature maps from Pooling layer 4 of VGG19, under the condition of a cosine distance of <0.55, produces an average error of 7.51 pixels, corresponding to 9.40% of the tire height. A total of 500 flooding images are used to validate the method.

Original languageEnglish
Article number04020072
JournalJournal of Computing in Civil Engineering
Issue number2
Publication statusPublished - 2021 Mar 1

Bibliographical note

Funding Information:
This work was supported by National Research Foundation of Korea (NRF) grants from the Ministry of Science and ICT (Grant No. 2018R1A2B2008600) and the Ministry of Education (Grant No. 2018R1A6A1A08025348).

Publisher Copyright:
© 2020 American Society of Civil Engineers.

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Computer Science Applications


Dive into the research topics of 'Computer Vision-Based Estimation of Flood Depth in Flooded-Vehicle Images'. Together they form a unique fingerprint.

Cite this