# Detecting floodwater on roadways from image data with handcrafted features and deep transfer learning

arXiv: https://arxiv.org/abs/1909.00125 · HTML: https://mlsanity.com/paper/1909.00125/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images](https://mlsanity.com/paper/2111.11567/) (2021)
- [An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities](https://mlsanity.com/paper/2205.07073/) (2022)
- [A Universal Railway Obstacle Detection System based on Semi-supervised Segmentation And Optical Flow](https://mlsanity.com/paper/2406.18908/) (2024)
- [Urban Waterlogging Detection: A Challenging Benchmark and Large-Small Model Co-Adapter](https://mlsanity.com/paper/2407.08109/) (2024)
- [Automated urban waterlogging assessment and early warning through a mixture of foundation models](https://mlsanity.com/paper/2510.18425/) (2025)
- [Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation](https://mlsanity.com/paper/2608.07562/) (2026)

## Abstract (arXiv)

Detecting roadway segments inundated due to floodwater has important applications for vehicle routing and traffic management decisions. This paper proposes a set of algorithms to automatically detect floodwater that may be present in an image captured by mobile phones or other types of optical cameras. For this purpose, image classification and flood area segmentation methods are developed. For the classification task, we used Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG) and pre-trained deep neural network (VGG-16) as feature extractors and trained logistic regression, k-nearest neighbors, and decision tree classifiers on the extracted features. Pre-trained VGG-16 network with logistic regression classifier outperformed all other methods. For the flood area segmentation task, we investigated superpixel based methods and Fully Convolutional Neural Network (FCN). Similar to the classification task, we trained logistic regression and k-nearest neighbors classifiers on the superpixel areas and compared that with an end-to-end trained FCN. Conditional Random Fields (CRF) method was applied after both segmentation methods to post-process coarse segmentation results. FCN offered the highest scores in all metrics; it was followed by superpixel-based logistic regression and then superpixel-based KNN.