Published on Sat Aug 31 2019

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

Cem Sazara, Mecit Cetin, Khan M. Iftekharuddin

This paper proposes a set of algorithms to automatically detect floodwater that may be present in an image captured by mobile phones. Detecting roadway segments inundated due to floodwater has important applications for vehicle routing and traffic management decisions.

0
0
0
Abstract

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.

Mon Oct 14 2019
Computer Vision
Encoder-Decoder based CNN and Fully Connected CRFs for Remote Sensed Image Segmentation
A deep Convolutional Neural Network (CNN) is employed for the 2D semantic segmentation of most common land cover object classes. The proposed CNN-FCRF model achieves an overall accuracy of 90.5% on the ISPRS Vaihingen Dataset.
0
0
0
Wed Oct 16 2019
Computer Vision
Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3
The problem of car detection from aerial images using Convolutional Neural Networks (CNN) presents additional challenges as compared to car (or any object) detection from ground images. We assess the performance of two state-of-the-art CNN algorithms.
1
0
1
Sun Oct 20 2019
Machine Learning
Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses
Automated pavement distresses detection using road images remains achallenging topic in the computer vision research community. In this study, a labeled dataset approach is introduced as a first step towards a more robust, easy-to-deploy pavement condition assessment system. The dataset consists of images captured from two camera views of an identical pavement segment.
0
0
0
Fri Mar 10 2017
Computer Vision
Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks
A deep learning approach has been developed to carry out road worrisomedetection using only LIDAR data. The proposed system achieved excellent performance and it is among the top-performing algorithms on the KITTI road benchmark.
0
0
0
Tue May 12 2020
Machine Learning
Very High Resolution Land Cover Mapping of Urban Areas at Global Scale with Convolutional Neural Networks
The objective is to make a segmentation map of a large area (a french department) with the following classes: asphalt, bare soil, building,grassland, mineral material (permeable artificialized areas), forest and water.
0
0
0
Fri Jul 21 2017
Computer Vision
Learning Aerial Image Segmentation from Online Maps
Deep learning methods are extremely data-hungry, aggravating the perennial bottleneck of supervised classification. This study deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel.
0
0
0