ABSTRACT
Water Body Extraction (WBE) is a challenging task in remote sensing, owing to the complexity of recognizing surface body objects with rich texture, spatial, spectral, temporal, and radiometric features. The use of spectral indices has shown to be successful in separating surface water from its surroundings at the cost of knowledge of appropriate threshold values. In the absence of knowledge on threshold values, extracting the water from remote sensing data is challenging, which is addressed by several Machine Learning (ML) and Deep Learning (DL) algorithms. However, the effectiveness of both ML and DL classifications is witnessed from visual features to semantic categories at the cost of distinct recognition between the water body and non-water body features. In this paper, a novel Multi Scale Feature Extraction Network (MSFEN) for extracting the pixel-level features from medium resolution remote sensing images is proposed and used traditional ML classifiers to extract the surface water bodies using pixel-level features extracted by MSFEN. The proposed framework is trained and tested on Linear Imaging Self Scanning Sensor – III (LISS-III) multispectral satellite images over major water reservoirs in Tamilnadu, Karnataka, Madhya Pradesh, and Odisha. Experimental results indicate that the proposed model MSFEN+SVM provides accurate extraction results by outperforming the existing state-of-the-art models (Fully Convolutional Network (FCN), Unet, SegNet, Multi Scale Convolutional Neural Network (MSCNN), Deepwater Map, Pyramid Scene Parsing Network (PSPNet), Improved PSPNet, Multi-scale Water Extraction Convolutional Neural Network (MWEN) and Multi-Scale Lake Water Extraction Network (MSLWENet) in terms of performance metrics considered.
Highlights
The combined textural features from the proposed Multi Scale Feature Extraction Network (MSFEN) have fine and coarse pixel-level features that enable the Machine Learning (ML) classifiers for accurate water body extraction.
The proposed MSFEN with machine learning can determine the extent of water reservoirs in rainy and dry seasons.
The proposed network requires fewer training parameters for better feature extraction than state-of-the-art methods.
The MSFEN with Support Vector Machine (SVM) provides better quantitative results than other combinations of MSFEN with ML classifiers.
Acknowledgements
We thank National Remote Sensing Center (NRSC), Hyderabad, Indian Space Research Organisation (ISRO), India, for providing the Resourcesat-2: LISS-III image data for educational purposes. We also thank the National Institute of Technology Puducherry, Karaikal, India, for providing research facilities in this area. We are grateful to the anonymous reviewers for their constructive comments and suggestions which improved the quality of this paper.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
The datasets used in this paper are publicly available and downloaded from National Remote Sensing Center (NRSC), Hyderabad, Indian Space Research Organisation (ISRO), India. Since the datasets are available publicly, the authors are requested to access them through the link https://bhuvan-app3.nrsc.gov.in/data/download/index.php. The images used for the research purposes are shown in the manuscript.