Water Bodies Segmentation Through Satellite Images Using ResNet
Keywords:
Satellite imagery, ResNet, Semantic segmentation, Water body.Abstract
Images by the satellites are useful for analysing and managing water bodies. Precise segmentation of water bodies by the images from the satellites can be used for various purposes, including flood management, environmental monitoring, balancing ecosystem and for civilization. Although the existing UNets data efficiency is quite limited because of its huge amount of annotated data for training, which is costly and time dwelling. Computational requirements and memory usage can be increased by its symmetric architecture. It may struggle with global context, producing boundary artifacts. It also faces challenges with class imbalance, which can lead to biased predictions. It also consumes a lot of time for training. So for this purpose an innovative and effective method of water body segmentation is essential that is ResNet50, a DCNN design well known for its effectiveness in image recognition tasks. This is the approach utilizes hierarchical features learned by ResNet50 to precisely identify water bodies, from the images by satellites, among complex backgrounds. By combining preprocessing techniques, data augmentation, and fine-tuning of the ResNet50 model, the semantic segmentation performance can be increased. This work presents a proposed solution for satellite image monitoring of the water body. To accomplish this objective, we have introduced the ResNet model, this is a semantic segmentation model of an image. This method has successfully got through a validation accuracy of 96.02 % for water segmentation with an error of 20.22%. Additionally, we conduct comparative analyses with existing techniques to demonstrate the lead of proposed approach. This paper presents a promising solution for automating water bodies segmentation in satellite imagery, thereby enabling us to efficiently monitor and management of water resources on a large scale.
Downloads
References
Silmie Vidiya Fani; Kamirul; Astriany Noer; Stevry Yushady CH Bissa,”U-Net Based Water Region Segmentation for LAPAN-A2 MSI“, 2022 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES) , 30 December 2022.
O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention. Springer, 2015, pp. 234–241.
A. C. Sparavigna, “Image segmentation applied to satellite imagery for monitoring water in lakes and reservoirs,” PHILICA, Article, no. 1214, 2018.
W. Alsabhan and T. Alotaiby, “Automatic building extraction on satel lite images using unet and resnet50,” Computational Intelligence and Neuroscience, vol. 2022, 2022.
D. Filatov Ghulam Nabi Ahmad, Hassan Yar, “Forest and Water Bodies Segmentation Through Satellite Images Using U-Net”, Published in arXiv.org 12 July 2022,Environmental Science, Computer Science.
Kunhao Yuan , Xu Zhuang, Gerald Schaefer and Jianxin Feng, “Deep-Learning-Based Multispectral Satellite Image Segmentation for Water Body Detection” ,IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ,Volume: 14, pp. 7422 - 7434, July 2021.
Jinxiao Wang ,FangChen, Meimei Zhang and BoYu, “A New Deep Learning Framework in Glacial Lake Detection” , IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 19, pp. 20009052–9052, May 2022.
Lunhao Duan and Xiangyun Hu, “Multiscale Refinement Network for Water-Body Segmentation in High-Resolution Satellite Imagery”, IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 17, NO. 4, pp.686-690, APRIL 2020.
Wenying Du, Nengcheng Chen, and Dandan Liu,” Automatic Balloon Snake Method for Topology Adaptive Water Boundary Extraction”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,Volume: 10, Issue: 12, December 2017.
Furkan Isikdogan ,AlanC.Bovik,” Surface Water Mapping by Deep Learning”, IEEE Journal Of selected topics in applied earth observations and remote sensing, Vol. 10, NO.11, pp.4909-4918,NOVEMBER2017.
H.Hafizi and K.Kalkan,“Evaluationofobject-basedwaterbodyextraction approachesusinglandsat-8 imagery,” J. Aeronaut. SpaceTechnol., vol.13, no. 1, pp. 81–89, 2020.
Lingkui Meng, Zhiyuan Zhang, Wen Zhang, Jinan Ye And Chao Song, “An Automatic Extraction Method for Lakes and Reservoirs Using Satellite Images,” PHILICA, Article, no. 1214, 2018.
N. J. Singh and K. Nongmeikapam, “Semantic segmentation of satellite images using deep-unet,” Arabian Journal for Science and Engineering, pp. 1–13, 2022.
L. Weng, Y. Xu, M. Xia, Y. Zhang, J. Liu, and Y. Xu, “Water areas seg mentation from remote sensing images using a separable residual segnet network,” ISPRS International Journal of Geo-Information, vol. 9, no. 4, p. 256, 2020.
Kaplan, G.; Avdan, U. Object-based water body extraction model using Sentinel-2 satellite imagery. Eur. J. Remote Sens. 2017, 50, 137–143.
Anusha, C.; Rupa, C.; Samhitha, G. “Region based Detection of Ships from Remote Sensing Satellite Imagery using Deep Learning”. In Proceedings of the 2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM), Pradesh, India, 23–25 February 2022; pp. 118–122.
Erfani, S.M.H.; Wu, Z.; Wu, X.; Wang, S.; Goharian, E. ATLANTIS,”A benchmark for semantic segmentation of waterbody images”. Environ. Model. Softw. 2022, 149, 105333.
Rajyalakshmi, C.; Rao, K.R.M.; Rao, R.R. Compressed High Resolution Satellite Image Processing to Detect Water Bodies with Combined Bilateral Filtering and Threshold Techniques. Trait. Signal 2022, 39, 669–675.
K. He, X. Zhang, S. Ren, and J. Sun. „Deep Residual Learning for Image Recognition“. In: arXiv e-prints (2015). arXiv: 1512.03385.
K. He, X. Zhang, S. Ren, and J. Sun. ‘Identity Mappings in Deep Residual Networks“. In: arXiv e-prints (2016). arXiv: 1603.05027.
O. Ronneberger, P. Fischer, and T. Brox. „U-Net: Convolutional Networks for Biomedical Image Segmentation“. In: ArXiv e-prints (2015). arXiv: 1505.04597.
Z.Zhang,Q.Liu,andY.Wang.„RoadExtraction by DeepResidual U-Net“. In: ArXiv e-prints abs/1711.10684 (2017). arXiv: 1711.10684.
Kaiming Heetal.“Deep Residual Learning for Image Recognition”. In:CoRRabs/ . http://arxiv.org/abs/1512. 03385.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. Int. Conf. Med. Image Comput. Comput.- Assist. Intervention, 2015, pp. 234–241.
J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2015, pp. 3431–3440.
X. Huang, C. Xie, X. Fang, and L. Zhang, “Combining pixel-and object-based machine learning for identification of water-body types from urban high-resolution remote-sensing imagery,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 8, no. 5, pp. 2097–2110, May 2015.
M. Silveira and S. Heleno, “Separation between water and land in SAR images using region-based level sets,” IEEE Geosci. Remote Sens. Lett., vol. 6, no. 3, pp. 471–475, Jul. 2009.
G. L. Feyisa, H. Meilby, R. Fensholt, and S. R. Proud, “Automated water extraction index: A new technique for surface water mapping using landsat imagery,” Remote Sens. Environ., vol. 140, pp. 23–35, 2014.
S. Lu, B. Wu, N. Yan, and H. Wang, “Water body mapping method with HJ-1A/B satellite imagery,” Int. J. Appl. Earth Observ. Geoinf., vol. 13, no. 3, pp. 428–434, 2011.
W. Feng, H. Sui, W. Huang, C. Xu, and K. An, “Water body extraction from very high-resolution remote sensing imagery using deep U-Net and a super pixel-based conditional random field model,” IEEE Geosci. Remote Sens. Lett., vol. 16, no. 4, pp. 618–622, Apr. 2019.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
