Impact of Environmental Factors on Water Body Segmentation: A Study of Deep Learning Models
DOI:
https://doi.org/10.47611/jsrhs.v13i4.8392Keywords:
Water Body Segmentation, Remote Sensing, Night Lighting Images, Data Augmentation, Selective Slicing, Segmentation ModelsAbstract
Water body segmentation is a critical task in remote sensing and environmental monitoring, with applications
ranging from flood management to natural resource assessment. This task is complex due to many factors such as
water color, vegetation, and land type variations. One major and often neglected challenge is the impact of night
lighting conditions. In this paper, we present a novel dataset specifically designed to enhance performance under
diverse conditions especially with nighttime scenarios. Utilizing nighttime imagery offers advantages such as
reduced solar reflection, minimized glare, and clearer detection of water boundaries, which can be particularly
useful during periods of haze, cloud cover, or when daytime observations are limited. Our methodology includes the
collection, annotation, augmentation, and performing selective slicing on this dataset, followed by the training and evaluation of advanced
segmentation models. The results demonstrate significant improvements in model performance, including accuracy,
IoU, and precision, across various scenarios, particularly in handling previously challenging conditions. This work
helps advance the state of water body segmentation and provides a valuable resource for future research in
environmental monitoring and remote sensing.
Downloads
References or Bibliography
Miao, Z., Fu, K., Sun, H., Sun, X., & Yan, M. (2018). Automatic water-body segmentation from high-resolution satellite images via deep networks. IEEE geoscience and remote sensing letters, 15(4), 602-606. https://doi.org/10.1109/LGRS.2018.2794545
Wang, Z., Gao, X., Zhang, Y., & Zhao, G. (2020). MSLWENet: A novel deep learning network for lake water body extraction of Google remote sensing images. Remote Sensing, 12(24), 4140. https://doi.org/10.3390/rs12244140
Lv, S., Meng, L., Edwing, D., Xue, S., Geng, X., & Yan, X. H. (2022). High-performance segmentation for flood mapping of hisea-1 sar remote sensing images. Remote Sensing, 14(21), 5504. https://doi.org/10.3390/rs14215504
Zhang, Z., Lu, M., Ji, S., Yu, H., & Nie, C. (2021). Rich CNN features for water-body segmentation from very high resolution aerial and satellite imagery. Remote Sensing, 13(10), 1912. https://doi.org/10.3390/rs13101912
Yuan, K., Zhuang, X., Schaefer, G., Feng, J., Guan, L., & Fang, H. (2021). Deep-learning-based multispectral satellite image segmentation for water body detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 7422-7434. https://doi.org/10.1109/JSTARS.2021.3098678
Wieland, M., Fichtner, F., Martinis, S., Groth, S., Krullikowski, C., Plank, S., & Motagh, M. (2023). S1S2-Water: A global dataset for semantic segmentation of water bodies from Sentinel-1 and Sentinel-2 satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/JSTARS.2023.3333969
Yang, X., Chen, Y., & Wang, J. (2020). Combined use of Sentinel-2 and Landsat 8 to monitor water surface area dynamics using Google Earth Engine. Remote Sensing Letters, 11(7), 687-696. https://doi.org/10.1080/2150704X.2020.1757780
Li, K., Wang, J., Cheng, W., Wang, Y., Zhou, Y., & Altansukh, O. (2022). Deep learning empowers the Google Earth Engine for automated water extraction in the Lake Baikal Basin. International Journal of Applied Earth Observation and Geoinformation, 112, 102928 https://doi.org/10.1016/j.jag.2022.102928
Chatterjee, R., Chatterjee, A., & Islam, S. H. (2022). Deep learning techniques for observing the impact of the global warming from satellite images of water-bodies. Multimedia Tools and Applications, 81(5), 6115-6130. https://doi.org/10.1007/s11042-021-11811-1
Pai, M. M., Mehrotra, V., Verma, U., & Pai, R. M. (2020). Improved semantic segmentation of water bodies and land in SAR images using generative adversarial networks. International Journal of Semantic Computing, 14(01), 55-69. https://doi.org/10.1142/S1793351X20400036
Li, L., Yan, Z., Shen, Q., Cheng, G., Gao, L., & Zhang, B. (2019). Water body extraction from very high spatial resolution remote sensing data based on fully convolutional networks. Remote Sensing, 11(10), 1162. https://doi.org/10.3390/rs11101162
Ch, A., Ch, R., Gadamsetty, S., Iwendi, C., Gadekallu, T. R., & Dhaou, I. B. (2022). ECDSA-based water bodies prediction from satellite images with UNet. Water, 14(14), 2234. https://doi.org/10.3390/w14142234
Tambe, R. G., Talbar, S. N., & Chavan, S. S. (2021). Deep multi-feature learning architecture for water body segmentation from satellite images. Journal of Visual Communication and Image Representation, 77, 103141. https://doi.org/10.1016/j.jvcir.2021.103141
Dang, B., & Li, Y. (2021). MSResNet: Multiscale residual network via self-supervised learning for water-body detection in remote sensing imagery. Remote Sensing, 13(16), 3122. https://doi.org/10.3390/rs13163122
Li, Z., Wang, R., Zhang, W., Hu, F., & Meng, L. (2019). Multiscale features supported DeepLabV3+ optimization scheme for accurate water semantic segmentation. Ieee Access, 7, 155787-155804. https://doi.org/10.1109/ACCESS.2019.2949635
Maiti, A., Oude Elberink, S. J., & Vosselman, G. (2022). Effect of label noise in semantic segmentation of high resolution aerial images and height data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2, 275-282. https://doi.org/10.5194/isprs-annals-V-2-2022-275-2022
Published
How to Cite
Issue
Section
Copyright (c) 2024 Siddharth Karthikeyan; Vidya Rao
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
