Authors : Machineni Yasaswini; Nallabothu Amrith; Dr. U. M. Prakash

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/mr7kry6s

Scribd : https://tinyurl.com/37p5a9h7

DOI : https://doi.org/10.38124/ijisrt/26mar1911

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Land cover mapping from satellite image is an important task in remote sensing for the applications such as environmental monitoring, urban planning, agriculture management and disaster assessment. However, it is difficult to extract meaningful data from high-resolution satellite images because of variation in illumination, complex terrain structures, and the fact that multiple land cover categories are contained in a single image. This research presents a proposal for a deep learning-based model of semantic segmentation of satellite imagery, based on encoder-decoder convolutional neural network architectures, namely U-Net and ResUNet-a. The system is used for pixel wise classification in order to identify the classes of land cover such as buildings, roads, vegetation, water bodies, land, and Unlabeled regions. The framework has programming stages for data preprocessing, model training, prediction, and visualization of the segmentation outputs. A web application based on Streamlit is also created to enable interactive viewing of segmentation results after users upload satellite images. Experimental results show accuracy of segmentation and enhanced boundary detection using the proposed models for land cover automated analysis.

References :

1. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Net- works for Biomedical Image Segmentation,” Springer, 2015.
2. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” IEEE, 2016.
3. Z. Zhang et al., “Deep Learning Based Land Cover Classification Using Satellite Imagery,” IEEE, 2020.
4. L. Ma, Y. Liu, and X. Zhang, “Deep Learning in Remote Sensing Applications,” ISPRS Journal, 2019.
5. X. X. Zhu et al., “Deep Learning in Remote Sensing: A Review,” IEEE GRSM, 2017.
6. J. Long, E. Shelhamer, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
7. V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017.
8. L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking Atrous Convolution for Semantic Image Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
9. M. Kampffmeyer, A. Salberg, and R. Jenssen, “Semantic Segmentation of Small Objects and Modeling of Uncertainty in Urban Remote Sensing Images Using Deep Convolutional Neural Networks,” IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2016.
10. G. Marmanis, M. Datcu, T. Esch, and U. Stilla, “Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks,” IEEE Geoscience and Remote Sensing Letters, 2016.