Abstract
Semantic segmentation is used for identification of buildings, roads, vegetation cover, and water body detection in satellite images. Several state-of-the-art deep learning models investigated have a large number of parameters and are difficult to train on low-configuration machines. To resolve this issue, quadratic encoder–decoder (QuadED), and residual quadratic encoder–decoder (ResQuadED) enabled with quadratic convolutional (QuadConv2D) layer are proposed as novel architectures in this manuscript. In the experiments, it is observed that QuadED performs better for binary semantic segmentation and ResQuadED performs better for both binary and multi-class semantic segmentation. As a result, the QuadED achieves an IoU of 76.82%, and 87.57% for the architectures with 5,51,913 and 4,90,088 parameters on the MBRSC and Massachusetts datasets, respectively. The ResQuadED model achieves an IoU of 77.87%, and 89.27% for the architectures with 5,37,585 and 4,54,682 parameters on the MBRSC and Massachusetts datasets, respectively. These results reveal that ResQuadED architecture performs significantly better for the evaluation metrics with fewer parameters than QuadED and existing architectures.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03717-w/MediaObjects/11760_2024_3717_Fig7_HTML.png)
Similar content being viewed by others
References
Jiang, Y., Lu, Z., Li, S., Lei, Y., Chu, Q., Yin, X., et al.: Large-scale and high-resolution crop mapping in china using sentinel-2 satellite imagery. Agriculture 10(10), 433 (2020)
Buttar, P.K., Sachan, M.K.: Semantic segmentation of satellite images for crop type identification in smallholder farms. J. Supercomput. 80(2), 1367–1395 (2024)
Blaga, L., Ilieş, D.C., Wendt, J.A., Rus, I., Zhu, K., Dávid, L.D.: Monitoring forest cover dynamics using orthophotos and satellite imagery. Remote Sens. 15(12), 3168 (2023)
Warth, G., Braun, A., Assmann, O., Fleckenstein, K., Hochschild, V.: Prediction of socio-economic indicators for urban planning using VHR satellite imagery and spatial analysis. Remote Sens. 12(11), 1730 (2020)
Sirko, W., Kashubin, S., Ritter, M., Annkah, A., Bouchareb, Y.S.E., Dauphin, Y. et al.: Continental-scale building detection from high resolution satellite imagery. arXiv preprint arXiv:2107.12283 (2021)
Chaudhary, V., Buttar, P.K., Sachan, M.K.: Satellite imagery analysis for road segmentation using U-Net architecture. J. Supercomput. 78(10), 12710–12725 (2022)
Buttar, P.K., Sachan, M.K.: Generating land cover maps in semi-arid regions based on a 3D Semantic segmentation architecture using multi-temporal sentinel-2 satellite images: a case study of Ludhiana district in Punjab, India. Journal of the Indian Society of Remote Sensing, pp. 1–16 (2024)
Buttar, P.K., Sachan, M.K.: Land cover segmentation using 3D FCN-based architecture with coordinate attention. IEEE Geosci. Remote Sens. Lett. (2024). https://doi.org/10.1109/LGRS.2024.3399774
Buttar, P.K., Sachan, M.K.: Semantic segmentation of clouds in satellite images based on U-Net++ architecture and attention mechanism. Expert Syst. Appl. 209, 118380 (2022)
Yuan, K., Zhuang, X., Schaefer, G., Feng, J., Guan, L., Fang, H.: Deep-learning-based multispectral satellite image segmentation for water body detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 7422–7434 (2021)
Gupta, S., Gupta, P., Verma, V.S.: Study on anatomical and functional medical image registration methods. Neurocomputing 452, 534–548 (2021)
Wadhwa, A., Bhardwaj, A., Verma, V.S.: A review on brain tumor segmentation of MRI images. Magn. Reson. Imaging 61, 247–259 (2019)
Bagwari, N., Kumar, S., Verma, VS.: Comparative analysis of differential evolution algorithm using shannon, fuzzy, and cosine similarity entropy functions for satellite image segmentation. In: 2022 3rd International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT). IEEE, pp. 1–6 (2022)
Kumar, S., Yadav, A., Varshney, A., Sharma, A., Shivani, S.: Comparative Analysis of U-Net Models Using ResNet34, InceptionV3, and VGG16 for the Processing of Satellite Images. In: 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), vol. 2. IEEE, pp. 1–6 (2024)
Byun, Y.G., Han, Y.K., Chae, T.B.: A multispectral image segmentation approach for object-based image classification of high resolution satellite imagery. KSCE J. Civ. Eng. 17, 486–497 (2013)
Saha, I., Maulik, U., Bandyopadhyay, S., Plewczynski, D.: SVMeFC: SVM ensemble fuzzy clustering for satellite image segmentation. IEEE Geosci. Remote Sens. Lett. 9(1), 52–55 (2011)
Bagwari, N., Kumar, S., Verma, V.S.: A comprehensive review on segmentation techniques for satellite images. Arch. Comput. Methods Eng. 30(7), 1–34 (2023)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3431–3440 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, pp. 234–241 (2015)
Jiang, Y., Yang, F., Zhu, H., Zhou, D., Zeng, X.: Nonlinear CNN: improving CNNs with quadratic convolutions. Neural Comput. Appl. 32, 8507–8516 (2020)
Mantini, P., Shah, SK.: CQNN: convolutional quadratic neural networks. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, p. 9819–9826 (2021)
Gonzalez, RC.: Digital image processing. Pearson Education India (2009)
Alsabhan, W., Alotaiby, T., et al.: Automatic building extraction on satellite images using Unet and ResNet50. Comput. Intell. Neurosci. 2022(1), 5008854 (2022)
Shao, Z., Tang, P., Wang, Z., Saleem, N., Yam, S., Sommai, C.: BRRNet: a fully convolutional neural network for automatic building extraction from high-resolution remote sensing images. Remote Sens. 12(6), 1050 (2020)
Guo, H., Su, X., Tang, S., Du, B., Zhang, L.: Scale-robust deep-supervision network for mapping building footprints from high-resolution remote sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 10091–10100 (2021)
Bakirman, T., Komurcu, I., Sertel, E.: Comparative analysis of deep learning based building extraction methods with the new VHR Istanbul dataset. Expert Syst. Appl. 202, 117346 (2022)
Chen, Z., Li, D., Fan, W., Guan, H., Wang, C., Li, J.: Self-attention in reconstruction bias U-Net for semantic segmentation of building rooftops in optical remote sensing images. Remote Sens. 13(13), 2524 (2021)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no Conflict of interest. All authors equally contributed to this manuscript. No financial interests are reported.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bagwari, N., Verma, V.S. & Kumar, S. Residual quadratic encoder–decoder architecture for semantic segmentation of satellite images. SIViP 19, 70 (2025). https://doi.org/10.1007/s11760-024-03717-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11760-024-03717-w