An Efficient Image Segmentation using Optimized Segmentation Network for Remote Sensing Satellite Images

Authors

  • Namdeo Baban Badhe Research Scholar, Department of Information Technology, Finolex Academy of Management and Technology, P-60, P-60/1, MIDC, Mirjole Block, Ratnagiri, Maharashtra 415639, India
  • Vinayak Ashok Bharadi HOD & Professor, Department of Information Technology, Finolex Academy of Management and Technology, MIDC, Mirjole Block, Ratnagiri, Maharashtra 415639, India
  • Nupur Giri HOD & Professor, Department of Computer Engineering, Vivekanand Education Society's Institute of Technology, Hashu Adwani Memorial Complex, Collector's Colony, Chembur, Mumbai, Maharashtra 400074, India
  • Sujata Alegavi Associate Professor, Head of the BTech Internet of Things Department, Thakur College Engineering and Technology, Kandivali - (East), Mumbai – 40010, India
  • Shashank S. Tolye Professor, Finolex Academy of Management and Technology, MIDC, Mirjole Block, Ratnagiri, Maharashtra – 415639, India

Keywords:

Image segmentation, spectral and spatial features, semantic segmentation, remote sensing, convolutional neural network

Abstract

Segmentation of high-resolution remote sensing images is of great importance for urban development planning. Moreover, while monitoring land covers through high-resolution satellite images, crops are significantly easy to be confused with the dark object’s spectra like, shadows, dense vegetation and asphalt roads. The previous semantic segmentation approaches do not pay enough attention to the location information among horizontal position and direction, which causes inaccurate segmentation of remote sensing images. To overcome these issues, an innovative Optimized Segmentation Network (OptSegNet) based remote sensing image segmentation is proposed which is a hybridization of convolutional network and dual-path UNet with Resnet_50. It consists of four stages such as, pre-processing, feature extraction, segmentation and post processing. Initially, the hyperspectral images which are derived from the Indian Pines dataset, Salinas, and Pavia University are preprocessed by using the guided box filtering technique. Secondly, the proposed method extracts the spatial and spectral features from the satellite images and also generates accurate segmentation results. In order to enhance the performance of proposed method, Enhanced Mountain Gazelle Optimization (EMGO) algorithm is used. Finally, in the post processing stage the proposed pairwise neural conditional random field method enhances the final segmented images into a high-resolution remote sensing image. Experimental outcomes illustrate that the introduced method achieves better performance when compared with the other traditional algorithms. Especially, the accomplished overall accuracy is 99.13%, 99.71%, and 99.34% on Indian Pines dataset, Salinas, and Pavia University dataset respectively.

Downloads

Download data is not yet available.

References

S. Illarionova, D. Shadrin, A. Trekin, V. Ignatiev, and I. Oseledets, “Generation of the NIR spectral band for satellite images with Convolutional Neural Networks,” Sensors, vol. 21, no. 16, p. 5646, 2021. doi:10.3390/s21165646

K. Yuan et al., “Deep-learning-based multispectral satellite image segmentation for water body detection,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 7422–7434, 2021. doi:10.1109/jstars.2021.3098678

Y. Chen, Q. Weng, L. Tang, Q. Liu, and R. Fan, “An automatic cloud detection neural network for high-resolution remote sensing imagery with cloud–snow coexistence,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022. doi:10.1109/lgrs.2021.3102970

L. Yin et al., “Haze grading using the Convolutional Neural Networks,” Atmosphere, vol. 13, no. 4, p. 522, 2022. doi:10.3390/atmos13040522

X. Xu et al., “A novel approach for scene classification from remote sensing images using Deep Learning Methods,” European Journal of Remote Sensing, vol. 54, no. sup2, pp. 383–395, 2020. doi:10.1080/22797254.2020.1790995

D. Rashkovetsky, F. Mauracher, M. Langer, and M. Schmitt, “Wildfire detection from multisensor satellite imagery using deep semantic segmentation,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 7001–7016, 2021. doi:10.1109/jstars.2021.3093625

Q. Hu, L. Zhen, Y. Mao, X. Zhou, and G. Zhou, “Automated building extraction using satellite remote sensing imagery,” Automation in Construction, vol. 123, p. 103509, 2021. doi:10.1016/j.autcon.2020.103509

A. Sharifi, H. Mahdipour, E. Moradi, and A. Tariq, “Agricultural Field extraction with deep learning algorithm and satellite imagery,” Journal of the Indian Society of Remote Sensing, vol. 50, no. 2, pp. 417–423, 2022. doi:10.1007/s12524-021-01475-7

L. Yao, T. Liu, J. Qin, N. Lu, and C. Zhou, “Tree counting with high spatial-resolution satellite imagery based on Deep Neural Networks,” Ecological Indicators, vol. 125, p. 107591, 2021. doi:10.1016/j.ecolind.2021.107591

S. Baroud, S. Chokri, S. Belhaous, and M. Mestari, “A brief review of graph convolutional neural network based learning for classifying remote sensing images,” Procedia Computer Science, vol. 191, pp. 349–354, 2021. doi:10.1016/j.procs.2021.07.047

X. Yu et al., “NestNet: A multiscale convolutional neural network for Remote Sensing Image Change Detection,” International Journal of Remote Sensing, vol. 42, no. 13, pp. 4898–4921, 2021. doi:10.1080/01431161.2021.1906982

S. Gadamsetty, R. Ch, A. Ch, C. Iwendi, and T. R. Gadekallu, “Hash-based deep learning approach for remote sensing satellite imagery detection,” Water, vol. 14, no. 5, p. 707, 2022. doi:10.3390/w14050707

K. A. Korznikov et al., “Using u-net-like deep convolutional neural networks for precise tree recognition in very high resolution RGB (red, green, blue) satellite images,” Forests, vol. 12, no. 1, p. 66, 2021. doi:10.3390/f12010066

A. Abdollahi, B. Pradhan, and N. Shukla, “Road extraction from high-resolution orthophoto images using convolutional neural network,” Journal of the Indian Society of Remote Sensing, vol. 49, no. 3, pp. 569–583, 2020. doi:10.1007/s12524-020-01228-y

X. Wu, D. Hong, and J. Chanussot, “Convolutional Neural Networks for Multimodal Remote Sensing Data Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–10, 2022. doi:10.1109/tgrs.2021.3124913

L. Zhou et al., “Shallow-to-deep spatial–spectral feature enhancement for Hyperspectral Image Classification,” Remote Sensing, vol. 15, no. 1, p. 261, 2023. doi:10.3390/rs15010261

C. Zhao, B. Qin, S. Feng, and W. Zhu, “Multiple Superpixel graphs learning based on adaptive multiscale segmentation for Hyperspectral Image Classification,” Remote Sensing, vol. 14, no. 3, p. 681, 2022. doi:10.3390/rs14030681

E. Ravi Kondal and S. Sankar Barpanda, “Hyperspectral image classification using HYB-3D convolution neural network spectral partitioning,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 29, no. 1, p. 295, 2022. doi:10.11591/ijeecs.v29.i1.pp295-303

L. Song, Z. Feng, S. Yang, X. Zhang, and L. Jiao, “Self-supervised assisted semi-supervised Residual Network for Hyperspectral Image Classification,” Remote Sensing, vol. 14, no. 13, p. 2997, 2022. doi:10.3390/rs14132997

A. Zhang et al., “Superpixel nonlocal weighting joint sparse representation for hyperspectral image classification,” Remote Sensing, vol. 14, no. 9, p. 2125, 2022. doi:10.3390/rs14092125

R. Chakraborty, R. Sushil, and M. L. Garg, “Hyper-spectral image segmentation using an improved PSO aided with multilevel fuzzy entropy,” Multimedia Tools and Applications, vol. 78, no. 23, pp. 34027–34063, 2019. doi:10.1007/s11042-019-08114-x

Z. Wang, C. Zou, and W. Cai, “Small sample classification of hyperspectral remote sensing images based on Sequential Joint Deeping Learning model,” IEEE Access, vol. 8, pp. 71353–71363, 2020. doi:10.1109/access.2020.2986267

Z. He, H. Wu, and G. Wu, “Spectral-spatial classification of hyperspectral images using label dependence,” IEEE Access, vol. 9, pp. 119219–119231, 2021. doi:10.1109/access.2021.3107976

T. Zhao and S.-X. Zhang, “X-ray image enhancement based on nonsubsampled shearlet transform and gradient domain guided filtering,” Sensors, vol. 22, no. 11, p. 4074, 2022. doi:10.3390/s22114074

S. Q. Nisa and A. R. Ismail, “Dual U-Net with resnet encoder for segmentation of medical images,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 12, 2022. doi:10.14569/ijacsa.2022.0131265

B. Abdollahzadeh, F. S. Gharehchopogh, N. Khodadadi, and S. Mirjalili, “Mountain Gazelle optimizer: A new nature-inspired metaheuristic algorithm for global optimization problems,” Advances in Engineering Software, vol. 174, p. 103282, 2022. doi:10.1016/j.advengsoft.2022.103282

Q. Li, Y. Shi, X. Huang, and X. X. Zhu, “Building footprint generation by integrating convolution neural network with feature Pairwise Conditional Random Field (FPCRF),” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 11, pp. 7502–7519, 2020. doi:10.1109/tgrs.2020.2973720

https://paperswithcode.com/dataset/indian-pines

https://paperswithcode.com/dataset/salinas

https://paperswithcode.com/dataset/pavia-university

S. Agrawal, R. Panda, S. Bhuyan, and B. K. Panigrahi, “Tsallis entropy based optimal multilevel Thresholding using cuckoo search algorithm,” Swarm and Evolutionary Computation, vol. 11, pp. 16–30, 2013. doi:10.1016/j.swevo.2013.02.001

S. Sarkar, S. Paul, R. Burman, S. Das, and S. S. Chaudhuri, “A fuzzy entropy based multi-level image thresholding using differential evolution,” Swarm, Evolutionary, and Memetic Computing, pp. 386–395, 2015. doi:10.1007/978-3-319-20294-5_34

S. Pare, A. K. Bhandari, A. Kumar, and G. K. Singh, “A new technique for multilevel color image thresholding based on modified fuzzy entropy and Lévy flight Firefly algorithm,” Computers & Electrical Engineering, vol. 70, pp. 476–495, 2018. doi:10.1016/j.compeleceng.2017.08.008

M. Salman and S. E. Yuksel, “Fusion of hyperspectral image and Lidar data and classification using deep convolutional Neural Networks,” 2018 26th Signal Processing and Communications Applications Conference (SIU), 2018. doi:10.1109/siu.2018.8404199

M. E. Paoletti et al., “Deep pyramidal residual networks for spectral–spatial hyperspectral image classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 2, pp. 740–754, 2019. doi:10.1109/tgrs.2018.2860125

G. Yang, U. B. Gewali, E. Ientilucci, M. Gartley, and S. T. Monteiro, “Dual-channel densenet for hyperspectral image classification,” IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018. doi:10.1109/igarss.2018.8517520

H. Gao, Y. Yang, D. Yao, and C. Li, “Hyperspectral image classification with pre-activation residual attention network,” IEEE Access, vol. 7, pp. 176587–176599, 2019. doi:10.1109/access.2019.2957163

J. Chen, S. Chen, P. Zhou, and Y. Qian, “Deep Neural Network based hyperspectral pixel classification with factorized spectral-spatial feature representation,” IEEE Access, vol. 7, pp. 81407–81418, 2019. doi:10.1109/access.2019.2923776

D. Datta, P. K. Mallick, D. Gupta, and G.-S. Chae, “Hyperspectral image classification based on novel hybridization of spatial-spectral-superpixelwise principal component analysis and dense 2D-3D convolutional neural network fusion architecture,” Canadian Journal of Remote Sensing, vol. 48, no. 5, pp. 663–680, 2022. doi:10.1080/07038992.2022.2114440

C. Mu, Z. Dong, and Y. Liu, “A two-branch convolutional neural network based on multi-spectral entropy rate Superpixel segmentation for hyperspectral image classification,” Remote Sensing, vol. 14, no. 7, p. 1569, 2022. doi:10.3390/rs14071569

S.S. Alegavi, R.R. Sedamkar, “Implementation of Deep Convolutional Neural Network for Classification of Multiscaled & Multiangled Remote Sensing Scene”, International Journal on Soft Computing approaches for image analysis in practical scenario: Challenges, Solutions and Applications, Intelligent Decision Technologies, 14 (2020) 21–34, DOI: 10.3233/IDT-190076 IOS Press February 2020.

S. S. Alegavi and R.R. Sedamkar, “Research Trends in Hyperspectral Imagery Data” International Journal of Computer Engineering & Technology (IJCET), (UGC Approved Journal), ISSN Print: 0976 – 6367, ISSN Online: 0976 – 6375, IJCET, Volume 10, Issue 2, Article Id., IJCET_10_02_008, IAEME Publications, pg. no. 67-73, March-April 2019.

Sherje, N. P., Agrawal, S. A., Umbarkar, A. M., Kharche, P. P., & Dhabliya, D. (2021). Machinability study and optimization of CNC drilling process parameters for HSLA steel with coated and uncoated drill bit. Materials Today: Proceedings, doi:10.1016/j.matpr.2020.12.1070

Paul Garcia, Anthony Walker, Luis Gonzalez, Carlos Pérez, Luis Pérez. Improving Question Generation and Answering Systems with Machine Learning. Kuwait Journal of Machine Learning, 2(2). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/187

Matti Virtanen, Jan de Vries, Thomas Müller, Daniel Müller, Giovanni Rossi. Machine Learning for Intelligent Feedback Generation in Online Courses . Kuwait Journal of Machine Learning, 2(2). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/188

Downloads

Published

12.07.2023

How to Cite

Badhe, N. B. ., Bharadi, V. A. ., Giri, N. ., Alegavi, S. ., & Tolye, S. S. . (2023). An Efficient Image Segmentation using Optimized Segmentation Network for Remote Sensing Satellite Images. International Journal of Intelligent Systems and Applications in Engineering, 11(9s), 804–821. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/3269

Issue

Vol. 11 No. 9s (2023)

Section

Research Article

License

Creative Commons 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.