• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology

Article

Spatial-Spectral Feature for Extraction Technique for Hyperspectral Crop Classification
  • VIEWS 882
  • PDF 214

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v15i2.1810

Year: 2022, Volume: 15, Issue: 2, Pages: 81-90

Original Article

Spatial-Spectral Feature for Extraction Technique for Hyperspectral Crop Classification

Vani V G1*, Thippeswamy K2

1Associate professor, Department of Computer science & Engineering, Government Engineering College, Kushalnagar, India
2Professor & Head, Department of PG studies, VTU Regional office, Mysore, India

*Corresponding Author
Email: [email protected]

Received Date:28 September 2021, Accepted Date:05 January 2022, Published Date:31 January 2022

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To present an extraction technique for the classification of the hyperspectral crop using the spatial-spectral feature. Methods: This paper presents a spatial-spectral feature extraction method employing the Image fusion technique and intrinsic feature extraction and a model for Improved Decision Boundary (IDB) using Support Vector Machine (SVM). Findings: The experiments have been conducted by using the Indian pines dataset which was extracted using the AVIRIS sensor. The dataset comprises of 16 distinctive classes such as corn, wheat, oats etc, which have used for evaluation of our model. Before the evaluation of the dataset the model has been trained using different training datasets in order to increase the accuracy and reduce misclassification. Moreover, the Spatial-Spectral Feature (SSF) model aided in distinguishing between crop intrinsic features and shadow element under dynamic environment condition. Our model attained 99.54%, 99.4%, 99.25% and 9.8 sec for OA accuracy, AA accuracy, Kappa and Time respectively. Furthermore, the overall accuracy of the model for the Support Vector Machine-3-dimensional discrete wavelet transform (SVM- 3DDWT), Convolutional Neural Network and Spatial-Spectral Feature Extraction Technique showed result of 94.28%, 96.12% and 99.4% respectively. Other existing models showed a low accuracy for the same dataset. Further, for addressing class imbalance issues this work modelled an improved decision boundary model for SVM by considering soft-margin rather than hard margin. The SSF-IDBSVM model achieves much better accuracies with less misclassification in comparison with recent deep learning-based HSI classification model. Novelty: Recently, several feature extraction and deep learning-based crop classification model have been modelled. However, existing crop classification fails to distinguish crop intrinsic feature concerning shadow feature; further, consider hard decision boundary; as a result, high misclassification is induced for smaller class size. Hence, this study provides an extraction feature which provides the classification of the crop in less time with higher classification and less misclassification.

Keywords: Artificial Intelligence; Datamining; Crop Classification; Feature Extraction; Feature Selection; Hyper Spectral Information; Machin Learning Technique

References

  1. Athani SS, Tejeshwar CH. Support Vector Machine-Based Classification Scheme of Maize Crop. 2017 IEEE 7th International Advance Computing Conference (IACC). 2017;p. 84–88. doi: 10.1109/IACC.2017.0032
  2. Murmu S, Biswas S. Application of Fuzzy Logic and Neural Network in Crop Classification: A Review. Aquatic Procedia. 2015;4:1203–1210. doi: 10.1016/j.aqpro.2015.02.153
  3. Tatsumi K, Yamashiki Y, Torres MAC, Taipe CLR. Crop classification of upland fields using Random forest of time-series Landsat 7 ETM+ data. Computers and Electronics in Agriculture. 2015;115:171–179. Available from: https://dx.doi.org/10.1016/j.compag.2015.05.001
  4. Gong M, Zhang M, Yuan Y. Unsupervised Band Selection Based on Evolutionary Multiobjective Optimization for Hyperspectral Images. IEEE Transactions on Geoscience and Remote Sensing. 2016;54(1):544–557. Available from: https://dx.doi.org/10.1109/tgrs.2015.2461653
  5. Sun W, Du Q. Graph-Regularized Fast and Robust Principal Component Analysis for Hyperspectral Band Selection. IEEE Transactions on Geoscience and Remote Sensing. 2018;56(6):3185–3195. Available from: https://dx.doi.org/10.1109/tgrs.2018.2794443
  6. Zhai H, Zhang H, Zhang L, Li P. Laplacian-Regularized Low-Rank Subspace Clustering for Hyperspectral Image Band Selection. IEEE Transactions on Geoscience and Remote Sensing. 2019;57(3):1723–1740. Available from: https://dx.doi.org/10.1109/tgrs.2018.2868796
  9. Hu P, Liu X, Cai Y, Cai Z. Band Selection of Hyperspectral Images Using Multiobjective Optimization-Based Sparse Self-Representation. IEEE Geoscience and Remote Sensing Letters. 2019;16(3):452–456. Available from: https://dx.doi.org/10.1109/lgrs.2018.2872540
  10. Wang Q, Zhang F, Li X. Optimal Clustering Framework for Hyperspectral Band Selection. IEEE Transactions on Geoscience and Remote Sensing. 2018;56(10):1–13. Available from: https://dx.doi.org/10.1109/tgrs.2018.2828161
  11. Jiang X, Song X, Zhang Y, Jiang J, Gao J, Cai Z. Laplacian Regularized Spatial-Aware Collaborative Graph for Discriminant Analysis of Hyperspectral Imagery. Remote Sensing. 2018;11(1):29. Available from: https://dx.doi.org/10.3390/rs11010029
  12. Huang Y, Sun Z. Semi-supervised Locality Preserving Discriminant Analysis for hyperspectral classification. 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). 2016;p. 151–156. doi: 10.1109/CISP-BMEI.2016.7852699
  13. Jayaprakash C, Damodaran BB, V. S, Soman KP. Dimensionality Reduction of Hyperspectral Images for Classification using Randomized Independent Component Analysis. 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN). 2018. doi: 10.1109/SPIN.2018.8474266
  14. Islam MR, Ahmed B, Hossain MA. Feature Reduction Based on Segmented Principal Component Analysis for Hyperspectral Images Classification. 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE). 2019. doi: 10.1109/ECACE.2019.8679394
  15. Wang L, Zhang J, Liu P, Choo KKR, Huang F. Spectral–spatial multi-feature-based deep learning for hyperspectral remote sensing image classification. Soft Computing. 2017;21(1):213–221. Available from: https://dx.doi.org/10.1007/s00500-016-2246-3
  16. Jiang J, Chen C, Yu Y, Jiang X, Ma J. Spatial-Aware Collaborative Representation for Hyperspectral Remote Sensing Image Classification. IEEE Geoscience and Remote Sensing Letters. 2017;14(3):404–408. Available from: https://dx.doi.org/10.1109/lgrs.2016.2645708
  17. Ye Z, Tan L, Bai L. Hyperspectral image classification based on spectral-spatial feature extraction. 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP). 2017;17(6):1042–1046. doi: 10.1109/RSIP.2017.7958808
  18. Liang Y, Zhao X, Guo AJX, Zhu F. Hyperspectral Image Classification With Deep Metric Learning and Conditional Random Field. IEEE Geoscience and Remote Sensing Letters. 2020;17(6):1042–1046. Available from: https://dx.doi.org/10.1109/lgrs.2019.2939356
  19. Santara A, Mani K, Hatwar P, Singh A, Garg A, Padia K, et al. BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing. 2017;55(9):5293–5301. doi: 10.1109/tgrs.2017.2705073
  20. Cao X, Zhou F, Xu L, Meng D, Xu Z, Paisley J. Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network. IEEE Transactions on Image Processing. 2018;27(5):2354–2367. Available from: https://dx.doi.org/10.1109/tip.2018.2799324
  22. Cai Y, Liu X, Cai Z. BS-Nets: An End-to-End Framework for Band Selection of Hyperspectral Image. IEEE Transactions on Geoscience and Remote Sensing. 2020;58(3):1969–1984. Available from: https://dx.doi.org/10.1109/tgrs.2019.2951433
  23. Cao X, Yao J, Xu Z, Meng D. Hyperspectral Image Classification With Convolutional Neural Network and Active Learning. IEEE Transactions on Geoscience and Remote Sensing. 2020;58(7):4604–4616. Available from: https://dx.doi.org/10.1109/tgrs.2020.2964627
  24. Lin L, Chen C, Xu T. Spatial-spectral hyperspectral image classification based on information measurement and CNN. EURASIP Journal on Wireless Communications and Networking. 2020;2020(1). Available from: https://dx.doi.org/10.1186/s13638-020-01666-9
  25. Alotaibi B, Alotaibi M. A Hybrid Deep ResNet and Inception Model for Hyperspectral Image Classification. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science. 2020;88(6):463–476. Available from: https://dx.doi.org/10.1007/s41064-020-00124-x
  26. Ye M, Ji C, Chen H, Lei L, Lu H, Qian Y. Residual deep PCA-based feature extraction for hyperspectral image classification. Neural Computing and Applications. 2020;32(18):14287–14300. Available from: https://dx.doi.org/10.1007/s00521-019-04503-3
  27. Yu C, Zhao M, Song M, Wang Y, Li F, Han R, et al. Hyperspectral Image Classification Method Based on CNN Architecture Embedding With Hashing Semantic Feature. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2019;12(6):1866–1881. Available from: https://dx.doi.org/10.1109/jstars.2019.2911987
  28. Roy SK, Krishna G, Dubey SR, Chaudhuri BB. HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters. 2020;17(2):277–281. Available from: https://dx.doi.org/10.1109/lgrs.2019.2918719
  29. Okwuashi O, Ndehedehe CE. Deep support vector machine for hyperspectral image classification. Pattern Recognition. 2020;103:107298. Available from: https://dx.doi.org/10.1016/j.patcog.2020.107298
  30. Kalaiarasi G, Maheswari S. Deep proximal support vector machine classifiers for hyperspectral images classification. Neural Computing and Applications. 2021;33(20):13391–13415. Available from: https://dx.doi.org/10.1007/s00521-021-05965-0
  31. Wang L, Feng Y, Gao Y, Wang Z, He M. Compressed Sensing Reconstruction of Hyperspectral Images Based on Spectral Unmixing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2018;11(4):1266–1284. Available from: https://dx.doi.org/10.1109/jstars.2017.2787483

Copyright

© 2022 V G & K. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)

  • 31 January 2022

Year: 2022, Volume: 15, Issue: 2

Article Metrics


Post Graduate Fellowship in Research Communication

More articles

DON'T MISS OUT!

Subscribe now for latest articles and news.