Abstract
In recent years, Convolutional Neural Networks (CNNs) have succeeded in Hyperspectral Image Classification and shown excellent performance. However, the implicit spatial information between features, which significantly affect the classification performance of CNNs, are neglected in most existing CNN models. To address this issue, we propose a parallel multi-input mechanism-based CNN (PMI-CNN) fully exploiting the implicit spectral-spatial information in Hyperspectral Images. PMI-CNN employs four parallel convolution branches to extract spatial features with different levels, feature maps from each branch are spliced, and used as the classifier’s input. The proposed PMI-CNN’s classification performance is examined on three benchmark datasets and compared with six competing models. Experimental results show that PMI-CNN has better classification performance via exploiting spectral-spatial information. Compared with other models, the classification accuracy of PMI-CNN on the Indian Pines dataset is significantly improved, varying between 1.23%-25.36%. Likewise, the PMI-CNN, performed on the other two benchmark datasets, achieves 0.54%-12.26% and 0.96%-8.38% advantages in overall accuracy over the other six models, respectively.
Similar content being viewed by others
References
Ghamisi P, Yokoya N, Li J, Liao W, Liu S, Plaza J, Rasti B, Plaza A (2017) Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art. IEEE Geosci Remote Sens Mag 5(4):37–78. https://doi.org/10.1109/MGRS.2017.2762087
Yokoya N, Grohnfeldt C, Chanussot J (2017) Hyperspectral and Multispectral Data Fusion: A comparative review of the recent literature. IEEE Geosci Remote Sens Mag 5(2):29–56. https://doi.org/10.1109/MGRS.2016.2637824
Luo F, Huang H, Duan Y, Liu J, Liao Y (2017) Local Geometric Structure Feature for Dimensionality Reduction of Hyperspectral Imagery. Remote Sens 9(8):790. https://doi.org/10.3390/rs9080790
Deng X, Zhu Z, Yang J, Zheng Z, Huang Z, Yin X, Wei S, Lan Y (2020) Detection of citrus huanglongbing based on Multi-Input neural network model of UAV hyperspectral remote sensing. Remote Sens 12(17):2678. https://doi.org/10.3390/rs12172678
Akbari H, Kosugi Y, Kojima K, Tanaka N (2010) Detection and analysis of the intestinal ischemia using visible and invisible hyperspectral imaging. IEEE Trans Biomed Eng 57(8):2011–2017. https://doi.org/10.1109/tbme.2010.2049110
Su W, Sun D (2018) Fourier transform infrared and raman and hyperspectral imaging techniques for quality determinations of powdery foods: a review. Compr Rev Food Sci Food Saf 17:104–122. https://doi.org/10.1111/1541-4337.12314
Plaza A, Plaza J, Martin G (2009) Incorporation of spatial constraints into spectral mixture analysis of remotely sensed hyperspectral data. In: 2009 IEEE international workshop on machine learning for signal processing, Grenoble, pp 1–6. https://doi.org/10.1109/mlsp.2009.5306202
Audebert N, Le Saux B, Lefevre S (2019) Deep learning for classification of hyperspectral data: a comparative review. IEEE Geosci Remote Sens Mag 7(2):159–173. https://doi.org/10.1109/MGRS.2019.2912563
Yang D, Bao W (2017) Group Lasso-Based band selection for hyperspectral image classification. IEEE Geosci Remote Sens Lett 14(12):2438–2442. https://doi.org/10.1109/lgrs.2017.2768074
Benediktsson J, Ghamisi P (2015) Spectral-Spatial Classification of hyperspectral remote sensing images artech. House, Boston
Bahria S, Essoussi N, Limam M (2011) Hyperspectral data classification using geostatistics and support vector machines. Remote Sens Lett 2(2):99–106. https://doi.org/10.1080/01431161.2010.497782
Blanzieri E, Melgani F (2008) Nearest neighbor classification of remote sensing images with the maximal margin principle. IEEE Trans Geosci Remote Sens 46(6):1804–1811. https://doi.org/10.1109/tgrs.2008.916090
Ham J, Yangchi C, Crawford M, Ghosh J (2005) Investigation of the random forest framework for classification of hyperspectral data. IEEE Trans Geosci Remote Sens 43(3):492–501. https://doi.org/10.1109/tgrs.2004.842481
Du P, Bai X, Tan K, Xue Z, Samat A, Xia J, Li E, Su H, Liu W (2020) Advances of four machine learning methods for spatial data handling: a review. J Geovis Spat Anal 4(1):13. https://doi.org/10.1007/s41651-020-00048-5
Hughes G (1968) On the mean accuracy of statistical pattern recognizers. IEEE Trans Inf Theory 14(1):55–63. https://doi.org/10.1109/tit.1968.1054102
Zhang Y, Cao G, Li X, Wang B (2018) Cascaded random forest for hyperspectral image classification. IEEE J Sel Top Appl Earth Observ Remote Sens 11(4):1082–1094. https://doi.org/10.1109/JSTARS.2018.2809781
Xia J, Yokoya N, Iwasaki A (2016) Hyperspectral image classification with canonical correlation forests. IEEE Trans Geosci Remote Sens 55 (1):421–431. https://doi.org/10.1109/tgrs.2016.2607755
Ergul U, Bilgin G (2019) HCKBOost: Hybridized composite kernel boosting with extreme learning machines for hyperspectral image classification. Neurocomputing 334:100–113. https://doi.org/10.1016/j.neucom.2019.01.010
Bayliss J D, Gualtieri J A, Cromp R F, Selander J M (1998) Analyzing hyperspectral data with independent component analysis. In: SPIE Proceedings of the 26th AIPR Workshop: exploiting new image sources and sensors. https://doi.org/10.1117/12.300050, vol 3240, pp 133–143
Rodarmel C, Shan J (2002) Principal component analysis for hyperspectral image classification. Surv Land inf Syst 62(2):115–122
Ji S, Ye J (2008) Generalized linear discriminant analysis: a unified framework and efficient model selection. IEEE Trans Neural Netw 19(10):1768–1782. https://doi.org/10.1109/tnn.2008.2002078
Cheng G, Yang C, Yao X, Guo L, Han J (2018) When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs. IEEE Trans Geosci Remote Sens 56(5):2811–2821. https://doi.org/10.1109/TGRS.2017.2783902
Chen Y, Lin Z, Zhao X, Wang G, Gu Y (2014) Deep Learning-Based classification of hyperspectral data. IEEE J Sel Top Appl Earth Observ Remote Sens 7(6):2094–2107. https://doi.org/10.1109/jstars.2014.2329330
Zhong Y, Fei F, Liu Y, Zhao B, Jiao H, Zhang L (2017) SatCNN: satellite image dataset classification using agile convolutional neural networks. Remote Sens Lett 8(2):136–145. https://doi.org/10.1080/2150704X.2016.1235299
Hu W, Huang Y, Wei L, Zhang F, Li H (2015) Deep convolutional neural networks for hyperspectral image classification. J Sens 2015:1–12. https://doi.org/10.1155/2015/258619
Li W, Wu G, Zhang F, Du Q (2016) Hyperspectral image classification using deep Pixel-Pair features. IEEE Trans Geosci Remote Sens 55(2):844–853. https://doi.org/10.1109/TGRS.2016.2616355
Paoletti M, Haut J, Plaza J, Plaza A (2017) A new deep convolutional neural network for fast hyperspectral image classification. ISPRS-J Photogramm Remote Sens 145(A):120–147. https://doi.org/10.1016/j.isprsjprs.2017.11.021
Makantasis K, Karantzalos K, Doulamis A, Doulamis N (2015) Deep supervised learning for hyperspectral data classification through convolutional neural networks In. https://doi.org/10.1109/IGARSS.2015.7326945, vol 2015. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, pp 4959–4962
Pan B, Shi Z, Xu X (2017) R-VCANet: A New Deep-Learning-Based Hyperspectral Image Classification Method. IEEE J Sel Top Appl Earth Observ Remote Sens 10(5):1975–1986. https://doi.org/10.1109/jstars.2017.2655516
Lee H, Kwon H (2016) Contextual deep CNN based hyperspectral classification. In: 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) - Contextual deep CNN based hyperspectral classification, pp 3322–3325. https://doi.org/10.1109/igarss.2016.7729859
Chen Y, Jiang H, Li C, Jia X, Ghamisi P (2016) Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54(10):6232–6251. https://doi.org/10.1109/TGRS.2016.2584107
Yang J, Zhao Y, Chan J (2017) Learning and transferring deep joint Spectral-Spatial features for hyperspectral classification. IEEE Trans Geosci Remote Sens 55(8):4729–4742. https://doi.org/10.1109/TGRS.2017.2698503
Xu Y, Zhang L, Du B, Zhang F (2018) Spectral-Spatial Unified networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56 (10):5893–5909. https://doi.org/10.1109/TGRS.2018.2827407
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Srivastava R, Greff K, Schmidhuber J (2015) Training very deep networks. In: Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS), Montreal, pp 2377–2385
Wang D, Du B, Zhang L, Chu S (2020) Hyperspectral image classification based on multi-scale information compensation. Remote Sens Lett 11 (3):293–302. https://doi.org/10.1080/2150704X.2019.1711238
Ren J, Wang R, Liu G, Wang Y, Wu W (2021) An SVM-based Nested Sliding Window Approach for Spectral–Spatial Classification of Hyperspectral Images. Remote Sens 13(1):114. https://doi.org/10.3390/rs13010114
Huang G, Liu Z, Maaten L, Weinberger K (2017) Densely connected convolutional networks. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), Honolulu, pp 2261–2269. https://doi.org/10.1109/cvpr.2017.243
Bahria S, Essoussi N, Limam M (2011) Hyperspectral data classification using geostatistics and support vector machines. Remote Sens Lett 2(2):99–106. https://doi.org/10.1080/01431161.2010.497782
Xu Y, Zhang L, Du B, Zhang F (2018) Spectral-Spatial Unified networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56 (10):5893–5909. https://doi.org/10.1109/TGRS.2018.2827407
Wang Z-Y, Xia Q-M, Yan J-W, Xuan S-Q, Su J-H, Yang C-F (2019) Hyperspectral image classification based on spectral and spatial information using multi-scale ResNet. Appl Sci 9(22):4890. https://doi.org/10.3390/app9224890
Funding
This paper was supported by the Open Fund of Hubei Key Laboratory of Intelligent Geo-Information Processing (Grant No. ZRIGIP-201801).
Author information
Authors and Affiliations
Contributions
All the authors made significant contributions to the work. Huan Zhong, Li Li designed the research, analysed the results, accomplished the validation work, and finished the final paper writing. Jiansi Ren, Wei Wu, and Ruoxiang Wang provided advice for the preparation and revision of the paper.
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest. The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; and in the decision to publish the results.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhong, H., Li, L., Ren, J. et al. Hyperspectral image classification via parallel multi-input mechanism-based convolutional neural network. Multimed Tools Appl 81, 24601–24626 (2022). https://doi.org/10.1007/s11042-022-12494-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12494-y