Abstract
Hyperspectral image is an image that contains both geometric space information and spectral information, however, the cost of acquiring a large number of hyperspectral image data samples is very high due to the limitations of imaging technology and detector level.With the development of artificial intelligence technology and the advent of the era of big data, data sample build and extend the method arises at the historic moment. In order to obtain sufficient sample data and establish the hyperspectral data information database of specific ground object required for research, the obtained hyperspectral image data needs to be expanded which can provide basic data support for the study of spatial spectral characteristics of ground objects and subsequent hyperspectral image classification and target detection. In this article, Firstly, the data structure and characteristics of hyperspectral image are analyzed, and then the common methods and significance of hyperspectral image data sample expansion under the condition of land-based imaging are systematically described from the two aspects of spatial dimension data and spectral dimension data.Finally, Aiming at the main problems existing in the process of hyperspectral image data expansion, the development direction in the future is prospected.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yu, R., Luo, Y.Q., Li, H.N., et al.: Three-dimensional convolutional neural network model for early detection of pine wilt disease using UAV-based hyperspectral images. Remote Sens 13(20) (2021)
Zdravcheva, N.D.: Hyperspectral environmental monitoring. In: IOP Conference Series: Materials Science and Engineering, pp. 614 (2019)
Wang, J.C., Zhu, M.: Development of hyperspectral reconnaissance technology. Aerosp. Electron. Warfare 35(03), 37–45 (2019)
Yang, Q.Q., Jin, C.Y., Li, T.W., et al.: Research progress and challenges of datadriven quantitative remote sensing. Natl. Remote Sens. Bull. 26(2), 268–285 (2022)
Liu, X.F., Liu, J.M., Fu, M.: Generating countermeasure network extended samples for hyperspectral image classification. Electron. Meas. Technol. 45(03), 146–152 (2022)
Zhang, Y., Hua, W.S., Huang, F.Y., et al.: Hyperspectral anomaly target detection based on spatial spectrum joint anomaly degree. Spectroscopy Spectral Anal. 40(06), 1902–1908 (2020)
Li, W., Chen, C., Zhang, M., et al.: Data augmentation for hyperspectral image classification with deep CNN. IEEE Geosci. Remote Sens. Lett. 1–5 (2018)
Liu, X., Wang, C., Wang, H., et al.: Target detection of hyperspectral image based on faster R-CNN with data set adjustment and parameter turning. OCEANS 2019-Marseille (2019)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1) (2019)
Arad, B., Ben-Shahar, O., Timofte, R., et al.: NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE (2018)
Arad, B., Timofte, R., Ben-Shahar, O., et al.: NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image (2020)
Wang, Q.H., Hua, W.S., Huang, F.Y., et al.: Based on the spectral Angle background purification of hyperspectral anomaly detection algorithm. Laser Technol. 44(5), 623–627 (2020). (in chinese)
Yang, L.H., Xu, J., Jiang, S.P.: Vacuum cryogenic environment reflector spectrum reflectance in situ measurement techniques. J. Appl. Opt. 36(04), 559–565 (2015)
Li, X., Strahler, A.H.: Geometric-optical modeling of a conifer forest canopy. IEEE Trans. Geosci. Remote Sens. GE-23(5), 705–721 (1985)
Ding, A.X., Qiao, Z.D., Dong, Y.D., et al.: BRDF model integration and case analysis basedon linear kernel driven model. Remote Sens. Technol. Appl. 33(03), 545–554 (2018)
Yan, G.J., Wu, J., Wang, J.D., et al.: Spectral prior knowledge in the application of remote sensing inversion of vegetation structure. J. Remote Sens. (01), 1–6 (2002)
Hinton, G.E., Osindero, S., The, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)
Zhang, J.C., Liu, P., Che, H.S., et al.: A near earth hyperspectral data expansion method for deep learning. CN 110070004A[P] (2019)
Gan, H.M., Yue, X.J., Hong, T.S., et al.: Hyperspectral inversion model for predicting chlorophyll content in Longan leaves based on deep learning. J. South China Agri. Univ. 39(03), 102–110 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jiale, Z., Bing, Z., Guanglong, W., Jiaju, Y., Lei, D., Qianghui, W. (2023). Hyperspectral Image Data Construction and Expansion Method of Ground Object. In: Wang, L., Wu, Y., Gong, J. (eds) Proceedings of the 8th China High Resolution Earth Observation Conference (CHREOC 2022). CHREOC 2022. Lecture Notes in Electrical Engineering, vol 969. Springer, Singapore. https://doi.org/10.1007/978-981-19-8202-6_15
Download citation
DOI: https://doi.org/10.1007/978-981-19-8202-6_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8201-9
Online ISBN: 978-981-19-8202-6
eBook Packages: EngineeringEngineering (R0)