Abstract
Crop classification from hyperspectral remote sensing images is an effective means to understand the agricultural scenario of the country. Band selection (BS) is a necessary step to reduce the dimensions of the hyperspectral image. We propose a band selection method that takes into account the image quality in terms of a non-reference quality index along with correlation analysis. The optimum bands selected using the proposed method are then fed to the three supervised machine learning classifiers, namely, support vector machine, K-nearest neighbours and random forest. We have also investigated the impact of correlation analysis by showing the comparison of the proposed band selection method with another variant of our method where correlation analysis is not included. The result shows that the crop classification shows better performance in terms of overall accuracy and kappa coefficient when image quality and correlation analysis are both considered while selecting optimum bands. All the experiments have been performed on the three hyperspectral datasets, Indian Pines, Salinas and AVIRIS-NG, which contain major crop classes. The results show that the optimum bands selected using the proposed method provide the highest overall accuracy, equal to 89.63% (Indian Pines), 95.88% (Salinas) and 97.44% (AVIRIS-NG). The overall accuracy shows a rise from +2% to +4% to that of bands without considering correlation analysis. The advantage of this band selection method is that it does not require any prior knowledge about the crop to select the bands.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhu, L., Radeloff, V.C., Ives, A.R.: Improving the mapping of crop types in the Midwestern US by fusing landsat and MODIS satellite data. Int. J. Appl. Earth Obs. Geoinf. 58, 1–11 (2017)
Chen, Y., et al.: Mapping croplands, cropping patterns, and crop types using MODIS time-series data. Int. J. Appl. Earth Obs. Geoinf. 69, 133–147 (2018)
Chauhan, H.J., Mohan, B.K.: Development of agricultural crops spectral library and classification of crops using hyperion hyperspectral data. J. Remote Sens. Technol. 1(1), 9 (2013)
Skriver, H., et al.: Crop classification using short-revisit multitemporal SAR data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 4(2), 423–431 (2011)
Khosravi, I., Alavipanah, S.K.: A random forest-based framework for crop mapping using temporal, spectral, textural and polarimetric observations. Int. J. Remote Sens. 40(18), 7221–7251 (2019)
Sahoo, R.N., Ray, S.S., Manjunath, K.R.: Hyperspectral remote sensing of agriculture. Curr. sci. 848–859 (2015)
Yan, Y., Yu, W., Zhang, L.: A method of band selection of remote sensing image based on clustering and intra-class index. Multimedia Tools Appl. 81(16), 22111–22128 (2022)
Hidalgo, D.R., Cortés, B.B., Bravo, E.C.: Dimensionality reduction of hyperspectral images of vegetation and crops based on self-organized maps. Inf. Process. Agric. 8(2), 310–327 (2021)
Martínez-Usó, A., Pla, F., García-Sevilla, P., Sotoca, J.M.: Automatic band selection in multispectral images using mutual information-based clustering. In: Martínez-Trinidad, J.F., Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS, vol. 4225, pp. 644–654. Springer, Heidelberg (2006). https://doi.org/10.1007/11892755_67
Chang, C.I., Kuo, Y.M., Chen, S., Liang, C.C., Ma, K.Y., Hu, P.F.: Self-mutual information-based band selection for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 59(7), 5979–5997 (2020)
Sawant, S.S., Manoharan, P., Loganathan, A.: Band selection strategies for hyperspectral image classification based on machine learning and artificial intelligent techniques-Survey. Arab. J. Geosci. 14, 1–10 (2021)
Sun, K., Geng, X., Ji, L., Lu, Y.: A new band selection method for hyperspectral image based on data quality. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7(6), 2697–2703 (2014)
Aneece, I., Thenkabail, P.S.: New generation hyperspectral sensors DESIS and PRISMA provide improved agricultural crop classifications. Photogram. Eng. Remote Sens. 88(11), 715–729 (2022)
Kutser, T., et al.: Remote sensing of black lakes and using 810 nm reflectance peak for retrieving water quality parameters of optically complex waters. Remote Sens. 8(6), 497 (2016)
Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21(12), 4695–4708 (2012)
Fauvel, M., Benediktsson, J.A., Chanussot, J., Sveinsson, J.R.: Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans. Geosci. Remote Sens. 46(11), 3804–3814 (2008)
Gualtieri, J.A., Cromp, R.F.: Support vector machines for hyperspectral remote sensing classification. In: 27th AIPR workshop: Advances in Computer-Assisted Recognition, vol. 3584, pp. 221–232. SPIE (1999)
Gualtieri, J.A., Chettri, S.R., Cromp, R.F., Johnson, L.F.: Support vector machine classifiers as applied to AVIRIS data. In Proceedings of the Eighth JPL Airborne Geoscience Workshop, pp. 8–11 (1999)
Nigam, R., et al.: Crop type discrimination and health assessment using hyperspectral imaging. Curr. Sci. 116(7), 1108–1123 (2019)
Mariotto, I., Thenkabail, P.S., Huete, A., Slonecker, E.T., Platonov, A.: Hyperspectral versus multispectral crop-productivity modeling and type discrimination for the HyspIRI mission. Remote Sens. Environ. 139, 291–305 (2013)
Vali, A., Comai, S., Matteucci, M.: Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: a review. Remote Sens. 12(15), 2495 (2020)
Wan, S., Wang, Y.P.: The comparison of density-based clustering approach among different machine learning models on paddy rice image classification of multispectral and hyperspectral image data. Agriculture 10(10), 465 (2020)
Adam, E., Mutanga, O., Rugege, D.: Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review. Wetlands Ecol. Manage. 18, 281–296 (2010)
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 Switzerland AG
About this paper
Cite this paper
Dave, K., Trivedi, Y. (2023). Classification of Crops Based on Band Quality and Redundancy from the Hyperspectral Image. In: Saini, M.K., Goel, N., Shekhawat, H.S., Mauri, J.L., Singh, D. (eds) Agriculture-Centric Computation. ICA 2023. Communications in Computer and Information Science, vol 1866. Springer, Cham. https://doi.org/10.1007/978-3-031-43605-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-43605-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43604-8
Online ISBN: 978-3-031-43605-5
eBook Packages: Computer ScienceComputer Science (R0)