ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Performance evaluation of convolutional neural network at hyperspectral and multispectral resolution for classification

Paul, S and Poliyapram, V and Kumar, DN and Nakamura, R (2019) Performance evaluation of convolutional neural network at hyperspectral and multispectral resolution for classification. In: SPIE Remote Sensing, 2019Proceedings of SPIE - The International Society for Optical Engineering, 9-11 Sept., 2019, Strasbourg; France.

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1117/12.2533077

Abstract

Convolutional Neural Network (CNN) has established as an effective deep learning model for hyperspectral image classification by considering both spectral and spatial information. In this study, the performance of two-dimensional (2D) CNN architecture is evaluated at hyperspectral and multispectral resolution. Two types of multispectral data are analyzed viz., original and transformed multispectral data. Hyperspectral bands are transformed to spectral resolution of multispectral bands by averaging the reflectances of specific hyperspectral narrow bands which are falling within the spectral ranges of multispectral bands. The well-known Pavia University dataset and a new dataset of Pear orchard are investigated in this study. In case of Pear orchard dataset, classification is performed with both types of multispectral data. All the experiments are carried out with the same 2D CNN architecture. In case of Pavia University dataset, hyperspectral and transformed multispectral data achieve OA() of 94.29±1.28 and 94.27±2.01 respectively considering 20 samples as training. In case of Pear orchard dataset, hyperspectral, multispectral and transformed multispectral data achieve OA() of 91.59±0.89, 88.65±1.35, and 93.24±0.16 respectively considering 20 samples as training. It is evident that transformed multispectral data, which comprises of inherent hyperspectral information, provides similar or better performance compared to hyperspectral data. Further, with the use of 3D CNN architecture, classification performance improves in case of Pavia University dataset, whereas it remains statistically similar in case of Pear orchard dataset. The present promising results illustrates the performance of CNN even in small dataset which is comparable to several published state-of-the art results on the same dataset.

Item Type: Conference Paper
Publication: Proceedings of SPIE - The International Society for Optical Engineering
Publisher: SPIE
Additional Information: Copyright of this article belongs to SPIE
Keywords: Convolution; Deep learning; Deep neural networks; Fruits; Image classification; Network architecture; Neural networks; Orchards; Remote sensing; Spectroscopy, 2D CNN; 3D CNN; Convolutional neural network; Hyperspectral Data; Multi-spectral data; Spectral-spatial classification, Classification (of information)
Department/Centre: Division of Mechanical Sciences > Centre for Earth Sciences
Division of Mechanical Sciences > Civil Engineering
Date Deposited: 28 Feb 2020 10:03
Last Modified: 28 Feb 2020 10:13
URI: http://eprints.iisc.ac.in/id/eprint/64563

Actions (login required)

View Item View Item