HYPERSPECTRAL CLASSIFICATION VIA SPATIAL CONTEXT EXPLORATION WITH MULTI-SCALE CNN

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

6 Scopus Citations
View graph of relations

Author(s)

  • Zhongqi Tian
  • Jingyu Ji
  • Shaohui Mei
  • Shuai Wan
  • Qian Du

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2018 IEEE International Geoscience & Remote Sensing Symposium - Proceedings
PublisherIEEE
Pages2563-2566
ISBN (Electronic)978-1-5386-7150-4
Publication statusPublished - Jul 2018

Publication series

NameIEEE International Symposium on Geoscience and Remote Sensing IGARSS
ISSN (Print)2153-6996

Conference

Title38th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
PlaceSpain
CityValencia
Period22 - 27 July 2018

Abstract

Spatial context has shown to be very useful in hyperspectral image processing. Existing convolutional neural network (CNN)-based methods for hyperspectral classification explore spatial context by single-scale convolution kernels in 2D or 3D shapes. However, such single-scale convolution may not be capable to explore the complex spatial context in a hyperspectral image. In this paper, we propose a multi-scale CNN, MS-CNN to explore the spatial context in different extents, in which adaptive spatial neighborhood convolution kernels are used to simultaneously extract multiple spectral-spatial features from spatial context of pixels. These features obtained by different spatial kernels are then concatenated and fused for further feature extraction and classification. Experimental results show that the proposed adaptive spatial neighborhood convolution are more effective to explore spatial context than traditional single-scale spatial convolution and the performance of the proposed MS-CNN outperforms several state-of-art CNNs for classification of hyperspectral images.

Research Area(s)

  • Classification, Convolutional neural network, Hyperspectral, Spatial context

Citation Format(s)

HYPERSPECTRAL CLASSIFICATION VIA SPATIAL CONTEXT EXPLORATION WITH MULTI-SCALE CNN. / Tian, Zhongqi; Ji, Jingyu; Mei, Shaohui; Hou, Junhui; Wan, Shuai; Du, Qian.

2018 IEEE International Geoscience & Remote Sensing Symposium - Proceedings. IEEE, 2018. p. 2563-2566 8518292 (IEEE International Symposium on Geoscience and Remote Sensing IGARSS).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)