Ndvi versus cnn features in deep learning for land cover classification of aerial images

Anushree Ramanath, Saipreethi Muthusrinivasan, Yiqun Xie, Shashi Shekhar, Bharathkumar Ramachandra

Research output: Contribution to conferencePaperpeer-review

Abstract

Agriculture plays a strategic role in the economic development of a country. Appropriate classification of land cover images is vital for planning the right agricultural practices and maintaining sustainable environment. This paper provides methods and analysis for land cover classification of remote sensing images. Satellite images form the input while mapping of every image to a distinct class is obtained as output. The objective is to compare the hand-crafted features based on Normalized Difference Vegetation Index (NDVI) and feature learning from Convolutional Neural Networks (CNN). The rationale of this work is to take advantage of techniques that are illumination invariant. NDVI versus CNN features have been compared on a linear Support Vector Machine (SVM). However, no comparative study has been carried out related to DVI based features and CNN based features on a deep learning classifier. This paper compares the performance of different classifiers and evaluates them based on test accuracy.

Original languageEnglish (US)
Pages6483-6486
Number of pages4
DOIs
StatePublished - 2019
Event39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan
Duration: Jul 28 2019Aug 2 2019

Conference

Conference39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country/TerritoryJapan
CityYokohama
Period7/28/198/2/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

  • Aerial Images
  • Convolutional Neural Network (CNN)
  • Feature Extraction
  • Land scene classification
  • Multi Layer Perceptron (MLP)
  • Normalized Difference Vegetation Index (NDVI)
  • Remote Sensing

Fingerprint

Dive into the research topics of 'Ndvi versus cnn features in deep learning for land cover classification of aerial images'. Together they form a unique fingerprint.

Cite this