Automatic land cover classification of geo-tagged field photos by deep learning

Guang Xu, Xuan Zhu, Dongjie Fu, Jinwei Dong, Xiangming Xiao

Research output: Contribution to journalArticleResearchpeer-review

41 Citations (Scopus)

Abstract

With more and more crowdsourcing geo-tagged field photos available online, they are becoming a potentially valuable source of information for environmental studies. However, the labelling and recognition of these photos are time-consuming. To utilise such information, a land cover type recognition model for field photos was proposed based on the deep learning technique. This model combines a pre-trained convolutional neural network (CNN) as the image feature extractor and the multinomial logistic regression model as the feature classifier. The pre-trained CNN model Inception-v3 was used in this study. The labelled field photos from the Global Geo-Referenced Field Photo Library (http://eomf.ou.edu/photos) were chosen for model training and validation. The results indicated that our recognition model achieved an acceptable accuracy (48.40% for top-1 prediction and 76.24% for top-3 prediction) of land cover classification. With accurate self-assessment of confidence, the model can be applied to classify numerous online geo-tagged field photos for environmental information extraction.

Original languageEnglish
Pages (from-to)127-134
Number of pages8
JournalEnvironmental Modelling and Software
Volume91
DOIs
Publication statusPublished - 1 May 2017

Keywords

  • Convolutional neural network
  • Crowdsourced photos
  • Deep learning
  • Land cover
  • Multinomial logistic regression
  • Transfer learning

Cite this