Volume XLII-2/W7
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W7, 1451-1454, 2017
https://doi.org/10.5194/isprs-archives-XLII-2-W7-1451-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W7, 1451-1454, 2017
https://doi.org/10.5194/isprs-archives-XLII-2-W7-1451-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.

  14 Sep 2017

14 Sep 2017

A ROUGH SET DECISION TREE BASED MLP-CNN FOR VERY HIGH RESOLUTION REMOTELY SENSED IMAGE CLASSIFICATION

C. Zhang1, X. Pan2, S. Q. Zhang3, H. P. Li3, and P. M. Atkinson1 C. Zhang et al.
  • 1Lancaster Environment Centre, Lancaster University, Lancaster, Lancaster, LA1 4YQ UK
  • 2School of Computer Technology and Engineering, Changchun Institute of Technology, 130021 Changchun, China
  • 3Northeast Institute of Geography and Agroecology, Chinese Academic of Science, 130102 Changchun, China

Keywords: Convolutional Neural Network, Multilayer Perceptron, VHR remotely sensed imagery, Rough Set Theory, Decision Tree, Fusion Decision

Abstract. Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR) images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning approaches have been developed over the past decades, most of them are developed toward pixel level spectral differentiation, e.g. Multi-Layer Perceptron (MLP), which are unable to exploit abundant spatial details within VHR images.

This paper introduced a rough set model as a general framework to objectively characterize the uncertainty in CNN classification results, and further partition them into correctness and incorrectness on the map. The correct classification regions of CNN were trusted and maintained, whereas the misclassification areas were reclassified using a decision tree with both CNN and MLP. The effectiveness of the proposed rough set decision tree based MLP-CNN was tested using an urban area at Bournemouth, United Kingdom. The MLP-CNN, well capturing the complementarity between CNN and MLP through the rough set based decision tree, achieved the best classification performance both visually and numerically. Therefore, this research paves the way to achieve fully automatic and effective VHR image classification.