Volume XLII-3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 2035-2039, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-2035-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 2035-2039, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-2035-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 Apr 2018

30 Apr 2018

SEMANTIC SEGMENTATION OF CONVOLUTIONAL NEURAL NETWORK FOR SUPERVISED CLASSIFICATION OF MULTISPECTRAL REMOTE SENSING

L. Xue1, C. Liu1, Y. Wu1, and H. Li1,2 L. Xue et al.
  • 1Computer science and technology department, Jilin University, 130012 ChangChun, Jilin province, China
  • 2Symbol Computation and Knowledge Engineer of Ministry of Education, Jilin University, 130012 Changchun, Jilin province, China

Keywords: Semantic Segmentation, Multi Spectral Remote Sensing, Convolutional Neural Network, U-net, multi-scale image

Abstract. Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the classification of roads, vegetation, buildings and water from remote Sensing Imagery is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for ground object segmentation and the results could be further improved. This paper used convolution neural network named U-Net, its structure has a contracting path and an expansive path to get high resolution output. In the network , We added BN layers, which is more conducive to the reverse pass. Moreover, after upsampling convolution , we add dropout layers to prevent overfitting. They are promoted to get more precise segmentation results. To verify this network architecture, we used a Kaggle dataset. Experimental results show that U-Net achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.