International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Volume XLII-3/W10
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W10, 539–545, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W10-539-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W10, 539–545, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W10-539-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

  07 Feb 2020

07 Feb 2020

RESEARCH ON SE-INCEPTION IN HIGH-RESOLUTION REMOTE SENSING IMAGE CLASSIFICATION

Z. L. Cai1, Q. Weng2, and S. Z. Ye3 Z. L. Cai et al.
  • 1College of Mathematics and Computer Science,Fuzhou University, Fuzhou, China
  • 2National Engineering Research Centre of Geospatial Information Technology, Fuzhou University, Fuzhou, China
  • 3Research Institute of Intelligent Manufacturing Simulation, Fuzhou University, Fuzhou, China

Keywords: Deep Learning, Transfer Learning, Convolutional Neural Networks Inception-V3, SENet, High Spatial Resolution Remote Sensing Images, Remote Sensing Image Classification

Abstract. With the deepening research and cross-fusion in the modern remote sensing image area, the classification of high spatial resolution remote sensing images has captured the attention of the researchers in the field of remote sensing. However, due to the serious phenomenon of “same object, different spectrum” and “same spectrum, different object” of high-resolution remote sensing image, the traditional classification strategy is hard to handle this challenge. In this paper, a remote sensing image scene classification model based on SENet and Inception-V3 is proposed by utilizing the deep learning method and transfer learning strategy. The model first adds a dropout layer before the full connection layer of the original Inception-V3 model to avoid over-fitting. Then we embed the SENet module into the Inception-V3 model for optimizing the network performance. In this paper, global average pooling is used as squeeze operation, and then two fully connected layers are used to construct a bottleneck structure. The model proposed in this paper is more non-linear, can better fit the complex correlation between channels, and greatly reduces the amount of parameters and computation. In the training process, this paper adopts the transfer learning strategy, makes full use of existing models and knowledge, improves training efficiency, and finally obtains scene classification results. The experimental results based on AID high-score remote sensing scene images show that SE-Inception has faster convergence speed and more stable training effect than the original Inception-V3 training. Compared with other traditional methods and deep learning networks, the improved model proposed in this paper has greater accuracy improvement.