4 January 2018 in IEEE Geoscience and Remote Sensing Letters
Semantic segmentation of aerial images refers to assigning one land cover category to each pixel. This is a challenging task due to the great differences in the appearances of ground objects. Many attempts have been made during the past decades. In recent years, convolutional neural networks (CNNs) have been introduced in the remote sensing field, and various solutions have been proposed to realize dense semantic labeling with CNNs. In this letter, we propose shuffling CNNs to realize semantic segmentation of aerial images in a periodic shuffling manner. This approach is a supplement to current methods for semantic segmentation of aerial images. We propose a naive version and a deeper version of this method, and both are adept at detecting small objects. Additionally, we propose a method called field-of-view (FoV) enhancement that can enhance the predictions. This method can be applied to various networks, and our experiments verify its effectiveness. The final results are further improved through an ensemble method that averages the score maps generated by the models at different checkpoints of the same network. We evaluate our models using the ISPRS Vaihingen and Potsdam data sets, and we acquire promising results using these two data sets.
13 December 2017 in Remote Sensing Letters
In this letter, we propose a deep convolutional encoder-decoder model for remote sensing images semantic pixel labelling. Specifically, the encoder network is employed to extract the high-level semantic feature of hyperspectral images and the decoder network is employed to map the low resolution feature maps to full input resolution feature maps for pixel-wise labelling. Different from traditional convolutional layers we use a ‘dilated convolution’ which effectively enlarge the receptive field of filters in order to incorporate more context information. Also the fully connected conditional random field (CRF) is integrated into the model so that the network can be trained end-to-end. CRF can effectively improve the localization performance. Experiments on the Vaihingen and Potsdam dataset demonstrate that our model can make promising performance.