No abstract

Land use classification of high-resolution remote sensing (HRRS) images is a challenging and prominent problem in which pretrained convolutional neural networks (CNNs) have made amazing achievements. However, single-structured pretrained CNNs have limitations to obtain high classification accuracy. Besides, each pretrained CNNs has different classification ability to classify land use. Therefore, taking advantages of different pretrained CNNs is essential for land use classification. In this study, we propose a novel classification approach based on multi-structure joint decision-making strategy and pretrained CNNs. The basic idea is to apply three CNNs to classify land use separately with the final classification results achieved by joint decision-making strategy. The proposed approach comprises of three steps. First, we create a new fully connected layer and Softmax classification layer. We combine them with the convolutional layers of AlexNet, Inception-v3, and ResNet18. AlexNet also includes the first two layers of fully connected layers. Secondly, we train these designed CNNs to converge by momentum-driven stochastic gradient descent. Thirdly, we utilize joint decision-making strategy to obtain the final prediction results by combining the prediction results of these designed CNNs. The performance of the proposed approach is evaluated on the UC Merced land use, AID, NWPU-45, OPTIMAL-31 datasets and further compared with the state-of-the-art methods. Results demonstrate that the proposed approach outperforms other methods. The benefits of the proposed approach are threefold. First, the multi-structure network maximizes different pretrained CNN structures to extract rich convolution features. Secondly, it could remarkably improve the classification accuracy of indistinguishable land use types of the HRRS images. Thirdly, it has great potential on small dataset with more land use types. The proposed CNN based on multi-structure joint decision approach achieves accurate and reliable land use classification with these benefits.INDEX TERMS Land use classification, convolutional neural network, transfer learning, high-resolution remote sensing images, multi-structure.

No abstract

With the development of web maps, people are no longer satisfied with fixed and limited scale map services but want to obtain personalized and arbitrary scale map data. Continuous map generalization technology can be used to generate arbitrary scale map data. This paper proposes a morphing method for continuously generalizing linear map features using shape context matching and hierarchical interpolation (SCM-HI). More specifically, shape characteristics are quantitatively described by shape context on which shape similarity is measured based on a chi-square method; then, two levels of interpolation, skeleton and detail interpolations, are employed to generate the geometry of intermediate curves. The main contributions of our approach include (1) exploiting both the geometry and spatial structure of a vector curve in shape matching by using shape context, and (2) preserving both the main shape structure as-rigid-as-possible and local geometric details as gradual and smooth as possible for intermediate curves by hierarchical interpolation. Experiments show that our method generates plausible morphing effects and can thus serve as a robust approach for continuous generalization of linear map features.