LAUSR

Change detection (CD) with hyperspectral images (HSIs) can be effectively performed using deep learning networks (DLN) by taking advantages of HSIs for their abundant spectral and spatial information and the excellent performance of DLN in machine learning. By modeling the temporal dependence of multiscale representative features, more discriminative information reflecting land use and land cover (LULC) changes can be obtained by suppressing less correlated information while improving the robustness of pseudo-changes caused by imaging noises. However, preserving time-dependent multiscale representative features while extracting spatial-spectral features based on conventional DLN is difficult, mainly owning to the structural limitation of conventional DLN. A Multi-path Convolutional LSTM (MP-ConvLSTM) taking advantage of LSTM and CNN through the designed parallel architecture to learn multi-level temporal dependencies of bi-temporal HSIs, therefore, was proposed for extracting multiscale temporal-spatial-spectral features by combining hidden states from different paths of ConvLSTM in present study. In the proposed MP-ConvLSTM, the Efficient Channel Attention (ECA) module was introduced to refine features of different paths, and Siamese CNN was adopted to reduce HSIs’ dimensionality and extract preliminary features to build up an end-to-end trainable model for CD with HSIs. The validity of the MP-ConvLSTM was evaluated using binary and multi-class CD datasets. The CD accuracy of the proposed MP-ConvLSTM was visually and statistically evaluated by different criteria and compared with those derived from several state-of-the-art (SOTA) CD algorithms. The experiments demonstrated that our proposed model not only outperformed those SOTA CD models but also exhibited better trade-off between complexity and accuracy in general.