Fusion of Bi-Temporal Zhuhai-1 Orbita Hyperspectral and Multiseason Sentinel-2 Remote Sensing Imagery for Semantic Change Detection Based on Dual-Path 3DCNN-LSTM

Remote sensing imagery plays a crucial role in monitoring Earth's surface changes. With the advancement of computational power, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been increasingly applied in change detection tasks. This paper proposes a novel approach, the dual-path 3D Convolutional Recurrent Neural Network (3DCNN-LSTM), which integrates 3D CNNs and Long Short-Term Memory to fuse bi-temporal Zhuhai-1 Orbita hyperspectral and multi-season Sentinel-2 remote sensing imagery for semantic change detection. The proposed method extracts joint spectral-spatial features using 3D convolution layers. Subsequently, bi-temporal features and multi-season features are spliced as one time-sequence and fed to one LSTM modules (referred to as Str1). In another strategy (Str2), multi-source features are fed separately to two LSTM modules and fused in fully connected layers. Experiments demonstrate that Str1 and Str2 achieves better performance than Siamese convolutional multiple-layers RNN (SiamCRNN). Str1 obtained the overall accuracy of 99.12%, kappa coefficient of 98.77%, and F1 score of 98.91%, achieving improvements of 4.81%, 6.7%, and 6.51%, respectively, compared to SiamCRNN.