Quaternion Convolutional Neural Network With EMAP Representation for Multisource Remote-Sensing Data Classification.

The fusion and classification of hyperspectral images (HSIs) and light detection and ranging (LiDAR) data have been extensively studied using deep learning. However, traditional real-valued deep-learning methods have limitations in distinguishing internal and external relations and capturing fine spatial characteristics. To break through these limitations, this letter proposes a quaternion convolutional neural network (QCNN) with extended morphological attribute profile (EMAP) quaternion representation (called EQR) for multisource remote-sensing (RS) data classification by utilizing quaternion properties. Specifically, we first propose the EQR for each single-source data, which encodes the multiattribute features in a compact, yet comprehensive manner, highlighting the internal relations. Second, we embed EQR into QCNN to preserve the internal relations and enable the interaction of multiattribute features. Then, we develop the 3-D quaternion convolution (3DQConv) to better exploit the 3-D characteristic of HSIs. Finally, we design different attention mechanisms and a two-level fusion strategy for multisource data to learn enhanced features. Experiments on two multisource RS datasets show that the proposed method achieved better performance than other state-of-the-art classification methods. [ABSTRACT FROM AUTHOR]