Hyperspectral Anomaly Detection Based on Multi-Scale Central Difference Convolution Network

• Published in: IEEE geoscience and remote sensing letters p. 1
• Main Authors: Wang, Xiaoyi, Wang, Liguo, Vizziello, Anna, Gamba, Paolo
• Format: Journal Article
• Language: English
• Published: IEEE 15.08.2023
• Subjects: Anomaly detection; Artificial neural networks; central differential convolution; Convolution; Feature extraction; Geoscience and remote sensing; Hyperspectral image; Hyperspectral imaging; Kernel; multi-scale; spatial difference
• ISSN: 1545-598X
• DOI: 10.1109/LGRS.2023.3305814

Convolutional neural networks (CNNs) have a strong capacity to extract deep-level features from data. However, the standard convolution (SC) only considers the intensity-information and ignores the spatial gradient-information. Since spatial difference features are more robust to illumination invariance, this letter proposes a Multi-Scale Central Differential Convolutional (MSCDC) network for hyperspectral anomaly detection. Specifically, we use Central Difference Convolution (CDC) to combine intensity- and gradient-information. This solution improves the representation ability of HSIs and enhances the difference between the background and the anomalies. Furthermore, to fully utilize local spatial information and adapt to targets with different sizes, CDC kernels of three different sizes are used to capture high-, mid- and low-level features, respectively. Finally, a SC is used to fuse multi-scale features and obtain more reliable spatial information. Compared with five popular hyperspectral anomaly detection methods on four real-world HSI datasets, the proposed MSCDC exhibits excellent performances.