Spatiotemporal Fusion for Nighttime Light Remote Sensing Images With Multivariate Activation Function

Yi Zeng, Boya Gao, Peng Liu, Xinyi Zhao

Abstract: Nighttime light (NTL) remote sensing images record various light information. However, it is often difficult for NTL remote sensing images to have both high temporal and high spatial resolution. To solve the above problem, this letter proposes a spatiotemporal fusion model for NTL images. Based on the convolutional neural network (CNN), we designed a new multivariate activation function and introduced adaptive instance normalization (AdaIN) to improve the quality of image fusion. Specifically, this multivariate activation function captures the abrupt changes from reference time to target time, removes redundant information, and retains complementary information. Meanwhile, the AdaIN effectively reduces the systematic errors caused by different sensors. To verify the effectiveness of the model, this letter uses Luojia1-01 and VNP46A1 remote sensing images to construct an NTL remote sensing dataset for fusion and carry out comparative experiments and ablation experiments. The results show that our method has a better performance.