Generative Adversarial Autoencoder Network for Anti-Shadow Hyperspectral Unmixing

Abstract

Hyperspectral unmixing can handle the mixed pixels in hyperspectral images (HSIs). Shadows of objects in observed areas are recorded by sensors, resulting in an HSI contaminated by shadows. Therefore, shadow pollution is a grievous obstacle for unmixing applications. Although shadow pollution occurs frequently in HSIs, previous unmixing studies have never considered the interference caused by shadows. Hence, mitigating shadow interference for unmixing will be significant for further acquiring subpixel information. In this letter, we employ a generative adversarial autoencoder (GAA) to develop a supervised unmixing method that can substantially reduce the impacts of shadow for unmixing. Specifically, we adopt the GAA to establish an anti-shadow unmixing network (GAA-AS), where the encoder block is used to feature reinforcement, and the decoder serves for abundance estimation. Moreover, we adopt a spectral-aware loss (SAL) as the loss function of adversarial training, which makes the discriminator better capture the difference between pixels. Finally, a softmax layer is adopted for the abundance sum-to-one constraint (ASC). Several experiments verify the effectiveness and advantages of our GAA-AS. In the experiment with shadow-polluted data, the proposed GAA-AS improves accuracies by approximately 70 % compared to SOTA approaches in the quantitative experiment with synthetic data, and the impacts of shadow pollution are also significantly alleviated in the experiment with real shadow-polluted HSIs. Additionally, note that the proposed GAA-AS is competitive even when no shadow exists in HSIs, verified by the experiment with shadowless data.