Autoencoder Network for Hyperspectral Unmixing With Adaptive Abundance Smoothing

Autor:	Qunhui Qiu, Liaoying Zhao, Ziqiang Hua, Xiaorun Li
Rok vydání:	2021
Předmět:	Pixel Computer science business.industry Hyperspectral imaging Pattern recognition Geotechnical Engineering and Engineering Geology Regularization (mathematics) Autoencoder Softmax function Artificial intelligence Electrical and Electronic Engineering business Encoder Feature learning Smoothing
Zdroj:	IEEE Geoscience and Remote Sensing Letters. 18:1640-1644
ISSN:	1558-0571 1545-598X
Popis:	Autoencoder is an efficient technique for unsupervised feature learning, which can be applied to hyperspectral unmixing. In this letter, we present an autoencoder network with adaptive abundance smoothing (AAS) to solve the challenges of previous techniques. Specifically, the proposed method uses a multilayer encoder to obtain the abundance and a single-layer decoder to reconstruct the image. The AAS algorithm tackles the outliers by exploiting the spatial–contextual information and can be adaptive for each pixel. Moreover, the softmax function is used as the encoder output function with the help of $L_{1/2}$ regularization to produce sparse output. Experimental results of the synthetic and real data reveal the superior performance of the proposed method against other competitors.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4e2cbdfa74eefaf9b55c7d3ce99ecba6 https://doi.org/10.1109/lgrs.2020.3005999 Zobrazit plný text záznamu