Geoinformatics Unit

Paper accepted for publication in IEEE TGRS

June 13, 2019

Our paper entitled "Remote sensing image reconstruction using tensor ring completion and total-variation" written by Wei He, Naoto Yokoya, Longhao Yuan, and Qibin Zhao has been accepted for publication in IEEE Transactions on Geoscience and Remote Sensing (TGRS).

Time-series remote sensing (RS) images are often corrupted by various types of missing information such as dead pixels, clouds, and cloud shadows that significantly influence the subsequent applications. In this paper, we introduce a new low-rank tensor decomposition model, termed tensor ring (TR) decomposition, to the analysis of RS datasets and propose a TR completion method for the missing information reconstruction. The proposed TR completion model has the ability to utilize the low-rank property of time-series RS images from different dimensions. To furtherly explore the smoothness of the RS image spatial information, total-variation regularization is also incorporated into the TR completion model. The proposed model is efficiently solved using two algorithms, the augmented Lagrange multiplier (ALM) and the alternating least square (ALS) methods. The simulated and real data experiments show superior performance compared to other state-of-the-art low-rank related algorithms.


Landsat 7 image restoration results using different methods. Our proposed methods: TVTRALM and TVTRALS.