Tatsumi UEZATO

     

Current Position

Tatsumi Uezato is a research scientist at RIKEN Center for Advanced Intelligence Project (AIP), Japan. His research interests include hyperspectral image processing, remote sensing, and machine learning.
He is a member of the IEEE (2017), IEEE Geoscience and Remote Sensing Society (GRSS), and IEEE signal processing society (SPS). He is a reviewer of IEEE transactions on geoscience and remote sensing, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Remote Sensing, Sensor and applied remote sensing.

Biography

2021 Jun	-	Present	Research scientist, RIKEN AIP
2019 Jan	-	2021 May	Postdoctoral researcher, RIKEN AIP
2017 Jan	-	2018 Dec	Postdoctoral researcher, IRIT
2016 Sep	-	2016 Dec	Research associate, The University of Sydney
2013 Feb	-	2016 Dec	Ph.D. in Engineering & IT, The University of Sydney

Journal Papers

1. T. Uezato, N. Yokoya, and W. He, " Illumination invariant hyperspectral image unmixing based on a digital surface model ," IEEE Transactions on Image Processing, vol. 29, no. 1, pp. 3652-3664, 2019.
   Quick Abstract

   Abstract: Although many spectral unmixing models have been developed to address spectral variability caused by variable incident illuminations, the mechanism of the spectral variability is still unclear. This paper proposes an unmixing model, named illumination invariant spectral unmixing (IISU). IISU makes the first attempt to use the radiance hyperspectral data and a LiDAR-derived digital surface model (DSM) in order to physically explain variable illuminations and shadows in the unmixing framework. Incident angles, sky factors, visibility from the sun derived from the LiDAR-derived DSM support the explicit explanation of endmember variability in the unmixing process from radiance perspective. The proposed model was efficiently solved by a straightforward optimization procedure. The unmixing results showed that the other state-of-the-art unmixing models did not work well especially in the shaded pixels. On the other hand, the proposed model estimated more accurate abundances and shadow compensated reflectance than the existing models.

Conference Papers

1. X. Dong, N. Yokoya, L. Wang, T. Uezato, "Learning mutual modulation for self-supervised cross-modal super-resolution," European Conference on Computer Vision (ECCV), 2022.
2. W. He, Q. Yao, N. Yokoya, T. Uezato, H. Zhang, L. Zhang, "Spectrum-aware and transferable architecture search for hyperspectral image restoration," European Conference on Computer Vision (ECCV), 2022.
3. T. Uezato, D. Hong, N. Yokoya, W. He, "Guided deep decoder: Unsupervised image pair fusion," European Conference on Computer Vision (ECCV) (spotlight), 2020.