Deep-Learning Based Super-Resolution of Sentinel-2 Images for Monitoring Supercentenarian Olive Trees

被引：3

作者：

Panagiotopoulou, Antigoni ^{[1
,2
]}

Charou, Eleni ^{[2
]}

Poirazidis, Konstantinos ^{[3
]}

Voutos, Yorghos ^{[4
]}

Martinis, Aristotelis ^{[3
]}

Grammatikopoulos, Lazaros ^{[1
]}

Petsa, Eleni ^{[1
]}

Bratsolis, Emmanuel ^{[1
]}

Mylonas, Phivos ^{[4
]}

机构：

[1] Univ West Attica, Dept Surveying & Geoinformat Engn, Athens, Greece

[2] NCSR Demokritos, Inst Informat & Telecommun, Athens, Greece

[3] Ionian Univ, Dept Environm, Zakynthos, Greece

[4] Ionian Univ, Dept Informat, Corfu, Greece

来源：

25TH PAN-HELLENIC CONFERENCE ON INFORMATICS WITH INTERNATIONAL PARTICIPATION (PCI2021) | 2021年

关键词：

Image super-resolution; Deep-Learning; Sentinel-2; Supercentenarian olive tree;

D O I：

10.1145/3503823.3503851

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In the present work deep-learning based super-resolution (SR) is applied on Sentinel-2 images of the Zakynthos island, Greece, with the intention of detecting stress levels in supercentenarian olive trees due to water deficiency. The aim of this study is monitoring the stress in supercentenarian olive trees over time and over season. Specifically, the Carotenoid Reflectance Index 2 (CRI2) is calculated utilizing the Sentinel-2 bands B2 and B5. CRI2 maps at 10m and at 2.5mspatial resolutions are generated. In fact, the images of band B2 with original spatial resolution 10m are super-resolved to 2.5m. Regarding the images of band B5, these are SR resolved from 20m firstly to 10m and secondly to 2.5m. Deep-learning based SR techniques, namely DSen2 and RakSRGAN, are utilized for enhancing the spatial resolution to 10m and 2.5m. The following five seasons are considered autumn 2019, spring 2019, spring 2020, summer 2019 and summer 2020. In the future, comparisons with field measurements could better assess for the proposed methodology effectiveness regarding the recognition of stress levels in very old olive trees.

引用

页码：143 / 148

页数：6

共 8 条

[1]

Galar Mikel, 2019, INT ARCH PHOTOGRAMME, P95, DOI [10.5194/isprsarchives-XLII-2-W16-95-2019, DOI 10.5194/ISPRSARCHIVES-XLII-2-W16-95-2019]

[2] Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network [J].

Lanaras, Charis ;

Bioucas-Dias, Jose ;

Galliani, Silvano ;

Baltsavias, Emmanuel ;

Schindler, Konrad .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 146 :305-319

[3]

Navrozidis I, 2019, INT GEOSCI REMOTE SE, P7220, DOI [10.1109/IGARSS.2019.8898076, 10.1109/igarss.2019.8898076]

[4]

Panagiotopoulou Antigoni, 2021, LECT NOTES COMPUTER, V2667, DOI [10.1007/978-3-030-68787-8, DOI 10.1007/978-3-030-68787-8]

[5] Remote sensing images super-resolution with deep convolution networks [J].

Ran, Qiong ;

Xu, Xiaodong ;

Zhao, Shizhi ;

Li, Wei ;

Du, Qian .

MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (13-14) :8985-9001

[6]

Rodriguez Andres C., 2019, Pattern Recognition. 40th German Conference, GCPR 2018. Proceedings: Lecture Notes in Computer Science (LNCS 11269), P351, DOI 10.1007/978-3-030-12939-2_24

[7] Improved SRGAN for Remote Sensing Image Super-Resolution Across Locations and Sensors [J].

Xiong, Yingfei ;

Guo, Shanxin ;

Chen, Jinsong ;

Deng, Xinping ;

Sun, Luyi ;

Zheng, Xiaorou ;

Xu, Wenna .

REMOTE SENSING, 2020, 12 (08)

[8] RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution [J].

Zhang, Wenlong ;

Liu, Yihao ;

Dong, Chao ;

Qiao, Yu .

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :3096-3105

← 1 →