Blending Ultra Spectral Images of Multi-Source Remote Sensors

Images and procedures from remote sensing are effective tools for studying the earth's surface. Data quality is essential for improving remote sensing applications and producing crisp, noise-free images. Due to the different gathering methods, obtaining a free set of data is quite challenging in most cases. So, picture or information fusion is crucial in far-flung sensing applications. Spatiotemporal fusion (STF) is a method for fusing pix with the proper temporal and spatial decision by integrating (temporally dense) coarse-resolution pictures with (temporally sparse) fine-resolution pictures. This paper makes a specialty of enforcing spatiotemporal fusion of multi-supply remote sensing pictures. In this paper, STF of multi-source remote sensing images, specifically Landsat and Sentinel sensors images is performed using the ESTARFM fusion method. In total 2 experiments were conducted with Landsat 7, Landsat 8, and Sentinel 2 data. In experiment 1 Landsat 7, and Sentinel 2 images are considered fine and coarse resolution images respectively, and in experiment 2 Landsat 8, and Sentinel 2 as fine and coarse resolution images. The metrics suggest that by applying the STF method, the similarity between the fused image and the original image at the prediction time of experiment 2 is more when compared to the corresponding image results of experiment 1.

• Publication year

  2022

• Venue

  2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)

• Publication date

  2022-11-16

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICECCME55909.2022.9988603
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An enhanced spatiotemporal fusion method – Implications for DNN based time-series LAI estimation by using Sentinel-2 and MODIS

  2022cited by this paper
• Spatiotemporal Fusion Modelling Using STARFM: Examples of Landsat 8 and Sentinel-2 NDVI in Bavaria

  2022cited by this paper
• Spatio-temporal fusion for remote sensing data: an overview and new benchmark

  2020cited by this paper
• Using spatio-temporal fusion of Landsat-8 and MODIS data to derive phenology, biomass and yield estimates for corn and soybean.

  2019cited by this paper
• Spatiotemporal Analysis of Landsat-8 and Sentinel-2 Data to Support Monitoring of Dryland Ecosystems

  2018cited by this paper
• Spatiotemporal Fusion of Multisource Remote Sensing Data: Literature Survey, Taxonomy, Principles, Applications, and Future Directions

  2018cited by this paper
• Fusion of Landsat 8 OLI and Sentinel-2 MSI Data

  2017cited by this paper
• Enhancing Spatio-Temporal Fusion of MODIS and Landsat Data by Incorporating 250 m MODIS Data

  2017cited by this paper

• Blending of Landsat and Sentinel images using Multi-sensor fusion

  2023cites this paper
• Spatial-Temporal Analysis for Traffic Incident Detection Using Deep Learning

  2023cites this paper
• Deep Learning Based Image Fusion Applied on Landsat-8 Archival Data Using UVCGAN

  2023cites this paper