Assessment of Spatiotemporal Fusion Algorithms for Planet and Worldview Images.

Chiman Kwan,Xiaolin Zhu,Bryan Chou,Giovanni Marchisio,Yuzhong Shen,Daniel Perez,Feng Gao,Jiang Li,Krzysztof Koperski

doi:10.3390/s18041051

Abstract

Although Worldview-2 (WV) images (non-pansharpened) have 2-m resolution, the re-visit times for the same areas may be seven days or more. In contrast, Planet images are collected using small satellites that can cover the whole Earth almost daily. However, the resolution of Planet images is 3.125 m. It would be ideal to fuse these two satellites images to generate high spatial resolution (2 m) and high temporal resolution (1 or 2 days) images for applications such as damage assessment, border monitoring, etc. that require quick decisions. In this paper, we evaluate three approaches to fusing Worldview (WV) and Planet images. These approaches are known as Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), Flexible Spatiotemporal Data Fusion (FSDAF), and Hybrid Color Mapping (HCM), which have been applied to the fusion of MODIS and Landsat images in recent years. Experimental results using actual Planet and Worldview images demonstrated that the three aforementioned approaches have comparable performance and can all generate high quality prediction images.

Highlights

Due to high spatial resolution, Worldview-2 (WV) images have been widely used for hazard assessment, nuclear site monitoring, border activity detection, etc
We summarize the results of applying Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), Flexible Spatiotemporal Data Fusion (FSDAF), and Hybrid Color Mapping (HCM) approaches to fusing WV and Planet images for forward prediction
Since our main interest is in forward prediction, we only compare with STARFM and FSDAF, which require one pair of Worldview and Planet images at an earlier time, and one Planet image at the time of prediction

Summary

Introduction

Due to high spatial resolution, Worldview-2 (WV) images have been widely used for hazard assessment, nuclear site monitoring, border activity detection, etc. The resolution of Planet images is lower than that of WV, Planet images use multiple small satellites to collect images and can cover the same area almost daily. It would be ideal to fuse the above images to create a high spatial and high temporal resolution image sequence so that quick and responsive actions can be taken for certain applications such as damage assessment due to hurricanes, fires, tsunamis, etc. One may question the necessity of this research, as the spatial resolutions of WV (2 m) and Planet (3.125 m) images are all of high resolution and do not seem to differ that much.

Objectives

Results

Conclusion