A geometric misregistration resistant data fusion approach for adding red-edge (RE) and short-wave infrared (SWIR) bands to high spatial resolution imagery
High spatial resolution images have been widely applied to the monitoring of land surfaces during the past decades. However, satellite and unmanned aerial vehicle (UAV) sensors (e.g., IKONOS, and QuickBird) usually only provide visible and near-infrared spectral bands with a high spatial resolution....
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/04be7d8f8db940cfa1a4bef4871baae4 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Sumario: | High spatial resolution images have been widely applied to the monitoring of land surfaces during the past decades. However, satellite and unmanned aerial vehicle (UAV) sensors (e.g., IKONOS, and QuickBird) usually only provide visible and near-infrared spectral bands with a high spatial resolution. Such limited spectral bands at a high spatial resolution are not adequate for crucial environmental and agricultural studies that require essential bands (e.g., the red-edge (RE) and the short-wave infrared (SWIR)), such as land cover classification and the estimation of plant physiological parameters. On the contrary, abundant spectral information is commonly available on sensors with a medium spatial resolution (e.g., Landsat, and Sentinel-2). Existing spatial-spectral fusion methods can leverage the unique advantages of these two types of sensors, and produce synthesized images with both spatial and spectral detail. However, most spatial-spectral methods ignore the inherent geometric registration errors when using multi-source data, inevitably introducing the errors into the fusion result. To address the limitation, this study presents a new spatial-spectral fusion method, the Misregistration-Resistant Data Fusion approach (MRDF), to add new spectral bands to the high spatial resolution images from medium resolution images. The proposed method is composed of a local-model-based similar pixel searching and a global partial least square (PLS) regression, and has the following advantages: (1) the local model utilizes neighborhood similar pixels to generate predictions robust against geometric misregistration; (2) the combined model integrates a global PLS regression to improve fusion accuracy for the SWIR bands; (3) the extended-box strategy and spatial filtering can relieve geometric errors when minimizing residuals for the SWIR bands. Satellite and airborne data from three sites were used to compare the performance of MRDF with seven other typical methods. Results showed that MRDF not only produced accurate fusion results with above-average efficiency but also improved the classification accuracy, which substantiated its great potential for various applications. |
---|