Advanced cloud cover assessment for panchromatic images
AssigneeDigitalGlobe, Inc.
InventorChris Padwick
Life of this patent
Estimating the term…
Abstract
Cloud cover assessment system and method provides for automatically determining whether a target digital image acquired from remote sensing platforms is substantially cloud-free. The target image is acquired and compared to a corresponding known cloud-free image from a cloud-free database, using an optimized feature matching process. A feature matching statistic is computed between pixels in the target image and pixels in the cloud-free image and each value is converted to a feature matching probability. Features in the target image that match features in the cloud-free image exhibit a high value of feature matching probability, and are considered unlikely to be obscured by clouds, and may be designated for inclusion in the cloud-free database.
Claims33
A computer-implemented method, comprising:
- receiving a panchromatic image;
- comparing the panchromatic image to a second image from a database of images, the second image having cloud-free regions;
- matching a first feature from the panchromatic image to a second feature from the second image, wherein the second feature is located in one of the cloud-free regions of the second image;
- and
- identifying a cloudy region in the panchromatic image based on the matching of the first feature to the second feature.
A computer-implemented method, comprising:
- receiving a panchromatic image;
- identifying an area of interest in the image;
- automatically creating a first data set from the area of interest;
- receiving a second data set from a database, wherein the second data set includes data regarding one or more cloud-free regions of an image;
- comparing the first data set to the second data set to create a third data set;
- and
- identifying cloudy data points in the panchromatic image based on the third data set.
A computer-implemented method, comprising:
- receiving a first panchromatic image having a first set of pixels, wherein the first panchromatic image has a resolution of at least 15 m;
- receiving a second panchromatic image from a database having a second set of pixels, wherein the second panchromatic image has a resolution of at least 15 m, wherein the second set of pixels is located in a cloud-free region of the second panchromatic image;
- cross correlating the first set of pixels with the second set of pixels to create a cross-correlated set of pixels;
- and
- identifying a cloudy region in the first panchromatic image from the cross-correlated set of pixels.
Dependencies are inferred from the claim text.