Back to results
US 2019/0057245 A1Published application
Satellite image classification across multiple resolutions and time using ordering constraint among instances
AssigneeRegents of the University of Minnesota
InventorsAnkush Khandelwal, Anuj Karpatne, Vipin Kumar
Life of this patent
Estimating the term…
Abstract
A method includes classifying low-resolution pixels of a low-resolution satellite image of a geographic area to form an initial classification map and selecting at least one physically-consistent classification map of the low-resolution pixels based on the initial classification map. A water level associated with at least one of the physically-consistent classification maps is then used to identify a set of high-resolution pixels representing a perimeter of water in the geographic area.
Claims20
A method comprising:
- receiving a satellite image of an area;
- classifying each pixel in the satellite image using a model;
- for each of a plurality of possible water levels, determining a cost associated with the water level, wherein determining the cost associated with a water level comprises:
- determining a number of pixels for which the model classification must change to be consistent with the water level;
- and
- determining a difference between the water level and a water level determined for the area at a previous time point;
- selecting the lowest cost water level;
- and
- using the selected lowest cost water level to reclassify at least one pixel.
6 more elements
A method comprising:
- classifying low-resolution pixels of a low-resolution satellite image of a geographic area to form an initial classification map;
- selecting at least one physically-consistent classification map of the low-resolution pixels based on the initial classification map;
- and
- using a water level associated with at least one of the physically-consistent classification maps to identify a set of high-resolution pixels representing a perimeter of water in the geographic area.
1 more element
A system comprising:
- a classifier receiving a low-resolution image of a geographic area and classifying each pixel of the image to form an initial classification map;
- a comparison module comparing the initial classification map to a plurality of physically-consistent classification maps to select a physically-consistent classification map;
- and
- a high-resolution classifier classifying high-resolution pixels of the geographic area based on the selected physically-consistent classifier map.
1 more element
Dependencies are inferred from the claim text.