High resolution land cover (HRLC)
High Resolution Land Cover (HRLC) may be provided. A first high resolution image of a scene may be received and a plurality of second medium resolution images of the scene taken over a period of time may be received. A segmentation of the first image may then be performed. Next, a plurality of transformations may be performed on the plurality of second images. Then a temporal stack layer for a plurality of temporal statistics for each of the plurality of transformations on the plurality of second images may be created. The temporal stack layer may then be intersected with the segmented first image using a plurality of spatial statistics to produce a plurality of spatio-temporal layers. A Machine Learning (ML) model may be used on the spatio-temporal layers to classify pixels in the first image into respective ones of a plurality of classifications.
1 . A method comprising:
receiving a first image of a scene;
receiving a plurality of second images of the scene taken over a period of time;
performing, by a computing device, a segmentation of the first image;
performing, by the computing device, a plurality of transformations on the plurality of second images;
creating, by the computing device, a temporal stack layer for a plurality of temporal statistics for each of the plurality of transformations on the plurality of second images;
intersecting, by the computing device, the temporal stack layer with the segmented first image using a plurality of spatial statistics, relative to segments of the segmented first image, to produce a plurality of spatio-temporal layers; and
using, by the computing device, a Machine Learning (ML) model on the plurality of spatio-temporal layers to classify pixels of the first image into respective ones of a plurality of classifications.
2 . The method of claim 1 , wherein one of the plurality of transformations comprises a Principal Component Analysis (PCA) transformation.
3 . The method of claim 1 , wherein one of the plurality of transformations comprises a Normalized Difference Vegetation Index (NDVI) transformation.
4 . The method of claim 1 , wherein one of the plurality of transformations comprises a Normalized Difference Wetness Index (NDWI) transformation.
5 . The method of claim 1 , wherein one of the plurality of transformations comprises a Modified Soil-Adjusted Vegetation Index (MSAVI) transformation.
6 . The method of claim 1 , wherein one of the plurality of transformations comprises a Tasseled Cap band 1 transformation.
7 . The method of claim 1 , wherein one of the plurality of transformations comprises a Tasseled Cap band 2 transformation.
8 . The method of claim 1 , wherein one of the plurality of transformations comprises a Tasseled Cap band 3 transformation.
9 . The method of claim 1 , wherein the plurality of temporal statistics comprise at least one of minimum, maximum, mean, median, standard deviation, and range.
10 . The method of claim 1 , wherein the plurality of spatial statistics comprise at least one of minimum, maximum, mean, standard deviation, and range.
11 . The method of claim 1 , wherein the plurality of classifications comprise at least one of deciduous trees, evergreen trees, scrub, grass, bare, built-up/structures, agriculture dry, agriculture wet, wetland, mangrove, water, snow/ice, clouds, and other impervious surface.
12 . The method of claim 1 , wherein the first image comprises a high resolution image, which includes a resolution of higher than 10 meters/pixel.
13 . The method of claim 1 , wherein the plurality of second images comprise medium resolution images, which includes a resolution of lower than 10 meters/pixel.
14 . A system comprising:
a memory storage; and
a processing unit coupled to the memory storage, wherein the processing unit is operative to:
receive a first image of a scene;
receive a plurality of second images of the scene taken over a period of time;
perform a segmentation of the first image;
perform a plurality of transformations on the plurality of second images;
create a temporal stack layer for a plurality of temporal statistics for each of the plurality of transformations on the plurality of second images;
intersect the temporal stack layer with the segmented first image using a plurality of spatial statistics, relative to segments of the segmented first image, to produce a plurality of spatio-temporal layers; and
use a Machine Learning (ML) model on the plurality of spatio-temporal layers to classify pixels of the first image into respective ones of a plurality of classifications.
15 . The system of claim 14 , wherein the plurality of transformations include multiple of: a Principal Component Analysis (PCA) transformation, a Normalized Difference Vegetation Index (NDVI) transformation, a Normalized Difference Wetness Index (NDWI) transformation, a Modified Soil-Adjusted Vegetation Index (MSAVI) transformation, a Tasseled Cap band 1 transformation, a Tasseled Cap band 2 transformation, and/or a Tasseled Cap band 3 transformation.
16 . The system of claim 14 , wherein the plurality of classifications comprise at least one of deciduous trees, evergreen trees, scrub, grass, bare, built-up/structures, agriculture dry, agriculture wet, wetland, mangrove, water, snow/ice, clouds, and other impervious surface.
17 . A non-transitory computer-readable medium that stores a set of instructions which when executed perform a method executed by the set of instructions comprising:
receiving a first image of a scene;
receiving a plurality of second images of the scene taken over a period of time;
performing a segmentation of the first image;
performing a plurality of transformations on the plurality of second images;
creating a temporal stack layer for a plurality of temporal statistics for each of the plurality of transformations on the plurality of second images;
intersecting the temporal stack layer with the segmented first image using a plurality of spatial statistics, relative to segments of the segmented first image, to produce a plurality of spatio-temporal layers; and
using a Machine Learning (ML) model on the plurality of spatio-temporal layers to classify pixels of the first image into respective ones of a plurality of classifications.
18 . The non-transitory computer-readable medium of claim 17 , wherein the first image comprises a high resolution image and wherein the plurality of second images comprise medium resolution images.