Iterative relabeling using spectral neighborhoods
View Patent ↗A first image is received. An initial label is assigned to at least some pixels in the first image, including by assigning a first label to a first pixel. A determination is made, based at least in part on labels of spectral neighbors of the first pixel, that the first pixel's label should be replaced with a different label. The first pixel's label is updated with the different label.
1. A system, comprising:
a processor configured to:
receive a first image;
assign an initial label to at least some pixels in the first image, including by assigning a first label to a first pixel;
determine, based at least in part on labels of spectral neighbors of the first pixel, that the first pixel's label should be replaced with a different label;
update the first pixel's label with the different label;
receive a second image; and
generate as output a composite classification image wherein a label of a given pixel in the composite classification image is selected from one of a label determined for the given pixel as it appears in the first image and a label for the given pixel as it appears in the second image; and
a memory coupled to the processor and configured to provide the processor with instructions.
2. The system of claim 1 wherein the determination is based at least in part on a majority vote of the spectral neighbors.
3. The system of claim 1 wherein the spectral neighbors comprise nearest neighbors.
4. The system of claim 1 wherein the initial label is assigned based at least in part by a classifier trained using a training set.
5. The system of claim 1 wherein the initial label is assigned based at least in part by a classifier that takes as input the received first image and a boundary map.
6. The system of claim 1 wherein the initial label is assigned using a historical classification.
7. The system of claim 6 wherein the historical classification is determined from crop data.
8. The system of claim 1 wherein the processor is further configured to iteratively refine the first pixel's label until convergence.
9. The system of claim 1 wherein the second image is included in a time series with the first image.
10. The system of claim 1 wherein the first image and the second image were captured by different sensors.
11. A method, comprising:
receiving a first image;
assigning an initial label to at least some pixels in the first image, including by assigning a first label to a first pixel;
determining, based at least in part on labels of spectral neighbors of the first pixel, that the first pixel's label should be replaced with a different label;
updating the first pixel's label with the different label;
receiving a second image; and
generating as output a composite classification image wherein a label of a given pixel in the composite classification image is selected from one of a label determined for the given pixel as it appears in the first image and a label for the given pixel as it appears in the second image.
12. The method of claim 11 wherein determining that the first pixel's label should be replaced with the different label is based at least in part on a majority vote of the spectral neighbors.
13. The method of claim 11 wherein the spectral neighbors comprise nearest neighbors.
14. The method of claim 11 wherein the initial label is assigned based at least in part by a classifier trained using a training set.
15. The method of claim 11 wherein the initial label is assigned based at least in part by a classifier that takes as input the received first image and a boundary map.
16. The method of claim 11 wherein the initial label is assigned using a historical classification.
17. The method of claim 11 further comprising iteratively refining the first pixel's label until convergence.
18. A computer program product embodied in a tangible computer readable storage medium and comprising computer instructions for:
receiving a first image;
assigning an initial label to at least some pixels in the first image, including by assigning a first label to a first pixel;
determining, based at least in part on labels of spectral neighbors of the first pixel, that the first pixel's label should be replaced with a different label;
updating the first pixel's label with the different label;
receiving a second image; and
generating as output a composite classification image wherein a label of a given pixel in the composite classification image is selected from one of a label determined for the given pixel as it appears in the first image and a label for the given pixel as it appears in the second image.
19. The method of claim 16 wherein the historical classification is determined from crop data.
20. The method of claim 11 wherein the second image is included in a time series with the first image.
21. The method of claim 11 wherein the first image and the second image were captured by different sensors.