Cut-line steering methods for forming a mosaic image of a geographical area
View Patent ↗A method for automatically steering mosaic cut lines along preferred routes to form an output mosaic image includes creating an assignment map corresponding to the output mosaic image where each pixel has an initial designation of unassigned; marking each pixel of the assignment map that intersects the preferred routes as being a Preferred Cut Line pixel to divide the Assignment Map into one or more regions; searching for each region to locate one or more source images that cover that region; and using a Selection Heuristic or Pairing Heuristic to determine quality of coverage. The Preferred Cut Line pixels are redesignated to match the image assignments of their bounded regions, and the output mosaic image is formed by contributing pixel values from the source images based upon the designations set forth in the assignment map.
1. A method for automatically steering mosaic cut lines along preferred routes to form an output mosaic image, comprising the steps of:
creating an assignment map corresponding to the output mosaic image where each pixel has an initial designation of unassigned;
marking pixels of the assignment map that intersect the preferred routes as being Preferred Cut Line pixels to divide the Assignment Map into one or more regions that are bounded by Preferred Cut Line pixels or the edge of the Assignment Map;
for each region, searching for one or more source images that completely cover that region, and responsive to multiple source images completely covering the region, using a Selection Heuristic to determine quality of coverage, and then designating each pixel in that region as being assigned to the source image determined to be best by the Selection Heuristic;
for any remaining unassigned regions, searching for two or more source images whose combined footprint completely covers the region, and for each set of two or more combined images, using a Pairing Heuristic to determine quality of coverage, and then designating each pixel in the region as being assigned to the two or more combined images determined best by the Pairing Heuristic;
redesignating the Preferred Cut Line pixels to match the image assignments of their bounded regions; and
forming the output mosaic image by contributing pixel values from the source images based upon the designations set forth in the Assignment Map.
2. The method of claim 1 , wherein the step of forming the output mosaic image is defined further as stepping through each pixel in the Assignment Map and using the image assignment stored there to determine which pixel values of the source image or images to use for the actual image content of the output mosaic image.
3. The method of claim 1 , wherein multiple source images are located that completely cover a particular region, and wherein the Selection Heuristic determines which source image is closest to nadir in the area covering the region.
4. The method of claim 1 , wherein multiple source images are located that completely cover a particular region, and wherein the Selection Heuristic used determines which source image covers the largest number of surrounding preferred cut line pixels.
5. The method of claim 1 , wherein multiple source images are located that completely cover a particular region, and wherein the Selection Heuristic used determines which source image covers the largest number of contiguous other regions.
6. The method of claim 1 , wherein multiple source images are located that combine to completely cover a particular region, and wherein the Pairing Heuristic used determines which source image covers the largest number of pixels in the region, and then determines which source image covers the largest number of remaining uncovered pixels in the region.
7. The method of claim 1 , wherein multiple source images are located that combine to completely cover a particular region, and wherein the Pairing Heuristic used determines which source image is closest to nadir at the center point of the region.
8. The method of claim 7 , wherein the Pairing Heuristic used also determines which sub-regions are not covered by the source image that is closest to nadir at the center point of the region, and then determines which source image is closest to nadir with respect to each sub-region.
9. The method of claim 1 , wherein the step of forming the output mosaic image is defined further as contributing pixel values from the source images based upon the designations set forth in the assignment map and feathering the pixel values along the preferred routes separating pixel values from different source images.
10. The method of claim 1 , wherein the preferred routes are determined utilizing a ground confidence map.
11. The method of claim 10 , wherein the ground confidence map is created via a method comprising the steps of:
selecting a plurality of geo-referenced, digital source images captured from different vantage points and cooperating to cover the geographic area, the source images having overlapping portions depicting a portion of the geographic area;
creating the ground confidence map of the geographic area, the ground confidence map having a plurality of pixels with each pixel corresponding to a particular geographic location;
assigning the pixels in the ground confidence map with pixel values indicative of composite ground confidence scores by:
calculating composite ground confidence scores for the pixel values of common geographic regions within the overlapping portions of the source images within a kernel corresponding to the particular geographic location of the pixels; and
storing pixel values indicative of the composite ground confidence score calculated for particular pixels, the pixel values indicative of a statistical probability that the geographical location represented by the particular pixels represent the ground.
12. The method of claim 1 , wherein the preferred routes are determined utilizing street center line data.
13. One or more non-transitory computer readable medium storing logic that when executed on one or more computers performs the functions of:
creating an assignment map corresponding to the output mosaic image where each pixel has an initial designation of unassigned;
marking pixels of the assignment map that intersect the preferred routes as being Preferred Cut Line pixels to divide the Assignment Map into one or more regions that are bounded by Preferred Cut Line pixels or the edge of the Assignment Map;
for each region, searching for one or more source images that completely cover that region, and responsive to multiple source images completely covering the region, using a Selection Heuristic to determine quality of coverage, and then designating each pixel in that region as being assigned to the source image determined to be best by the Selection Heuristic;
for any remaining unassigned regions, searching for two or more source images whose combined footprint completely covers the region, and for each set of two or more combined images, using a Pairing Heuristic to determine quality of coverage, and then designating each pixel in the region as being assigned to the two or more combined images determined best by the Pairing Heuristic;
redesignating the Preferred Cut Line pixels to match the image assignments of their bounded regions; and
forming the output mosaic image by contributing pixel values from the source images based upon the designations set forth in the Assignment Map.
14. The one or more non-transitory computer readable medium of claim 13 , wherein the step of forming the output mosaic image is defined further as stepping through each pixel in the Assignment Map and using the image assignment stored there to determine which pixel values of the source image or images to use for the actual image content of the output mosaic image.
15. The one or more non-transitory computer readable medium of claim 13 , wherein multiple source images are located that completely cover a particular region, and wherein the Selection Heuristic determines which source image is closest to nadir in the area covering the region.
16. The one or more non-transitory computer readable medium of claim 13 , wherein multiple source images are located that completely cover a particular region, and wherein the Selection Heuristic used determines which source image covers the largest number of surrounding preferred cut line pixels.
17. The one or more non-transitory computer readable medium of claim 13 , wherein multiple source images are located that completely cover a particular region, and wherein the Selection Heuristic used determines which source image covers the largest number of contiguous other regions.
18. The one or more non-transitory computer readable medium of claim 13 , wherein multiple source images are located that combine to completely cover a particular region, and wherein the Pairing Heuristic used determines which source image covers the largest number of pixels in the region, and then determines which source image covers the largest number of remaining uncovered pixels in the region.
19. The one or more non-transitory computer readable medium of claim 13 , wherein multiple source images are located that combine to completely cover a particular region, and wherein the Pairing Heuristic used determines which source image is closest to nadir at the center point of the region.
20. The one or more non-transitory computer readable medium of claim 19 , wherein the Pairing Heuristic used also determines which sub-regions are not covered by the source image that is closest to nadir at the center point of the region, and then determines which source image is closest to nadir with respect to each sub-region.
21. The one or more non-transitory computer readable medium of claim 13 , wherein the step of forming the output mosaic image is defined further as contributing pixel values from the source images based upon the designations set forth in the assignment map and feathering the pixel values along the preferred routes separating pixel values from different source images.
22. The one or more non-transitory computer readable medium of claim 13 , wherein the preferred routes are determined utilizing a ground confidence map.
23. The one or more non-transitory computer readable medium of claim 22 , wherein the ground confidence map is created in a method comprising the steps of:
selecting a plurality of geo-referenced, digital source images captured from different vantage points and cooperating to cover the geographic area, the source images having overlapping portions depicting a portion of the geographic area;
creating the ground confidence map of the geographic area, the ground confidence map having a plurality of pixels with each pixel corresponding to a particular geographic location;
assigning the pixels in the ground confidence map with pixel values indicative of composite ground confidence scores by:
calculating composite ground confidence scores for the pixel values of common geographic regions within the overlapping portions of the source images within a kernel corresponding to the particular geographic location of the pixels; and
storing pixel values indicative of the composite ground confidence score calculated for particular pixels, the pixel values indicative of a statistical probability that the geographical location represented by the particular pixels represent the ground.
24. The one or more non-transitory computer readable medium of claim 13 , wherein the preferred routes are determined utilizing street center line data.