Method and system for location detection of photographs using topographic techniques
A computer implemented method and system for identifying locations in photographs using topographic techniques is disclosed. The method comprises receiving an image; in response to receiving the image, generating a depth map of the image; removing non-geographic features from the depth map; generating a topographic map based on the depth map; modifying the topographic map to represent each pixel by height differential; and comparing the modified topographic map to a modified global topographic map to determine a location of the image.
1. A computer implemented method for identifying locations in photographs using topographic techniques, comprising:
receiving an image taken from a single perspective;
in response to receiving the image, generating a depth map of the image;
removing non-geographic features from the depth map;
generating a topographic map based on the depth map;
modifying the topographic map to represent each pixel by height differential; and
comparing the modified topographic map to a modified global topographic map to determine a location of the image.
2. The method of claim 1 , wherein the image is an outdoor scene wherein the location of the image is unknown.
3. The method of claim 1 , wherein the depth map identifies for each pixels of the image, a height and distance from a camera lens of a camera that captures the image.
4. The method of claim 1 , wherein non-geographic features are identified as small groups of pixels at a same height and distance on the depth map.
5. The method of claim 1 , wherein generating the topographic map based on the depth map comprises:
rotating the depth map 90 degrees to view the depth map from a sky view perspective;
identifying gaps in height and distance information from the depth map; and
filling in missing height and distance information using heights and distances already known for the image.
6. The method of claim 1 , further comprising modifying the global topographic map to represent each pixel by height differential.
7. The method of claim 1 , further comprising storing the location of the image as the location on the modified global topographic map that matches the modified topographic map of the image.
8. A system for identifying locations in photographs using topographic techniques, comprising:
a) at least one processor;
b) at least one input device; and
at least one storage device storing processor-executable instructions which, when executed by the at least one processor, perform a method including:
receiving an image taken from a single perspective;
in response to receiving the image, generating a depth map of the image;
removing non-geographic features from the depth map;
generating a topographic map based on the depth map;
modifying the topographic map to represent each pixel by height differential; and
comparing the modified topographic map to a modified global topographic map to determine a location of the image.
9. The system of claim 8 , wherein the image is an outdoor scene wherein the location of the image is unknown.
10. The system of claim 8 , wherein the depth map identifies for each pixels of the image, a height and distance from a camera lens of a camera that captures the image.
11. The system of claim 8 , wherein non-geographic features are identified as small groups of pixels at a same height and distance on the depth map.
12. The system of claim 8 , wherein generating the topographic map based on the depth map comprises:
rotating the depth map 90 degrees to view the depth map from a sky view perspective;
identifying gaps in height and distance information from the depth map; and
filling in missing height and distance information using heights and distances already known for the image.
13. The system of claim 8 , further comprising modifying the global topographic map to represent each pixel by height differential.
14. The system of claim 8 , further comprising storing the location of the image as the location on the modified global topographic map that matches the modified topographic map of the image.
15. A non-transitory computer readable medium for storing computer instructions that, when executed by at least one processor causes the at least one processor to perform a method for identifying locations in photographs using topographic techniques, comprising:
receiving an image taken from a single perspective;
in response to receiving the image, generating a depth map of the image;
removing non-geographic features from the depth map;
generating a topographic map based on the depth map;
modifying the topographic map to represent each pixel by height differential; and
comparing the modified topographic map to a modified global topographic map to determine a location of the image.
16. The non-transitory computer readable medium of claim 15 , wherein the image is an outdoor scene wherein the location of the image is unknown.
17. The non-transitory computer readable medium of claim 15 , wherein the depth map identifies for each pixels of the image, a height and distance from a camera lens of a camera that captures the image.
18. The non-transitory computer readable medium of claim 15 , wherein non-geographic features are identified as small groups of pixels at a same height and distance on the depth map.
19. The non-transitory computer readable medium of claim 15 , wherein generating the topographic map based on the depth map comprises:
rotating the depth map 90 degrees to view the depth map from a sky view perspective;
identifying gaps in height and distance information from the depth map; and
filling in missing height and distance information using heights and distances already known for the image.
20. The non-transitory computer readable medium of claim 15 , further comprising modifying the global topographic map to represent each pixel by height differential.