Computer vision database platform for a three-dimensional mapping system
A method and related software are disclosed for processing imagery related to three dimensional models. To display new visual data for select portions of images, an image of a physical structure such as a building with a façade is retrieved with an associated three dimensional model for that physical structure according to common geolocation tags. A scaffolding of surfaces composing the three dimensional model is generated and regions of the retrieved image are registered to the surfaces of the scaffolding to create mapped surfaces for the image. New image data such as texture information is received and applied to select mapped surfaces to give the retrieved image the appearance of having the new texture data at the selected mapped surface.
1. A system for updating a building model texture, the system comprising:
an image acquisition module for receiving one or more images, the one or more images comprising pixels representing a surface of a building;
a memory; and
a processing module coupled to the image acquisition module and memory, the processing module capable of:
processing regions in each of the one of the one or more images to generate information associated with architectural features identified within the regions as metadata;
comparing at least one of the one or more images to one or more previously stored geospatial images, the comparing including an analysis of the generated metadata;
ranking the comparing based on the analysis of the generated metadata;
creating a pixel-to-pixel correlation between the one or more images and at least one of the one or more previously stored geospatial images based on the ranking;
storing pixel-to-pixel correlated images in a database with the generated metadata, wherein the generated metadata further comprises metadata indicating the ranking of the comparison with the one or more previously stored geospatial images; and
updating a texture for a building model related to the one or more previously stored geospatial images by retexturing at least one surface of the building model with a stored pixel-to-pixel correlated image.
2. The system of claim 1 , wherein the processing module updates the building model texture when the pixel-to-pixel correlation indicates differences between the stored pixel-to-pixel correlated image and one or more previously stored geospatial images.
3. The system of claim 1 , wherein processing regions of the one or more images further comprises establishing a total count of the identified architectural features in the one or more images.
4. The system of claim 1 , wherein processing regions of the one or more images further comprises establishing feature distribution of the identified architectural features in the one or more images.
5. The system of claim 1 , wherein processing regions of the one or more images further comprises detecting occlusions to the identified architectural features.
6. The system of claim 5 , wherein processing regions of the one or more images further comprises removing occlusions to the identified architectural features.
7. The system of claim 1 , wherein a match probability metric for ranking the comparison of the one or more images to the one or more previously stored geospatial images is based on a weighting criteria.
8. The system of claim 7 , wherein the match probability metric further comprises a received selection criteria.
9. The system of claim 8 , wherein the received selection criteria is used to adjust the weighting criteria for a future ranking.
10. The system of claim 8 , wherein the received selection criteria comprises lighting information of the one of the one or more images.
11. One or more non-transitory computer readable medium storing instructions that, when executed, cause a processor to execute operations comprising:
processing regions in each of one or more images comprising pixels representing one or more surfaces of a building, the processing to generate information associated with architectural features identified within the regions as metadata;
comparing at least one of the one or more images to one or more previously stored geospatial images, the comparing including an analysis of the generated metadata;
ranking the comparing based on the analysis of the metadata;
creating a pixel-to-pixel correlation between the one or more images and at least one of the one or more previously stored geospatial images based on the ranking;
storing pixel-to-pixel correlated images in a database with the generated metadata, wherein the generated metadata further comprises metadata indicating the ranking of the comparison with the one or more previously stored geospatial images; and
updating a texture for a building model related to the one or more previously stored geospatial images by retexturing at least one surface of the building model with a stored pixel-to-pixel correlated image.
12. The one or more non-transitory computer readable medium of claim 11 , wherein the updating the building model texture is responsive to detecting differences between the stored pixel-to-pixel correlated image and one of the one or more previously stored geospatial images.
13. The one or more non-transitory computer readable medium of claim 11 , wherein processing regions of the one or more images further comprises establishing a total count of the identified architectural features in the one or more images.
14. The one or more non-transitory computer readable medium of claim 11 , wherein processing regions of the one or more images further comprises establishing feature distribution of the identified architectural features in the one or more images.
15. The one or more non-transitory computer readable medium of claim 11 , wherein processing regions of the one or more images further comprises detecting occlusions to the identified architectural features.
16. The one or more non-transitory computer readable medium of claim 15 , wherein processing regions of the one or more images further comprises removing occlusions to the identified architectural features.
17. The one or more non-transitory computer readable medium of claim 11 , wherein a match probability metric for ranking the comparison of the one or more images to the one or more previously stored geospatial images is based on a weighting criteria.
18. The one or more non-transitory computer readable medium of claim 17 , wherein the match probability metric further comprises a selection criteria.
19. The one or more non-transitory computer readable medium of claim 18 , wherein the selection criteria is used to adjust the weighting criteria for a future ranking.
20. The one or more non-transitory computer readable medium of claim 18 , wherein the selection criteria comprises lighting information of the one or more images.