Multi view camera registration
A system for registering one or more cameras and/or creating an accurate three-dimensional (3D) model of a world space environment including back projecting at least one image from at least one of a plurality of camera views to the 3D model based on a set of existing camera parameters. The back projected image is added as a texture for the 3D model. This texture is automatically compared to one or more images from other camera views using a color space comparison of images to determine a set of differences or errors. The camera parameters and the 3D model are automatically adjusted to minimized the differences or errors. Over time, the parameters and the 3D model converge on a state that can be used to track moving objects, insert virtual graphics and/or perform other functions.
1. A method for creating a model of a world space, comprising:
back projecting at least one image from at least one camera view to a model of a world space environment;
comparing the at least one back projected image to at least one image from at least one other camera view to determine a set of error metrics by transforming the model of the world space environment to a transformed image for a first camera and comparing the transformed image to an image captured by the first camera; and
aggregating the set of error metrics into a combined differences value and comparing the combined differences value to a threshold value.
2. The method of claim 1 , wherein the back projecting the at least one image from the at least one camera view to the model of the world space environment is based on at least one camera parameter.
3. The method of claim 1 , further comprising repeating the back projecting the at least one image from the at least one camera view to the model of the world space environment and the comparing the at least one back projected image to the at least one image from the at least one other camera view until the combined differences value is less than the threshold value.
4. The method of claim 1 , wherein the comparing the at least one back projected image to at least one image from at least one other camera view comprises comparing color values of the at least one back projected image and the at least one image from the at least one other camera view.
5. The method of claim 1 , wherein the back projecting the at least one image from the at least one camera view to the model of the world space environment includes back projecting images from the at least one camera view to one or more instances of the model of the world space environment to create textures for the model of the world space environment.
6. The method of claim 1 , wherein comparing the at least one back projected image to the at least one image from the at least one other camera view includes using a color space comparison between the at least one back projected image and the at least one image from the at least one other camera view.
7. The method of claim 1 , further comprising adding an additional image from the at least one camera view to the model of the world space environment, comparing the additional image to an image from the at least one other camera view, and adjusting at least one camera parameter and the model of the world space environment to minimize one or more differences between the additional image and the image from the at least one other camera view.
8. The method of claim 1 , further comprising tracking a moving object and/or inserting an image into video from the at least one camera view or the at least one other camera view.
9. The method of claim 1 , further comprising adding an additional detail to the model of the world space environment based on the comparison of the at least one back projected image to the at least one image from the at least one other camera view.
10. An apparatus for creating a model of a world space, comprising:
one or more processors; and
one or more non-transitory, tangible computer readable storage media connected to the one or more processors;
wherein the one or more processors are configured to add an image from at least one camera view to a model of an environment based on at least one camera parameter, compare the added image to an image from a different camera view, and adjust the at least one camera parameter and the model of the environment to minimize one or more differences between the added image and the image from the different camera view based on a set of error metrics determined by transforming the model of the environment to a transformed image for a first camera and comparing the transformed image to an image captured by the first camera; and
wherein the one or more processors are operable to aggregate the set of error metrics into a combined differences value and compare the combined differences value to a threshold value.
11. The apparatus of claim 10 , wherein the one or more processors are configured to compare the added image to the image from the different camera view based on a color space comparison which determines the one or more differences between the added image and the image from the different camera view.
12. The apparatus of claim 10 , wherein the one or more processors are configured to add the image by back projecting the image from the at least one camera view to the model of the environment.
13. The apparatus of claim 10 , wherein the one or more processors are configured to repeat the adding the image from the at least one camera view to the model of the environment and the comparing the added image to the image from the different camera view until the combined differences value is less than the threshold value; wherein the one or more processors are further configured to utilize the comparison to add an additional detail to the model of the environment.
14. The apparatus of claim 10 , wherein the one or more processors are configured to add a new feature to the model of the environment, compare the added image to the image from the different camera view based on the new feature added to the model of the environment, and adjust the at least one camera parameter and the model of the environment to minimize the one or more differences based on the new feature added to the model of the environment.
15. The apparatus of claim 10 , wherein the model of the environment includes a model of a world space environment.
16. The apparatus of claim 10 , wherein the one or more processors are configured to aggregate a set of error metrics derived by comparing the added image to the image from the different camera view into a combined differences value and compare the combined differences value to a threshold value.
17. An apparatus for creating a model of a world space, comprising:
one or more processors; and
one or more non-transitory, tangible computer readable storage media connected to the one or more processors;
wherein the one or more processors are configured to add an image from at least one camera view to a model of an environment based on at least one camera parameter, compare the added image to an image from a different camera view to determine a set of error metrics, adjust the at least one camera parameter and the model of the environment to minimize one or more differences between the added image and the image from the different camera view, and utilize the comparison to add an additional detail to the model of the environment and minimize the set of error metrics; and
wherein the one or more processors are operable to aggregate the set of error metrics into a combined differences value and compare the combined differences value to a threshold value.
18. The apparatus of claim 17 , wherein the one or more processors are configured to compare the added image to the image from the different camera view using a color space comparison to determine the one or more differences between the added image and the image from the different camera view.
19. The apparatus of claim 17 , wherein the one or more processors are configured to add the image from the at least one camera view to the model of the environment based on the at least one camera parameter by adding the image to the model of the environment as a texture for the model of the environment.
20. The apparatus of claim 17 , wherein the model of the environment includes a world model of the environment.