Automated spatial indexing of images to video
A spatial indexing system receives a video that is a sequence of frames depicting an environment, such as a floor of a construction site, and performs a spatial indexing process to automatically identify the spatial locations at which each of the images were captured. The spatial indexing system also generates an immersive model of the environment and provides a visualization interface that allows a user to view each of the images at its corresponding location within the model.
1. A method comprising:
generating a three-dimensional rendering of an environment based at least in part on video captured by an image capture system as the image capture system moves through the environment;
modifying a displayed interface to include the three-dimensional rendering of the environment;
accessing one or more content annotations created within the environment at a set of locations within the environment; and
modifying the displayed interface to include the content annotations at locations within the three-dimensional rendering of the environment corresponding to the set of locations,
wherein a location of a content annotation is determined based on a mapping of an image timestamp captured by a system that created the content annotation to an image frame timestamp to which it is closest captured by the image capture system.
2. The method of claim 1 , wherein the content annotations comprise metadata describing one or more of the location at which the content annotation was created, a time at which the content annotation was created, an identity of a user that created the content annotation, and the system that created the content annotation.
3. The method of claim 2 , wherein the set of locations are determined based on locations described by the metadata.
4. The method of claim 1 , wherein the content annotations are created by a user that moves the image capture system through the environment.
5. The method of claim 1 , wherein the content annotations comprise text.
6. The method of claim 1 , wherein the content annotations comprise a comment associated with an image captured within the environment.
7. The method of claim 1 , wherein the content annotations comprise one or more of images, timestamps, camera orientation information, and metadata associated with the content annotations.
8. The method of claim 1 , wherein the three-dimensional rendering of the environment is aligned with a floorplan of the environment, and wherein the floorplan specifies positions of a plurality of physical features in the environment that are included within the three-dimensional rendering of the environment.
9. The method of claim 1 , wherein a content annotation is associated with a feature of the environment, and wherein the displayed interface is modified to include the content annotation when the feature of the environment is shown within the three-dimensional rendering of the environment.
10. The method of claim 1 , wherein the content annotations are generated from a plurality of users, and wherein the content annotations are displayed in a feed such that more than one content annotation is visible at once.
11. A system comprising:
a processor; and
a non-transitory computer readable storage medium comprising computer program instructions that when executed by the processor, cause the processor to:
generating a three-dimensional rendering of an environment based at least in part on video captured by an image capture system as the image capture system moves through the environment;
modifying a displayed interface to include the three-dimensional rendering of the environment;
accessing one or more content annotations created within the environment at a set of locations within the environment; and
modifying the displayed interface to include the content annotations at locations within the three-dimensional rendering of the environment corresponding to the set of locations,
wherein a location of a content annotation is determined based on a mapping of an image timestamp captured by a system that created the content annotation to an image frame timestamp to which it is closest captured by the image capture system.
12. The system of claim 11 , wherein the content annotations comprise metadata describing one or more of the location at which the content annotation was created, a time at which the content annotation was created, an identity of a user that created the content annotation, and the system that created the content annotation.
13. The system of claim 12 , wherein the set of locations are determined based on locations described by the metadata.
14. The system of claims 11 , wherein the content annotations are created by a user that moves the image capture system through the environment.
15. The system of claim 11 , wherein the content annotations comprise text.
16. The system of claim 11 , wherein the content annotations comprise a comment associated with an image captured within the environment.
17. The system of claim 11 , wherein the content annotations comprise one or more of images, timestamps, camera orientation information, and metadata associated with the content annotations.
18. The system of claim 11 , wherein the three-dimensional rendering of the environment is aligned with a floorplan of the environment, and wherein the floorplan specifies positions of a plurality of physical features in the environment that are included within the three-dimensional rendering of the environment.
19. The system of claim 11 , wherein a content annotation is associated with a feature of the environment, and wherein the displayed interface is modified to include the content annotation when the feature of the environment is shown within the three-dimensional rendering of the environment.
20. The system of claim 11 , wherein the content annotations are generated from a plurality of users, and wherein the content annotations are displayed in a feed such that more than one content annotation is visible at once.