Automated guide for image capturing for 3D model creation
An image capture system provides automated prompts for aiding a user in capturing images for use in 3D model creation. While a user is preparing to capture an image, the system provides visual indications that indicate whether a quality-based condition is satisfied. Based on the visual indications, a user can determine whether an image, if captured, would likely be suitable for use in creating a 3D model. Determining if the quality-based condition is satisfied may include monitoring output generated by one or more sensors and comparing the output against a threshold value. Additionally, the system may analyze the visual content or metadata associated with an image to determine if the quality-based condition is satisfied and request user input to further identify certain image features that were identified by the system.
1. A method for capturing images used to create 3D models, the method comprising:
displaying, on a device, visual content comprising a target object that would be captured as an image if a capture control for the device were activated;
determining, by one or more processors, whether a quality-based condition is satisfied, wherein determining whether the quality-based condition is satisfied comprises determining, by one or more processors, whether the entirety of the target object is visible in the visual content, wherein determining whether the entirety of the target object is visible in the visual content comprises performing edge detection for the target object, wherein performing edge detection for the target object comprises:
determining a type of the target object;
identifying a set of edges associated with the type of the target object; and
determining whether all of the identified set of edges are visible in the visual content;
at least while the quality-based condition is not satisfied, displaying, on the device, a visual indication associated with the quality-based condition concurrent with displaying the visual content; and
capturing the visual content displayed on the device, as an image, in response to activation of the capture control.
2. The method of claim 1 , wherein:
the target object is a building;
the set of edges comprise one or more outer building edges; and
determining, by one or more processors, whether all of the identified set of edges are visible in the visual content comprises determining whether all of the one or more outer building edges are visible in the visual content.
3. The method of claim 1 , further comprising:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, ceasing to display the visual indication.
4. The method of claim 1 , further comprising:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, changing an appearance of the visual indication.
5. The method of claim 1 , wherein:
the target object is a building; and
determining, by one or more processors, whether the entirety of the target object is visible in the visual content comprises determining whether the visual content comprises one or more of: a corner of the building, a top of the building, or a bottom of the building.
6. The method of claim 1 , wherein the visual indication outlines a portion of the visual content.
7. The method of claim 6 , wherein the portion of the visual indication outlined is the target object.
8. A method for guiding image capture for 3D reconstruction processes, the method comprising:
displaying, on a device, visual content comprising a target object that would be captured within an image if a capture control for the device were activated;
determining, by one or more processors, whether a quality-based condition is satisfied, wherein determining whether the quality-based condition is satisfied comprises:
identifying a target object type;
detecting at least one line associated with the target object type; and
determining whether all of the at least one line is visible in the visual content;
at least while the quality-based condition is not satisfied, displaying, on the device, a visual indication associated with the quality-based condition concurrent with displaying the visual content; and
capturing the visual content displayed on the device, as an image, in response to activation of the capture control.
9. The method of claim 8 , further comprising:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, ceasing to display the visual indication.
10. The method of claim 8 , further comprising:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, changing an appearance of the visual indication.
11. The method of claim 8 , wherein:
the target object type is a building; and
determining, by one or more processors, whether the at least one detected line associated with the target object type comprises one or more of: a post of the building, a ridgeline of the building, or a roofline of the building.
12. The method of claim 8 , wherein the at least one detected line forms an outline of the target object displayed on the device.
13. The method of claim 12 , wherein the outline is disposed entirely within an image frame comprising the visual content.
14. One or more non-transitory computer-readable media storing one or more sequences of instructions that, when executed by one or more processors, cause:
displaying, on a device, visual content comprising a target object that would be captured as an image if a capture control for the device were activated;
determining, by one or more processors, whether a quality-based condition is satisfied, wherein determining whether the quality-based condition is satisfied comprises determining, by one or more processors, whether the entirety of the target object is visible in the visual content, wherein determining whether the entirety of the target object is visible in the visual content comprises performing edge detection for the target object, wherein performing edge detection for the target object comprises:
determining a type of the target object;
identifying a set of edges associated with the type of the target object; and
determining whether all of the identified set of edges are visible in the visual content;
at least while the quality-based condition is not satisfied, displaying, on the device, a visual indication associated with the quality-based condition concurrent with displaying the visual content; and
capturing the visual content displayed on the device, as an image, in response to activation of the capture control.
15. The one or more non-transitory computer-readable media of claim 14 , wherein:
the target object is a building;
the set of edges comprise one or more outer building edges; and
determining, by one or more processors, whether all of the identified set of edges are visible in the visual content comprises determining whether all of the one or more outer building edges are visible in the visual content.
16. The one or more non-transitory computer-readable media of claim 14 , further comprising one or more sequences of instructions that when, executed by one or more processors, cause:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, ceasing to display the visual indication.
17. The one or more non-transitory computer-readable media of claim 14 , further comprising one or more sequences of instructions that when, executed by one or more processors, cause:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, changing an appearance of the visual indication.
18. The one or more non-transitory computer-readable media of claim 14 , wherein:
the target object is a building; and
determining, by one or more processors, whether the entirety of the target object is visible in the visual content comprises determining whether the visual content comprises one or more of: a corner of the building, a top of the building, or a bottom of the building.
19. The one or more non-transitory computer-readable media of claim 14 , wherein the visual indication outlines a portion of the visual content.
20. The one or more non-transitory computer-readable media of claim 19 , wherein the portion of the visual indication outlined is the target object.
21. One or more non-transitory computer-readable media storing one or more sequences of instructions that, when executed by one or more processors, cause:
displaying, on a device, visual content comprising a target object that would be captured within an image if a capture control for the device were activated;
determining, by one or more processors, whether a quality-based condition is satisfied, wherein determining whether the quality-based condition is satisfied comprises:
identifying a target object type;
detecting at least one line associated with the target object type; and
determining whether all of the at least one line is visible in the visual content;
at least while the quality-based condition is not satisfied, displaying, on the device, a visual indication associated with the quality-based condition concurrent with displaying the visual content; and
capturing the visual content displayed on the device, as an image, in response to activation of the capture control.
22. The one or more non-transitory computer-readable media of claim 21 , further comprising one or more sequences of instructions that when, executed by one or more processors, cause:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, ceasing to display the visual indication.
23. The one or more non-transitory computer-readable media of claim 21 , further comprising one or more sequences of instructions that when, executed by one or more processors, cause:
detecting that the quality-based condition is satisfied; and
in response to detecting that the quality-based condition is satisfied, changing an appearance of the visual indication.
24. The one or more non-transitory computer-readable media of claim 21 , wherein:
the target object type is a building; and
determining, by one or more processors, whether the at least one detected line associated with the target object type comprises one or more of: a post of the building, a ridgeline of the building, or a roofline of the building.
25. The one or more non-transitory computer-readable media of claim 21 , wherein the at least one detected line forms an outline of the target object displayed on the device.
26. The one or more non-transitory computer-readable media of claim 25 , wherein the outline is disposed entirely within an image frame comprising the visual content.