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 system for capturing images used to create 3D models, the system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions which, when executed by the one or more processors, cause the processors to:
receive an image frame for quality analysis;
generate, based on the image frame, a bounding box for a feature of a building object;
determine whether a quality-based condition for the image frame is satisfied, the quality-based condition indicating that an entirety of the bounding box is disposed within the image frame; and
provide one or more visual indications associated with the image frame based on a status of the quality-based condition.
2. The system of claim 1 , wherein the building object comprises at least one of a door, a window, or a roof.
3. The system of claim 1 , wherein the feature comprises at least one of a roof facet, a roof line, or a gable.
4. The system of claim 1 , wherein the feature comprises a corner of the building object.
5. The system of claim 1 , wherein the image frame is captured by a device.
6. The system of claim 5 , wherein the instructions, when executed by the one or more processors, further cause the processors to:
determine whether a different quality-based condition for the image frame is satisfied, the different quality-based condition indicating an angle of tilt associated with the device is within a particular range.
7. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the processors to:
determine whether a different quality-based condition for the image frame is satisfied, the different quality-based condition indicating that a brightness and a contrast of the image frame are sufficient to detect features.
8. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the processors to:
determine whether a different quality-based condition for the image frame is satisfied, the different quality-based condition indicating whether all expected edges of the feature are visible in the image frame.
9. The system of claim 1 , wherein the building object is an object that forms at least part of a building.
10. A method for capturing images used to create 3D models, the method being implemented by a system of one or more processors, and the method comprising:
receiving an image frame for quality analysis;
identifying, based on the image frame, a feature of a building object;
determining whether a quality-based condition for the image frame is satisfied, the quality-based condition indicating that an entirety of the feature disposed within the image frame;
determining whether a different quality-based condition is satisfied, wherein determining whether the different quality-based condition is satisfied comprises determining at least one of:
whether an angle of tilt associated with a device that captured the image frame is within a particular range,
whether a brightness and a contrast of the image frame are sufficient to detect features, or
whether all expected edges of the feature are visible in the image frame; and
providing one or more visual indications associated with the image frame based on a status of the quality-based condition.
11. The method of claim 10 , wherein the building object comprises at least one of a door, a window, or a roof.
12. The method of claim 10 , wherein the feature comprises at least one of a roof facet, a roof line, or a gable.
13. The method of claim 10 , wherein the feature comprises a corner of the building object.
14. The method of claim 10 , the method further comprising:
generating a bounding box around the feature;
wherein determining whether the quality-based condition for the image frame is satisfied comprises determining whether an entirety of the bounding box is within the image frame.
15. The method of claim 10 , wherein determining whether the different quality-based condition is satisfied comprises:
determining whether the angle of tilt associated with the device is within the particular range.
16. The method of claim 10 , wherein determining whether the different quality-based condition is satisfied comprises:
determining whether the brightness and the contrast of the image frame are sufficient to detect features.
17. The method of claim 10 , wherein determining whether the different quality-based condition is satisfied comprises:
determining whether all expected edges of the feature are visible in the image frame.
18. The method of claim 10 , wherein the building object is an object that forms at least part of a building.
19. One or more non-transitory computer-readable media storing one or more sequences of instructions that, when executed by one or more processors, cause the processors to:
receive an image frame for quality analysis;
identify, based on the image frame, a feature of a building object;
determine whether a quality-based condition for the image frame is satisfied, the quality-based condition indicating that an entirety of the feature disposed within the image frame;
determine whether a different quality-based condition is satisfied, wherein to determine whether the different quality-based condition is satisfied the instructions cause the processors to determine at least one of:
whether an angle of tilt associated with a device that captured the image frame is within a particular range,
whether a brightness and a contrast of the image frame are sufficient to detect features, or
whether all expected edges of the feature are visible in the image frame; and
provide one or more visual indications associated with the image frame based on a status of the quality-based condition.
20. The one or more non-transitory computer-readable media of claim 19 , wherein to determine whether the different quality-based condition is satisfied, the instructions cause the processors to:
determine whether a brightness and a contrast of the image frame are sufficient to detect features.
21. The one or more non-transitory computer-readable media of claim 19 , wherein the building object is an object that forms at least part of a building.