Method for generating reproducible perspectives of photographs of an object, and mobile device with an integrated camera
A first 2D recording of a specified reference view of an object is captured by a camera and, starting from the first 2D recording, a user's starting location relative to the object is ascertained by a computer vision module. Starting from the origin of a coordinate system as the starting location of the camera, one or more specified and/or settable relative positions in the vicinity of the object and/or in the object are determined as one or more locations for the respective perspective of the camera for taking at least one second 2D recording. The respective location in an object view on a display of the camera is displayed by a respective first augmented reality marker on the ground and/or on the object. The alignment of the camera with regard to angle and rotation with the perspective corresponding to the respective location is performed in this case by second augmented reality markers as auxiliary elements.
1. A method for generating reproducible perspectives of photographs of an object, comprising:
capturing a first 2D recording of a specified reference view of the object by a camera;
ascertaining a starting location from the first 2D recording by a computer vision module;
determining, by starting from the starting location, at least one position, specified and/or settable relative to the object for a respective perspective of the camera for at least one second 2D recording of the object;
displaying a respective location on a display of the camera by a first augmented reality marker on at least one of ground and the object; and
displaying, when a user is positioned at the respective location, at least one of
at least one auxiliary element of at least one second augmented reality marker on the display of the camera for aligning the camera with at least one of the reproducible perspectives, the at least one auxiliary element indicating when the at least one of the reproducible perspectives is achieved, and
at least one of cut-out images and compositions generated from the object by a 3D model of the object on an exterior of the object by overlaying a mask, including calculating a shadow from the 3D model that is inserted into the at least one second 2D recording.
2. The method as claimed in claim 1 , wherein the computer vision module recognizes a reference object on the object in the reference view and from a contour of the reference object ascertains the starting location relative to the object.
3. The method as claimed in claim 2 , wherein at least one of an acceleration sensor and a gyro sensor in the camera ascertains a current relative position and orientation relative to the starting location.
4. The method as claimed in claim 3 , wherein the object is a motor vehicle.
5. The method as claimed in claim 4 , wherein the reference object is a license plate of the motor vehicle.
6. The method as claimed in claim 5 , wherein dimensions of the object are taken into account when determining the at least one position for the respective perspective of the camera, whereby the method is applicable to different objects.
7. The method as claimed in claim 6 , further comprising, when the camera reaches the respective perspective, automatically capturing the at least one second 2D recording by the camera.
8. The method as claimed in claim 7 , wherein the reproducible perspectives include exterior perspectives of the object and interior perspectives of the object.
9. The method as claimed in claim 8 , further comprising:
receiving a user selection pertaining to the 3D model; and
retrieving the 3D model from at least one of a local memory and a server according to the user selection.
10. The method as claimed in claim 9 , wherein the at least one second 2D recording of the object is modified by at least one of overlays and cut-outs.
11. The method as claimed in claim 2 , wherein the reference object is a license plate of the motor vehicle.
12. The method as claimed in claim 1 , wherein the object is a motor vehicle.
13. The method as claimed in claim 1 , wherein dimensions of the object are taken into account when determining the at least one position for the respective perspective of the camera, whereby the method is applicable to different objects.
14. The method as claimed in claim 1 , further comprising, when the camera reaches the respective perspective, automatically capturing the at least one second 2D recording by the camera.
15. The method as claimed in claim 1 , wherein the reproducible perspectives include exterior perspectives of the object and interior perspectives of the object.
16. The method as claimed in claim 1 , further comprising:
receiving a user selection pertaining to the 3D model; and
retrieving the 3D model from at least one of a local memory and a server according to the user selection.
17. The method as claimed in claim 1 , wherein the at least one second 2D recording of the object is modified by at least one of overlays and cut-outs.
18. A camera, comprising:
a display; and
a processor, configured to
capture a first 2D recording of a specified reference view of an object;
ascertain a starting location from the first 2D recording by a computer vision module;
determine, by starting from the starting location, at least one position, specified and/or settable relative to the object for a respective perspective of the camera for at least one second 2D recording of the object;
display a respective location on a display of the camera by a first augmented reality marker on at least one of ground and the object; and
display, when a user is positioned at the respective location, at least one of
at least one auxiliary element of at least one second augmented reality marker on the display of the camera for aligning the camera with at least one of the reproducible perspectives, the at least one auxiliary element indicating when the at least one of the reproducible perspectives is achieved, and
at least one of cut-out images and compositions generated from the object by a 3D model of the object on an exterior of the object by overlaying a mask, including calculating a shadow from the 3D model that is inserted into the at least one second 2D recording.
19. The camera as claimed in claim 18 , wherein the computer vision module recognizes a reference object on the object in the reference view and from a contour of the reference object ascertains the starting location relative to the object.
20. The camera as claimed in claim 18 , wherein the reproducible perspectives include exterior perspectives of the object and interior perspectives of the object.