Method for augmenting a first image with image data from a second image

1. A computer implemented method for augmenting a first image with image data from a second image, the method comprising:

receiving the first image depicting a first scene;

capturing the second image depicting a second scene using an image capturing device;

identifying an object in the second image;

receiving a 3D model from a database, the database comprising a plurality of 3D models, the 3D model corresponding to the identified object of the second image;

aligning the 3D model with the identified object in the second image;

extracting pixel data from the second image using a contour of the 3D model's projection onto the second image; and

inserting the extracted pixel data of the second image data into the first image, thereby rendering an augmented image.

2. The method according to claim 1 , further comprising:

determining a first 3D coordinate space of the first image;

determining a second 3D coordinate space of the second image;

determining an object coordinate for the identified object in the second image using the second 3D coordinate space, and

wherein inserting the extracted pixel data of the second image data into the first image comprises inserting the extracted pixel data, at a position coordinate in the first image corresponding to the object coordinate.

3. The method according to claim 2 further comprising adjusting the position of the extracted pixel data in the augmented image by:

zooming in or out, or translating the first image, thereby manipulating the first 3D coordinate space of the first image; and

adjusting the position of the extracted pixel data in the augmented image to correspond to the object coordinate in the manipulated 3D coordinate space of the first image.

4. The method according to claim 2 , further comprising:

for the 3D model, defining a first value for a scale parameter, a first value for a translation parameter, and a first value for a rotation parameter;

for the identified object in the second image, defining a second value for a scale parameter, a second value for a translation parameter, and a second value for a rotation parameter; and

aligning the 3D model to the determined 3D coordinate space of the second image by manipulating one or more of the first scale parameter, the first translation parameter and the first rotational parameter of the 3D model, such that the first scale parameter corresponds to the second scale parameter, and the first translation parameter corresponds to the second translation parameter, and the first rotation parameter corresponds to the second rotation parameter.

5. The method according to claim 1 , further comprising:

requesting an input from a user; and

receiving an input from the user, and wherein the step of receiving the 3D model comprises sending data pertaining to the received input to the database.

6. The method according to claim 1 , further comprising:

identifying one or more objects in the first image; and

removing at least one of the one or more identified objects in the first image or manipulating at least one of the one or more identified objects by changing a position of at least one of the one or more identified objects in the first image.

7. The method according to claim 1 , further comprising:

removing the inserted pixel data from the augmented image;

capturing a third image of the second scene using the image capturing device;

re-identifying the previously identified object of the second image in the third image;

calculating a third 3D coordinate space for the third image;

aligning the 3D model with the identified object in third image;

extracting pixel data from the third image ( 202 ) of a contour of the 3D model projection onto the third image;

determining a second object coordinate for the identified object in the third image using the third 3D coordinate space; and

inserting the extracted pixel data of the third image data into the first image at a position coordinate in the first image corresponding to the second object coordinate.

8. The method according to claim 1 , wherein the step of identifying the object in the second image comprises determining an object type using an image search algorithm.

9. The method according to claim 1 , wherein the step of identifying the object in the second image comprises scanning a QR code on the object to be identified in the second scene.

10. The method according to claim 1 , wherein the step of identifying the object in the second image comprises reading a beacon signal transmitted by the object to be identified in the second scene.

11. The method according to claim 1 , wherein the step of receiving the 3D model comprises sending image data pertaining to the identified object to the database.

12. The method according to claim 1 , wherein the step of capturing a second image comprises using AR or VR equipment, and wherein the method further comprises displaying the augmented image using said AR or VR equipment.

13. The method according to claim 1 , further comprising storing the augmented image in a memory.

14. A device configured to augment a first image with image data from a second image, the device comprising circuitry configured to perform the method of claim 1 .

15. A non-transitory computer-readable storage medium having stored thereon instructions which, when executed by a device having processing capabilities, cause the device to:

receive the first image depicting a first scene;

capture the second image depicting a second scene using an image capturing device;

identify an object in the second image;

receive a 3D model from a database, the database comprising a plurality of 3D models, the 3D model corresponding to the identified object of the second image;

align the 3D model with the identified object in the second image;

extract pixel data from the second image using a contour of the 3D model's projection onto the second image; and

insert the extracted pixel data of the second image data into the first image, thereby rendering an augmented image.