Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019008185) A METHOD AND SYSTEM FOR NODE VECTORISATION
Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

Claims

1 . A method for vectorising nodes within a plurality of 360 degree images, including:

a) identifying a set of points of interest within a first 360 degree image of the plurality of 360 degree images;

b) identifying a corresponding set of points of interest within a second 360 degree image of the plurality of 360 degree images; and c) calculating 3D coordinates of the points of interest using triangulation of both sets of points of interest.

2. A method as claimed in claim 1 , wherein the set of points of interest are identified within the first 360 degree image based upon at least one visual characteristic exceeding a threshold.

3. A method as claimed in claim 2, wherein the visual characteristic is contrast.

4. A method as claimed in any one of claims 2 to 3, wherein the visual characteristic relates to a group of pixels proximate to each point of interest in the 360 degree image.

5. A method as claimed in any one of the preceding claims, wherein the second 360 degree image is vertically aligned to the first 360 degree image prior to identification of the corresponding set of points of interest.

6. A method as claimed in any one of the preceding claims, further including the step of generating features for the set of points of interest.

7. A method as claimed in claim 6, wherein the corresponding set of points of interest is identified utilizing the features for the set of points of interest.

8. A method as claimed in any one of the preceding claims, wherein the plurality of 360 degree images are a sequence of 360 degree images.

9. A method as claimed in claim 8, wherein the sequence of 360 degree images are captured using a 360 degree camera.

10. A method as claimed in claim 9, wherein the 360 degree camera is a video camera.

1 1 . A method as claimed in any one of claims claim 8 to 10, wherein the sequence of 360 degree images differ in distance from one another.

12. A method as claimed in any one of the preceding claims, wherein each of the plurality of 360 degree images is associated with a location.

13. A method as claimed in claim 12, wherein the location of the first and second 360 degree images differs.

14. A method as claimed in any one of the preceding claims, when dependent on claim 8, further including the step of selecting the second

360 degree image based upon the next 360 degree image within the sequence with a location that differs from the first 360 degree image beyond a minimum threshold.

15. A method as claimed in any one of the preceding claims, further including the step of generating a 3D mesh using the 3D coordinates.

16. A method as claimed in any one of the preceding claims, further including mapping each of the 3D coordinates to an existing 3D mesh of the same real world location.

17. A system for vectorising nodes within a plurality of 360 degree images, including:

One or more processors configured for identifying a set of points of interest within a first 360 degree image of the plurality of 360 degree images; identifying a corresponding set of points of interest within a second 360 degree image of the plurality of 360 degree images; and calculating the 3D coordinates of the points of interest using triangulation of both sets of points of interest; and

A memory configured for storing a plurality of 360 degree images and 3D coordinates for each of the points of interest.

A computer program configured for performing the method of any one of claims 1 to 16.

A computer readable medium configured for storing the computer program of claim 18.