Method and apparatus for roof type classification and reconstruction based on two dimensional aerial images

1. A method comprising:

receiving a roof image;

determining if roof features satisfy a predetermined edge threshold, wherein in an instance in which the roof image does not satisfy the predetermined edge threshold a mean shift is applied to the roof image;

determining, using a processor, a segmentation of the roof image based on cutting lines associated with the roof features; and

classifying roof segments based on the roof features within the roof segment, wherein the classifying of the roof segments is based on the roof features correlation to a roof type pattern.

2. The method of claim 1 further comprising:

determining a plurality of points of interest associated with the roof image; and

wherein the cutting lines are candidate cutting lines that are based on the points of interest.

3. The method of claim 2 , wherein the roof image comprises a roof footprint; and

wherein determining a point of interest comprises determining points at which the angle of the footprint satisfies a predetermined angle threshold.

4. The method of claim 1 further comprising:

classifying the roof based on the roof segment classification.

5. The method of claim 1 further comprising:

determining if at least a portion of the roof image satisfies a predetermined scale threshold, wherein in an instance in which the at least a portion of the roof image does not satisfy the predetermined scale threshold the roof image is adjusted to satisfy the predetermined scale threshold.

6. A method comprising:

receiving a roof image;

determining a plurality of points of interest associated with the roof image;

determining candidate cutting lines based on the points of interest;

determining, using a processor, a segmentation of the roof image based on the candidate cutting lines associated with roof features, wherein determining a segmentation of the roof image comprises determining a plurality of segment combinations based on the candidate cutting lines and points of interest;

selecting a segment combination based on satisfying a predetermined probability threshold; and

classifying roof segments based on roof features within the roof segment, wherein the classifying of the roof segments is based on the roof features correlation to a roof type pattern.

7. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the processor, cause the apparatus to at least:

receive a roof image;

determine if roof features satisfy a predetermined edge threshold, wherein in an instance in which the roof image does not satisfy the predetermined edge threshold a mean shift is applied to the roof image;

determine a segmentation of the roof image based on cutting lines associated with the roof features; and

classify roof segments based on the roof features within the roof segment, wherein the classifying of the roof segments is based on the roof features correlation to a roof type pattern.

8. The apparatus of claim 7 , wherein the at least one memory and the computer program code are further configured to:

determine a plurality of points of interest associated with the roof image; and

wherein the cutting lines are candidate cutting lines that are based on the points of interest.

9. The apparatus of claim 8 , wherein the roof image comprises a roof footprint; and

wherein determining a point of interest comprises determining points at which the angle of the footprint satisfies a predetermined angle threshold.

10. The apparatus of claim 8 , wherein the at least one memory and the computer program code are further configured to:

determine candidate cutting lines based on the points of interest;

wherein determining a segmentation of the roof image comprises determining a plurality of segment combinations based on the candidate cutting lines and points of interest; and

select a segment combination based on satisfying a predetermined probability threshold.

11. The apparatus of claim 7 , wherein the at least one memory and the computer program code are further configured to:

classify the roof based on the roof segment classification.

12. The apparatus of claim 7 , wherein the at least one memory and the computer program code are further configured to:

determine if at least a portion of the roof image satisfies a predetermined scale threshold, wherein in an instance in which the at least a portion of the roof image does not satisfy the predetermined scale threshold the roof image is adjusted to satisfy the predetermined scale threshold.

13. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions configured to:

receive a roof image;

determine if roof features satisfy a predetermined edge threshold, wherein in an instance in which the roof image does not satisfy the predetermined edge threshold a mean shift is applied to the roof image;

determine a segmentation of the roof image based on cutting lines associated with roof features; and

classify roof segments based on the roof features within the roof segment, wherein the classifying of the roof segments is based on the roof features correlation to a roof type pattern.

14. The computer program product of claim 13 , wherein the computer-executable program code portions further comprise program code instructions configured to:

determine a plurality of points of interest associated with the roof image; and

wherein the cutting lines are candidate cutting lines that are based on the points of interest.

15. The computer program product of claim 13 , wherein the roof image comprises a roof footprint; and

wherein determining a point of interest comprises determining points at which the angle of the footprint satisfies a predetermined angle threshold.

16. The computer program product of claim 13 , wherein the computer-executable program code portions further comprise program code instructions configured to:

determine candidate cutting lines based on the points of interest;

wherein determining a segmentation of the roof image comprises determining a plurality of segment combinations based on the candidate cutting lines and points of interest; and

select a segment combination based on satisfying a predetermined probability threshold.

17. The computer program product of claim 13 , wherein the computer-executable program code portions further comprise program code instructions configured to:

classify the roof based on the roof segment classification.

18. The computer program product of claim 13 , wherein the computer-executable program code portions further comprise program code instructions configured to:

determine if at least a portion of the roof image satisfies a predetermined scale threshold, wherein in an instance in which the at least a portion of the roof image does not satisfy the predetermined scale threshold the roof image is adjusted to satisfy the predetermined scale threshold.