System and method for construction estimation using aerial images
A system and method for construction estimation using aerial images is provided. The system receives at least one aerial image of a building. An estimation engine processes the aerial image at a plurality of angles to automatically identify a plurality (e.g., perimeter and interior) lines in the image corresponding to a plurality of features of a roof the building. The estimation engine allows users to generate two-dimensional and three-dimensional models of the roof by automatically delineating various roof features, and generates a report including information about the roof of the building.
1. A system for construction estimation, comprising:
a memory for storing at least one aerial image of a building; and
a processor in communication with the memory, the processor:
receiving, from the memory, the at least one aerial image;
processing the at least one aerial image to automatically identify a plurality of perimeter lines and interior lines in the at least one aerial image corresponding to one or more features of a roof of the building;
constructing a two-dimensional wireframe model of the roof based on the identified plurality of perimeter lines and interior lines; and
automatically generating a three-dimensional wireframe model of the roof of the building based on the constructed two-dimensional wireframe model,
wherein the processor processes the at least one aerial image by applying at least one filter to the at least one aerial image to compute a likelihood for each point in the at least one aerial image indicating whether the point represents a roof line; scanning the at least one aerial image at a first angle to obtain first image intensity data; rotating the at least one aerial image to a second angle different from the first angle; scanning the at least one aerial image at the second angle to obtain second image intensity data; and processing the first and second image intensity data to automatically identify the plurality of perimeter and interior lines in the at least one aerial image corresponding to the one or more features of the roof of the building.
2. The system of claim 1 , further comprising a graphical user interface for displaying the at least one aerial image of the building.
3. The system of claim 1 , wherein the plurality of interior lines in the at least one aerial image correspond to one or more of an eave, a hip, a ridge, a valley and an interior intersection of the roof of the building.
4. The system of claim 1 , wherein the processor generates a report comprising construction information associated with the generated three-dimensional wireframe model of the roof, the construction information being indicative of one or more of roof dimensions, pitches, surfaces, areas, and material costs associated with the roof.
5. The system of claim 1 , wherein the processor crops the at least one aerial image around the building.
6. The system of claim 1 , wherein the processor
crops the at least one aerial image around the building, and
automatically aligns the at least one aerial image based on the identified plurality of perimeter lines in the at least one aerial image corresponding to a perimeter of the roof of the building, the identified plurality of perimeter lines forming one of a closed polygon and a bounded area.
7. The system of claim 2 , wherein the processor allows a user to adjust one or more of the automatically identified plurality of perimeter and interior lines via the graphical user interface.
8. A method for construction estimation, comprising the steps of:
receiving, by a processor, at least one aerial image of a building;
processing the at least one aerial image to automatically identify a plurality of perimeter lines and interior lines in the at least one aerial image corresponding to one or more features of a roof of the building;
constructing a two-dimensional wireframe model of the roof based on the identified plurality of perimeter lines and interior lines;
automatically generating a three-dimensional wireframe model of the roof of the building based on the constructed two-dimensional wireframe model;
applying at least one filter to the at least one aerial image to compute a likelihood for each point in the at least one aerial image indicating whether the point represents a roof line;
scanning the at least one aerial image at a first angle to obtain first image intensity data;
rotating the at least one aerial image to a second angle different from the first angle;
scanning the at least one aerial image at the second angle to obtain second image intensity data; and
processing the first and second image intensity data to automatically identify the plurality of perimeter and interior lines in the at least one aerial image corresponding to the one or more features of the roof of the building.
9. The method of claim 8 , further comprising generating and displaying a graphical user interface for displaying the at least one aerial image of the building.
10. The method of claim 8 , further comprising generating a report comprising construction information associated with the generated three-dimensional wireframe model of the roof, the construction information being indicative of one or more of roof dimensions, pitches, surfaces, areas, and material costs associated with the roof.
11. The method of claim 8 , further comprising cropping the at least one aerial image around the building.
12. The method of claim 8 , further comprising
cropping the at least one aerial image around the building, and
automatically aligning the at least one aerial image based on the identified plurality of perimeter lines in the at least one aerial image corresponding to a perimeter of the roof of the building, the identified plurality of perimeter lines forming one of a closed polygon and a bounded area.
13. The method of claim 8 , further comprising allowing a user to adjust one or more of the automatically identified plurality of perimeter and interior lines via a graphical user interface.
14. A non-transitory, computer-readable medium having computer-readable instructions stored thereon which, when executed by a processor, causes the processor to perform the steps comprising:
receiving, by the processor, at least one aerial image of a building;
processing the at least one aerial image to automatically identify a plurality of perimeter lines and interior lines in the at least one aerial image corresponding to one or more features of a roof of the building;
constructing a two-dimensional wireframe model of the roof based on the identified plurality of perimeter lines and interior lines;
automatically generating a three-dimensional wireframe model of the roof of the building based on the constructed two-dimensional wireframe mode;
applying at least one filter to the at least one aerial image to compute a likelihood for each point in the at least one aerial image indicating whether the point represents a roof line;
scanning the at least one aerial image at a first angle to obtain first image intensity data;
rotating the at least one aerial image to a second angle different from the first angle;
scanning the at least one aerial image at the second angle to obtain second image intensity data; and
processing the first and second image intensity data to automatically identify the plurality of perimeter and interior lines in the at least one aerial image corresponding to the one or more features of the roof of the building.
15. The non-transitory, computer-readable medium of claim 14 , further comprising computer-readable instructions for causing the processor to perform the steps of generating and displaying a graphical user interface for displaying the at least one aerial image of the building.
16. The non-transitory computer-readable medium of claim 14 , further comprising computer-readable instructions for causing the processor to perform the steps of generating a report comprising construction information associated with the generated three-dimensional wireframe model of the roof, the construction information being indicative of one or more of roof dimensions, pitches, surfaces, areas, and material costs associated with the roof.
17. The non-transitory computer-readable medium of claim 14 , further comprising computer-readable instructions for causing the processor to perform the steps of cropping the at least one aerial image around the building.
18. The non-transitory computer-readable medium of claim 14 , further comprising computer-readable instructions for causing the processor to perform the steps of
cropping the at least one aerial image around the building, and
automatically aligning the at least one aerial image based on the identified plurality of perimeter lines in the at least one aerial image corresponding to a perimeter of the roof of the building, the identified plurality of perimeter lines forming one of a closed polygon and a bounded area.