Drone-based lowest floor elevation
The present disclosure describes systems and methods for acquiring structural attributes of a building. One such method comprises acquiring, by one or more cameras of an unmanned aerial vehicle, infrared thermal and visible RGB aerial images of a building; identifying structural components of the building based on an infrared thermal aerial image, wherein a floor structure of the building is identified from a color change in the infrared thermal aerial image between the building and a foundation structure of the building; positioning a bounding box around the floor structure of the building present in the infrared thermal aerial image; and estimating a lowest floor elevation of the building by calculating a lowest floor elevation value based on an amount of image pixels representing a distance between a top of the bounding box and a top of the foundation structure of the building. Other methods and systems are also provided.
1 . A method comprising:
acquiring, by one or more cameras of an unmanned aerial vehicle, one or more infrared thermal aerial images of a building and one or more visible RGB aerial images of the building;
identifying, by a computing device, structural components of the building based on the one or more infrared thermal aerial images of the building, wherein a floor structure of the building is identified from a color change in the one or more infrared thermal aerial images between the building and a foundation structure of the building; positioning, by the computing device, a bounding box around the floor structure of the building present in the one or more infrared thermal aerial images; and
estimating, by the computing device, a lowest floor elevation of the building by calculating a lowest floor elevation value based on an amount of image pixels representing a distance between a top of the bounding box and a top of the foundation structure of the building.
2 . The method of claim 1 , wherein the lowest floor elevation value for the building is calculated by converting the amount of image pixels representing the lowest floor elevation into the lowest floor elevation value in terms of a measurement of distance using a pixel ratio factor.
3 . The method of claim 2 , wherein the measurement of distance comprises feet under an imperial measurement system and the pixel ratio factor comprises a pixel per feet ratio.
4 . The method of claim 3 , wherein a view of the building is tilted in at least one of the one or more infrared thermal aerial images, the method further comprising generating, by the computing device, a corrected right angle infrared thermal aerial image of at least a portion of the building by horizontally distributing pixels along a straight line across the portion of the building, wherein the pixel ratio factor is determined using the corrected right angle infrared thermal aerial image.
5 . The method of claim 1 , wherein an obstruction is present in the one or more infrared thermal aerial images and the bounding box is positioned by joining two bounded boxes on each side of the obstruction.
6 . The method of claim 1 , further comprising configuring, by the computing device, a flight plan for the unmanned aerial vehicle to a plurality of buildings, wherein the unmanned aerial vehicle acquires the one or more visible RGB aerial images and the one or more infrared thermal aerial images for each of the plurality of buildings during execution of the flight plan.
7 . The method of claim 1 , further comprising predicting, by the computing device, a foundation type for the building based on the one or more visible RGB aerial images.
8 . The method of claim 7 , wherein the computing device is trained to predict the foundation type using a database of building images.
9 . The method of claim 1 , further comprising estimating, by the computing device, an Envelope Energy Performance signature for the building based on the one or more visible RGB aerial images and the one or more infrared thermal aerial images.
10 . The method of claim 1 , further comprising determining, by the computing device, a foundation type for the building based on the one or more visible RGB images and the one or more infrared thermal aerial images.
11 . A system comprising:
a computing device comprising a processor and a memory;
machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
acquire one or more infrared thermal aerial images of a building and one or more visible RGB aerial images of the building;
identify structural components of the building based on the one or more infrared thermal aerial images of the building, wherein a floor structure of the building is identified from a color change in the one or more infrared thermal aerial images between the building and a foundation structure of the building;
position a bounding box around the floor structure of the building present in the one or more infrared thermal aerial images; and
estimate a lowest floor elevation of the building by calculating a lowest floor elevation value based on an amount of image pixels representing a distance between a top of the bounding box and a top of the foundation structure of the building.
12 . The system of claim 11 , wherein the lowest floor elevation value for the building is calculated by converting the amount of image pixels representing the lowest floor elevation into the lowest floor elevation value in terms of a measurement of distance using a pixel ratio factor.
13 . The system of claim 12 , wherein the measurement of distance comprises feet under an imperial measurement system and the pixel ratio factor comprises a pixel per feet ratio.
14 . The system of claim 13 , wherein a view of the building is tilted in at least one of the one or more infrared thermal aerial images, wherein the machine-readable instructions, when executed by the processor, further cause the computing device to generate a corrected right angle infrared thermal aerial image of at least a portion of the building by horizontally distributing pixels along a straight line across the portion of the building, wherein the pixel ratio factor is determined using the corrected right angle infrared thermal aerial image.
15 . The system of claim 11 , wherein an obstruction is present in the one or more infrared thermal aerial images and the bounding box is positioned by joining two bounded boxes on each side of the obstruction.
16 . The system of claim 11 , wherein the machine-readable instructions, when executed by the processor, further cause the computing device to configure a flight plan for an unmanned aerial vehicle to a plurality of buildings and transmit the flight plan to the unmanned aerial vehicle, wherein the unmanned aerial vehicle acquires the one or more infrared thermal aerial images and the one or more visible RGB aerial images.
17 . The system of claim 11 , wherein the machine-readable instructions, when executed by the processor, further cause the computing device to predict a foundation type for the building based on the one or more visible RGB aerial images.
18 . The system of claim 17 , wherein the computing device is trained to predict the foundation type using a database of building images.
19 . The system of claim 11 , wherein the machine-readable instructions, when executed by the processor, further cause the computing device to estimate an Envelope Energy Performance signature for the building based on the one or more visible RGB aerial images and the one or more infrared thermal aerial images.
20 . The system of claim 11 , wherein the machine-readable instructions, when executed by the processor, further cause the computing device to determine a foundation type for the building based on the one or more visible RGB images and the one or more infrared thermal aerial images.