Unmanned aerial vehicle rooftop inspection system
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for an unmanned aerial system inspection system. One of the methods is performed by a UAV and includes receiving, by the UAV, flight information describing a job to perform an inspection of a rooftop. A particular altitude is ascended to, and an inspection of the rooftop is performed including obtaining sensor information describing the rooftop. Location information identifying a damaged area of the rooftop is received. The damaged area of the rooftop is traveled to. An inspection of the damaged area of the rooftop is performed including obtaining detailed sensor information describing the damaged area. A safe landing location is traveled to.
1. A computerized method performed by a system comprising one or more processors, the method comprising:
displaying, via an interface, a first graphical representation of a structure to be inspected, the first graphical representation comprising one or more images describing an aerial view of the structure;
determining a flight pattern according to which an unmanned aerial vehicle (UAV) is to navigate above the structure and obtain sensor data describing an aerial view of the structure, the flight pattern including waypoints;
instructing the UAV to perform the flight pattern and navigate the UAV according to the flight pattern, and obtain sensor data;
receiving sensor data obtained by the UAV during performance of the flight pattern, wherein the sensor data includes multiple digital images describing an aerial view depicting a rooftop of the structure, and wherein a subset of the digital images include greater than a threshold level of detail of particular areas of the rooftop;
generating a second graphical representation of the structure based on the multiple digital images, wherein the second graphical representation comprises composite imagery of the rooftop based on the multiple digital images;
determining the occurrence of damaged areas of the rooftop in the multiple digital images; and
displaying, via a user interface, the second graphical representation of the rooftop with damaged areas of the rooftop identified in the second graphical representation, wherein the damaged areas of the rooftop are represented by a graphical indication of the respective damaged areas, wherein the user interface is configured to receive selection of a damaged area identified in the second graphical representation and display one or more digital images that include greater than the threshold level of detail of the damaged area.
2. The method of claim 1 , wherein determining the occurrence of damaged areas of the rooftop comprises:
executing a visual classifier trained to identify rooftop damage, that a particular area of the rooftop identified from the obtained sensor information is indicated as being damaged.
3. The method of claim 1 , wherein determining whether surface damage has occurred about a particular area of the rooftop comprises:
determining whether a feature indicative of rooftop damage exists in a digital image; and
weighting the feature to determine that the feature is indicative of a damaged area or an undamaged area.
4. The method of claim 1 , further comprising training a visual classifier based on a first dataset of images comprising examples of rooftop damage.
5. The method of claim 1 , further comprising:
determining based on the aerial images, a material composition of the rooftop, wherein the material composition for the rooftop is one of wood, tile or clay.
6. The method of claim 1 , wherein the type of rooftop damage identified is one of hail damage, cracked tiles, broken tiles, surface dents or organism growth.
7. The method of claim 1 , further comprising:
receiving, via a user interface, positions about the second graphical representation of the rooftop indicating locations of damaged areas.
8. The method of claim 1 , wherein the positions above the structure are set at an altitude such that a required image pixel resolution is obtained.
9. The method of claim 1 , further comprising:
displaying, via the interface, a graphical representation of the flight pattern above the first graphical representation of the property.
10. The method of claim 1 , further comprising:
determining the type of damage; and
assigning a description to the type of damage.
11. A system comprising one or more processors, and a computer storage media storing instructions, that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
displaying, via an interface, a first graphical representation of a structure to be inspected, the first graphical representation comprising one or more images describing an aerial view of the structure;
determining a flight pattern according to which an unmanned aerial vehicle (UAV) is to navigate above the structure and obtain sensor data describing an aerial view of the structure, the flight pattern including waypoints;
instructing the UAV to perform the flight pattern and navigate the UAV according to the flight pattern, and obtain sensor data;
receiving sensor data obtained by the UAV during performance of the flight pattern, wherein the sensor data includes multiple digital images describing an aerial view depicting a rooftop of the structure, and wherein a subset of the digital images are detailed images;
generating a second graphical representation of the structure based on the multiple digital images, wherein the second graphical representation comprises composite imagery of the rooftop based on the multiple digital images;
determining the occurrence of damaged areas of the rooftop in the multiple digital images; and
displaying, via a user interface, the second graphical representation of the rooftop with damaged areas of the rooftop identified in the second graphical representation, wherein the damaged areas of the rooftop are represented by a graphical indication of the respective damaged areas, wherein the user interface is configured to receive selection of a damaged area and display one or more detailed images of the damaged area.
12. The system of claim 11 , wherein determining the occurrence of damaged areas of the rooftop comprises:
executing a visual classifier trained to identify rooftop damage, that a particular area of the rooftop is indicated as being damaged.
13. The system of claim 12 , further comprising the operations of:
training the visual classifier based on a first dataset of images comprising examples of rooftop damage.
14. The system of claim 11 , wherein determining the occurrence of damaged areas of the rooftop comprises:
determining whether a feature indicative of rooftop damage exists in a digital image; and
weighting the feature to determine that the feature is indicative of a damaged area or an undamaged area.
15. The system of claim 11 , further comprising the operations of:
determining based on the aerial images, a material composition of the rooftop, wherein the material composition for the rooftop is one of wood, tile or clay.
16. The system of claim 11 , wherein the type of rooftop damage identified is one of hail damage, cracked tiles, broken tiles, surface dents or organism growth.
17. The system of claim 11 , further comprising the operations of:
receiving, via a user interface, positions about the second graphical representation of the rooftop indicating locations of damaged areas of the rooftop.
18. The system of claim 11 , wherein waypoints above the structure are set at an altitude such that a required image pixel resolution for the multiple digital images of the rooftop is obtained.
19. The system of claim 11 , further comprising the operations of:
displaying, via the interface, a graphical representation of the flight pattern above the first graphical representation of the property.
20. The system of claim 11 , further comprising the operations of:
determining the type of damage; and
assigning a description to the type of damage.
21. A computer storage medium comprising instructions that when executed by one or more processors, cause the processors to perform operations comprising:
displaying, via an interface, a first graphical representation of a structure to be inspected, the first graphical representation comprising one or more images describing an aerial view of the structure;
determining a flight pattern according to which an unmanned aerial vehicle (UAV) is to navigate above the structure and obtain sensor data describing an aerial view of the structure, the flight pattern including waypoints;
instructing the UAV to perform the flight pattern and navigate the UAV according to the flight pattern, and obtain sensor data;
receiving sensor data obtained by the UAV during performance of the flight pattern, wherein the sensor data includes multiple digital images describing an aerial view depicting a rooftop of the structure, and wherein a subset of the digital images include greater than a threshold level of detail of particular areas of the rooftop;
generating a second graphical representation of the structure based on the multiple digital images, wherein the second graphical representation comprises composite imagery of the rooftop based on the multiple digital images;
determining the occurrence of damaged areas of the rooftop in the multiple digital images; and
displaying, via a user interface, the second graphical representation of the rooftop with damaged areas of the rooftop identified in the second graphical representation, wherein the damaged areas of the rooftop are represented by a graphical indication of the respective damaged areas, wherein the user interface is configured to receive selection of a damaged area and display one or more digital images that include greater than the threshold level of detail of the damaged area.
22. The computer storage medium of claim 21 , wherein determining the occurrence of damaged areas of the rooftop comprises:
executing a visual classifier trained to identify rooftop damage, that a particular area of the rooftop is indicated as being damaged.
23. The computer storage medium of claim 22 , further comprising the operations of:
training a visual classifier based on a first dataset of images comprising examples of rooftop damage.
24. The computer storage medium of claim 21 , wherein determining the occurrence of damaged areas of the rooftop comprises:
determining whether a feature indicative of rooftop damage exists in a digital image; and
weighting the feature to determine that the feature is indicative of a damaged area or an undamaged area.
25. The computer storage medium of claim 21 , further comprising the operations of:
determining based on the aerial images, a material composition of the rooftop, wherein the material composition for the rooftop is one of wood, tile or clay.
26. The computer storage medium of claim 21 , wherein the type of rooftop damage identified is one of hail damage, cracked tiles, broken tiles, surface dents or organism growth.
27. The computer storage medium of claim 21 , further comprising the operations of:
receiving, via a user interface, positions about the second graphical representation of the rooftop indicating locations of damaged areas of the rooftop.
28. The computer storage medium of claim 21 , wherein waypoints above the structure are set at an altitude such that a required image pixel resolution for the multiple digital images of the rooftop is obtained.
29. The computer storage medium of claim 21 , further comprising the operations of:
displaying, via the interface, a graphical representation of the flight pattern above the first graphical representation of the property.
30. The computer storage medium of claim 21 , further comprising the operations of:
determining the type of damage; and
assigning a description to the type of damage.