Detecting changes in aerial images

• US 9,389,084 B1
• Filed: 09/17/2015
• Issued: 07/12/2016
• Est. Priority Date: 09/17/2015
• Status: Active Grant

• Current Assignee: Skycatch, Inc.
• Original Assignee: Skycatch, Inc.
• Inventors: Morales, Leonardo Felipe Romo, Chen, David, Pansari, Ambar, Sanz, Christian
• Primary Examiner(s): Jen, Ian
• Application Number:
  US14/857,457
• Time in Patent Office: 299 Days
• Field of Search: 701/436
• US Class Current: 1/1
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence

Abstract

The present disclosure is directed toward systems and methods for identifying changes to a target site based on aerial images of the target site. For example, systems and methods described herein generate representations of the target site based on aerial photographs provided by an unmanned aerial vehicle. In one or more embodiments, systems and method described herein identify differences between the generated representations in order to detect changes that have occurred at the target site.

Claims

1. A method comprising:

generating a first three-dimensional representation of a target site based on one or more first aerial images of the target site;

generating a second three-dimensional representation of the target site based on one or more second aerial images of the target site;

aligning the first three-dimensional representation and the second three-dimensional representation;

analyzing the first three-dimensional representation and the second three-dimensional representation to identify differences between the first three-dimensional representation and the second three-dimensional representation; and

generating a report indicating changes at the target site based on the differences between the first three-dimensional representation and the second three-dimensional representation.

2. The method as recited in claim 1, wherein:

the first three-dimensional representation comprises a plurality of first features;

the second three-dimensional representation comprises a plurality of second features;

wherein aligning the first three-dimensional representation and the second three-dimensional representation comprises matching one or more of the plurality of the first features with one or more of the plurality of the second features.

3. The method as recited in claim 2, wherein analyzing the first three-dimensional representation and the second three-dimensional representation to identify differences between the first three-dimensional representation and the second three-dimensional representation comprises analyzing differences between one or more of the plurality of first features and one or more of the plurality of second features.

4. The method as recited in claim 3, wherein generating a report indicating changes at the target site based on the differences between the first three-dimensional representation and the second three-dimensional representation comprises generating a report detailing the differences between one or more of the plurality of first features and one or more of the plurality of second features.

5. The method as recited in claim 3, further comprising identifying a magnitude of one or more of the differences between one or more of the plurality of first features and one or more of the plurality of second features.

6. The method as recited in claim 5, wherein generating a report indicating changes at the target site comprises generating an image comprising one or more annotations indicating the identified magnitudes for one or more of the differences between one or more of the plurality of first features and one or more of the plurality of second features.

7. The method as recited in claim 6, wherein generating a report further comprises removing one or more annotations indicating identified magnitudes for one or more differences that are less than a threshold value.

8. The method as recited in claim 6, further comprising assigning a visual characteristic to each of the plurality of second features in the second three-dimensional representation, wherein the assigned visual characteristic is representative of a magnitude of difference between the second feature in the second three-dimensional representation and the corresponding first feature in the first three-dimensional representation.

9. A system comprising at least one non-transitory computer readable storage medium storing instructions thereon that, when executed by at least one processor, cause the system to:

generate a first three-dimensional representation of a target site based on one or more first aerial images;

generate a second three-dimensional representation of the target site based on one or more second aerial images;

align the first three-dimensional representation and the second three-dimensional representation;

analyze the first three-dimensional representation and the second three-dimensional representation to identify differences between the first three-dimensional representation and the second three-dimensional representation; and

generate a report indicating changes at the target site based on the differences between the first three-dimensional representation and the second three-dimensional representation.

10. The system as recited in claim 9, wherein:

the first three-dimensional representation comprises a plurality of first features;

the second three-dimensional representation comprises a plurality of second features;

aligning the first three-dimensional representation and the second three-dimensional representation comprises matching one or more of the plurality of the first features with one or more of the plurality of the second features; and

analyzing the first three-dimensional representation and the second three-dimensional representation to identify differences between the first three-dimensional representation and the second three-dimensional representation comprises analyzing differences between one or more of the plurality of first features and one or more of the plurality of second features.

11. The system as recited in claim 10, wherein generating a report indicating changes at the target site based on the differences between the first three-dimensional representation and the second three-dimensional representation comprises generating a report detailing the differences between one or more of the plurality of first features and one or more of the plurality of second features.

12. The system as recited in claim 11, wherein the instructions, when executed by the at least one processor, further cause the system to identify a magnitude for one or more of the differences between one or more of the plurality of first features and one or more of the plurality of second features.

13. The system as recited in claim 12, wherein generating a report indicating changes at the target site comprises:

generating an image comprising one or more annotations indicating the identified magnitudes for one or more of the differences between one or more of the plurality of first features and one or more of the plurality of second features;

removing one or more annotations indicating identified magnitudes for one or more differences that are less than a threshold value.

14. The system as recited in claim 13, wherein the instructions, when executed by the at least one processor, further cause the system to assign a visual characteristic to each of the plurality of second features in the second three-dimensional representation, wherein the assigned visual characteristic is representative of a magnitude of difference between the second feature in the second three-dimensional representation and the corresponding first feature in the first three-dimensional representation.

15. A system comprising:

one or more unmanned aerial vehicles for capturing one or more first aerial images of a target site at a first time, and capturing one or more second aerial images of the target site at a second time;

at least server device storing instructions that, when executed by the at least one server device, cause the at least one server device to;

generate a first three-dimensional representation of the target site based on the one or more first aerial images;

generate a second three-dimensional representation of the target site based on the one or more second aerial images;

detect, based on the first three-dimensional representation and the second three-dimensional representation, changes at the target site between the first time and the second time; and

generate a report indicating the detected changes at the target site.

16. The system as recited in claim 15, wherein detecting, based on the first three-dimensional representation and the second three-dimensional representation, changes at the target site between the first time and the second time comprises analyzing differences between the first three-dimensional representation and the second three-dimensional representation.

17. The system as recited in claim 16, wherein analyzing differences between the first three-dimensional representation and the second three-dimensional representation comprises:

aligning matched points in the second three-dimensional representation with corresponding points in the first three-dimensional representation; and

analyzing differences in non-matched points in the first three-dimensional representation and the second three-dimensional representation.

18. The system as recited in claim 17, wherein generating a report indicating the detected changes at the target site comprises generating a reporting image comprising one or more annotations indicating the analyzed differences in the matched points.

19. The system as recited in claim 15, wherein the at least one server device further stores instructions that, when executed by the at least one server device, cause the at least one server device to generate a two-dimensional representation of the target site based on a view of the second three-dimensional representation of the target site.

20. The system as recited in claim 19, wherein generating a report indicating the detected changes at the target site between the first time and the second time comprises indicating, on the two-dimensional representation of the target site, one or more detected changes at the target site between the first time and the second time.