Systems and methods for autonomous perpendicular imaging of test squares

• US 10,521,664 B2
• Filed: 10/01/2018
• Issued: 12/31/2019
• Est. Priority Date: 11/04/2016
• Status: Active Grant

• Current Assignee: Loveland Innovations, Inc.
• Original Assignee: Loveland Innovations, LLC
• Inventors: Loveland, Jim, Larson, Leif, Christiansen, Dan, Christiansen, Tad, Christiansen, Cam
• Primary Examiner(s): Pham, Nam D
• Application Number:
  US16/149,010
• Publication Number:
  US 20190042829A1
• Time in Patent Office: 456 Days
• Field of Search: 348144
• CPC Class Codes: G01C 11/02 Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/30184 Infrastructure
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: G06T 7/38 Registration of image sequences
• CPC Class Codes: G06V 20/17 taken from planes or by drones
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G09B 21/00 Teaching, or communicating with, the blind, deaf or mute audible presentation of material to be studied G09B5/04; devices or methods for replacing direct visual or auditory perception by another kind of perception A61F9/08, A61F11/04; audible indication of meter readings or of colour G01D7/12; watches for blind persons G04B25/02; speech analysis, speech recognition G10L; sound-recording or reproducing, per se G11B
• CPC Class Codes: G09B 29/006 Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes
• CPC Class Codes: G09B 29/106 using electronic means
• CPC Class Codes: G09B 9/30 Simulation of view from aircraft
• CPC Class Codes: G09B 9/301 by computer-processed or -generated image
• CPC Class Codes: G09B 9/302 the image being transformed by computer processing, e.g. updating the image to correspond to the changing point of view
• CPC Class Codes: H04N 7/185 from a mobile camera, e.g. for remote control

Abstract

An unmanned aerial vehicle (UAV) assessment and reporting system may utilize one or more scanning techniques to provide useful assessments and/or reports for structures and other objects. The scanning techniques may be performed in sequence and optionally used to further fine-tune each subsequent scan. The system may include shadow elimination, annotation, and/or reduction for the UAV itself and/or other objects. A UAV may receive or determine a pitch of roof of a structure or otherwise orthogonally align an optical axis of a camera with respect to a planar roof surface. An imaging system may capture perpendicular images of sample regions that have a defined area-squared.

Claims

1. An unmanned aerial vehicle (UAV) assessment system for capturing orthogonal images, comprising:

a camera to capture images of at least a portion of a roof of a structure; and

an imaging system to;

adjust an angle of the camera of the UAV to a non-zero angle relative to a downward direction to align an optical axis of the camera substantially orthogonal to an angled surface of the roof, and

capture an image of the angled surface of the roof with the optical axis of the camera aligned perpendicular to the angled surface.

2. The UAV assessment system of claim 1, further comprising a camera control module to align the angle of the camera substantially orthogonal with respect to the angled surface of the roof based three equidistant distances measured by a sensor of the UAV at a common angle relative to the optical axis of the camera.

3. The UAV assessment system of claim 1, wherein a pitch of the surface of the roof is determined from a three-dimensional model of at least a portion of the structure.

4. The UAV assessment system of claim 1, further comprising a pitch determination system to determine the angled surface of the roof, and wherein the pitch of the roof is used to adjust the angle of the camera of the UAV to align the optical axis of the camera substantially orthogonal to the angled surface of the roof.

5. The UAV assessment system of claim 4, wherein the pitch determination system is part of a remote system in communication with the UAV.

6. The UAV assessment system of claim 4, wherein the pitch determination system comprising an image processing system to determine an angle of the surface of the roof based on at least one captured image.

7. The UAV assessment system of claim 6, wherein the image processing system utilizes computer vision to identify an angle of the surface of the roof.

8. The UAV assessment system of claim 1, further comprising a pitch determination system to determine a pitch of the angled surface of the roof, and wherein the pitch of the roof is used adjust the angle of the camera of the UAV to align the optical axis of the camera substantially orthogonal to the angled surface of the roof.

9. The UAV assessment system of claim 1, wherein the imaging system is configured to capture an image with a target square footage of 100 square feet.

10. The UAV assessment system of claim 1, wherein the camera comprises one of a visible light imaging camera and an infrared imaging camera.

11. A method to capture sample regions having a target area-squared (A2), comprising:

identifying a non-zero angle with respect to ground to which a camera of a UAV can be adjusted for a given location of the UAV to align an optical axis of the camera orthogonal to an angled surface of a roof of a structure; and

capturing an image of at least a portion of the angled surface of the roof of the structure that includes a sample region of the surface with a predefined target area-squared (A2) using an imaging system with the optical axis of the camera aligned perpendicular to the angled surface based on the identified non-zero angle.

12. The method of claim 11, wherein the camera includes an image sensor having an effective aspect ratio that is one of 2:

2, 3;

2, 4;

3, and 16;

9.

13. The method of claim 11, wherein the sample region of the surface of the roof having the target area-squared fills an entire frame of the captured image without cropping.

14. The method of claim 11, wherein an image sensor of the camera includes a rectangular aspect ratio, and wherein the predefined area-squared (A²) fills an entire rectangular frame.

15. The method of claim 14, wherein the sample region is one of:

rectangular, square, and triangular.

16. The method of claim 14, wherein the predefined area-squared (A²) comprises a 100 square-foot “

test square”

that is rectangular.

17. An imaging system for a UAV to capture orthogonal images of a surface at an angle with respect to a downward direction, comprising:

a UAV positioning system to receive a position of a UAV relative to a roof surface that is at an angle relative to a downward direction;

a tilt angle determination system to determine a tilt angle for a camera of the UAV to orthogonally align an optical axis of the camera of the UAV with the angled roof surface;

a camera control module to instruct the UAV to do at least one of;

adjust the tilt angle an angle of the camera to orthogonally align the optical axis of the camera with respect to the angled roof surface, and

adjust a location of the UAV relative to the roof surface to facilitate orthogonal alignment of the optical axis of the camera with respect to the angled roof surface.

18. The imaging system of claim 17, wherein the tilt angle determination system comprises at least one sensor to measure distance, wherein each sensor is configured to measure a distance to the roof surface at a known angle relative to the optical axis of the camera.

19. The imaging system of claim 17, wherein the tilt angle determination system comprising an image processor to process at least one captured image of the roof surface to determine an angle of the roof surface.

20. The imaging system of claim 17, wherein the tilt angle determination system comprising an image processor to process at least one captured image of the roof surface to determine an angle of the roof surface.