Audio-based 3D point cloud generation and analysis

Patent metadata

Field	Value
Publication number	US-9996970-B2
Application number	US-201615344268-A
Country	US
Kind code	B2
Filing date	Nov 4, 2016
Priority date	Mar 15, 2013
Publication date	Jun 12, 2018
Grant date	Jun 12, 2018

Abstract

In a system and method for inspecting a property, a microphone receives one or more audio waves propagating from a structure. One or more processors generate a 3D point cloud based on the received audio waves, analyzed the generated 3D point cloud to identify features of a surface or subsurface of the structure, and generate an estimate of a condition of the surface or subsurface.

First claim

What is claimed is:

1. A property inspection system comprising:
a microphone configured to receive one or more audio waves propagating from at least part of a structure, wherein the microphone is a laser microphone or a dynamic microphone;
one or more processors communicatively connected to the microphone;
one or more memories communicatively connected to the one or more processors, the one or more memories storing computer readable instructions that, when executed, cause the one or more processors to:
(i) generate a three-dimensional (3D) point cloud based on the one or more audio waves received at the microphone;
(ii) analyze the generated 3D point cloud to identify one or more features of a surface or a subsurface of the structure;
(iii) generate an estimate of a condition of the surface or the subsurface of the structure based on the identified one or more features; and
(iv) store the generated estimate at the one or more memories.

2. The property inspection system of claim 1 , wherein the microphone is the laser microphone.

3. The property inspection system of claim 1 , further including an aerial device attached to the microphone, the aerial device configured to convey the microphone.

4. The property inspection system of claim 3 , wherein the aerial device includes a control system configured to move the aerial device.

5. The property inspection system of claim 4 , wherein the control system is configured to autonomously move the aerial device.

6. The property inspection system of claim 4 , wherein the control system is configured to move the aerial device in response to wirelessly receiving a command from a controller manipulated by a user.

7. The property inspection system of claim 1 , further including a non-aerial device attached to the microphone, the non-aerial device configured to convey the microphone.

8. The property inspection system of claim 1 , further comprising: a mechanical feeler to physically manipulate the surface of the structure, wherein the one or more audio waves represent an audio response to the physical manipulation.

9. The property inspection system of claim 1 , further comprising:
an audio projector communicatively connected to the one or more processors and configured to project the one or more audio waves so that the one or more audio waves reflect off the surface or the subsurface of the structure before being received at the microphone.

10. The property inspection system of claim 1 , wherein the one or more identified features include one or more of the following: indents, holes, cracks, and crevices.

11. The property inspection system of claim 1 , wherein the processors analyze the generated 3D point cloud to identify the one or more features by:
retrieving a second 3D point cloud from the one or more memories; and
comparing the 3D point cloud to the second 3D point cloud.

12. The property inspection system of claim 1 wherein the instructions, when executed, further cause the one or more processors to:
generate a model surface utilizing the 3D point cloud and a surface reconstruction algorithm;
perform an analysis of the generated model surface; and
identify the one or more features of the surface or subsurface of the structure based, at least in part, on the analysis of the generated model surface.

13. A computer-implemented method of inspecting a structure, the method comprising:
receiving, at a microphone, one or more audio waves propagating from at least part of a structure, wherein the microphone is a dynamic microphone or a laser microphone;
generating, by one or more processors communicatively connected to the microphone, a three-dimensional (3D) point cloud of the structure based on the received one or more audio waves;
analyzing, by the one or more processors, the generated 3D point cloud to identify one or more features of a surface or a subsurface of the structure;
generating, by the one or more processors, an estimate of a condition of the surface or the subsurface of the structure based on the identified one or more features; and
storing the generated estimate at one or more memories.

14. The method of claim 13 , further comprising moving the microphone to a position where the one or more audio waves are received, wherein moving the microphone includes:
moving an aerial device conveying the microphone, the aerial device including a control system for moving the aerial device.

15. The method of claim 14 , wherein moving the aerial device comprises causing a control system to autonomously move the aerial device.

16. The method of claim 14 , wherein moving the aerial device comprises causing the control system to move the aerial device in response to wirelessly receiving a command from a controller manipulated by a user.

17. The method of claim 13 , further comprising physically manipulating the surface of the structure, wherein the one or more audio waves represent an audio response to the physical manipulation.

18. The method of claim 13 , further comprising projecting the one or more audio waves so that the one or more audio waves reflect off the surface or the subsurface of the structure before being received at the microphone.

19. The method of claim 13 , wherein analyzing the generated 3D point cloud to identify the one or more features comprises:
retrieving a second 3D point cloud from the one or more memories; and
comparing the 3D point cloud to the second 3D point cloud.

20. The method of claim 13 , further comprising:
generating a model surface utilizing the 3D point cloud and a surface reconstruction algorithm;
analyzing the generated model surface;
wherein the one or more features of the surface or the subsurface of the structure are identified based, at least in part, on said analyzing.

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Freeman James M
• Schmidgall Roger D
• Boyer Patrick H
• Christopulos Nicholas U
• Maurer Jonathan D
• Tofte Nathan L
• Jordan Ii Jackie O

Classifications

• G01S13/89

  for mapping or imaging · CPC title

• H04N7/185

  from a mobile camera, e.g. for remote control · CPC title

• G06Q40/08

  Insurance · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01S17/89 Primary

  for mapping or imaging · CPC title