Systems and methods for adaptive property analysis via autonomous vehicles

• US 10,825,346 B2
• Filed: 04/30/2018
• Issued: 11/03/2020
• 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): Nolan, Peter D
• Assistant Examiner(s): Smith-Stewart, Demetra R
• Application Number:
  US15/966,560
• Publication Number:
  US 20180247545A1
• Time in Patent Office: 918 Days
• Field of Search: None
• CPC Class Codes: B64C 39/024 of the remote controlled vehicle type, i.e. RPV
• CPC Class Codes: B64D 47/08 Arrangements of cameras
• CPC Class Codes: B64U 10/14 with four distinct rotor axes, e.g. quadcopters
• CPC Class Codes: B64U 2101/30 for imaging, photography or videography
• CPC Class Codes: B64U 2201/10 autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
• 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: G05D 1/0094 involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06V 10/225 based on a marking or identifier characterising the area
• CPC Class Codes: G06V 10/235 based on user input or interaction
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft
• CPC Class Codes: G08G 5/045 Navigation or guidance aids, e.g. determination of anti-collision manoeuvers radar or analogous systems specially adapted for anti-collision between aircraft G01S13/933
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source
• 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 conduct micro scans of a wide variety of property types. Scan data from any of a wide variety of sensor types may be compared with profile data using computer vision techniques to identify characteristics, defects, damage, construction materials, and the like. A hierarchal structure of the scan data may reduce the size of data sets used for property identification. For example, identifying a material type of a property may reduce or eliminate the need to compare scan data with specific data profiles for defects not related to the identified material type. Similarly, identifying a particular characteristic of a property may narrow down the data sets of possible material types. A rule set evaluator may evaluate matched profile data to determine adaptive actions to modify the navigation or scanning process of the UAV.

Claims

1. An unmanned aerial vehicle (UAV) assessment system for imaging a structure, comprising:

a first sensor of a first sensor type on a UAV to capture scan data by scanning a property during a first flight pattern;

a library of data profiles that includes;

a first set of data profiles associated with the first sensor type for material identification, and a set of characteristic data profiles for each of a plurality of different material types that are identifiable within the first set of data profiles;

a computer vision evaluator to;

extract, using computer-vision techniques, high-dimensional data from scan data captured by the first sensor,

compare at least one of (i) the scan data captured by the first sensor and (ii) the extracted high-dimensional data from the scan data with data profiles within the first set of data profiles to identify a material of the property,

compare at least one of (i) the scan data captured by the first sensor and (ii) the extracted high-dimensional data from the scan data with the distinct set of characteristic data profiles associated with the identified material, and

assign a characteristic to the property based on the comparison with the distinct set of characteristic data profiles associated with the identified material; and

a rule set evaluator to determine at least one adaptive action to be taken by the UAV to modify the scanning of the property during the first flight pattern based on a real-time evaluation of the assigned characteristic of the property.

2. The UAV assessment system of claim 1, wherein the assigned characteristic comprises a construction defect.

3. The UAV assessment system of claim 1, wherein the assigned characteristic comprises damage to the property.

4. The UAV assessment system of claim 1, wherein the property comprises at least a portion of at least one of a residence, an office building, an industrial facility, a tower, a bridge, a road, a light assembly, a vehicle, industrial equipment, and land.

5. The UAV assessment system of claim 1, wherein the first sensor comprises an optical imaging sensor.

6. The UAV assessment system of claim 1, wherein the first sensor comprises a non-optical imaging sensor.

7. The UAV assessment system of claim 6, wherein the computer vision evaluator uses the scan data from the non-optical imaging sensor to identify the material of the property, and

wherein high-dimensional scan data is extracted from the scan data from the at least one non-optical imaging sensor.

8. The UAV assessment system of claim 6, wherein the at least one non-optical imaging sensor comprises an infrared imaging sensor.

9. The UAV assessment system of claim 6, wherein the at least one non-optical imaging sensor comprises an ultrasonic imaging sensor.

10. The UAV assessment system of claim 1, wherein the high-dimensional data comprises multi-dimensional data.

11. The UAV assessment system of claim 1, wherein the adaptive action comprises a modification of a navigation path of the UAV.

12. The UAV assessment system of claim 1, wherein the adaptive action comprises a modification of a scan process of the UAV in response to the evaluated characteristic of the property.

13. The UAV assessment system of claim 12, wherein the modification of the scan process of the UAV in response to the evaluated characteristic of the property comprises the activation of a second sensor type to capture additional scan data of the property.

14. A method for imaging a property using an unmanned aerial vehicle (UAV) assessment system, comprising:

capturing, via a first type of sensor carried by a UAV, scan data during a scan of a property during a first flight;

comparing the scan data captured by the first type of sensor with at least one of a plurality of data profiles within a library of data profiles;

identifying a data profile within the library of data profiles that matches the scan data captured by the first type of sensor;

identifying a material type of the property based on the identified data profile within the library of data profiles that matches the scan data captured by the first type of sensor;

comparing, subsequently, scan data captured by the first type of sensor with a subset of data profiles within the library of data profiles, wherein at least some of the data profiles within the library of data profiles are excluded from the subset of data profiles based on the identified material;

identifying, based on the subsequent comparison of the scan data with the subset of data profiles, a data profile that matches the scan data;

assigning a characteristic to the property based on the matched data profile from within the subset of data profiles; and

determining, via a rule set evaluator, at least one adaptive action to be taken by the UAV to modify the scan of the property during the first flight based on a real-time evaluation of the assigned characteristic of the property.

15. The method of claim 14, wherein assigning the characteristic comprises identifying a construction defect associated with the property.

16. A method for imaging a property using an unmanned aerial vehicle (UAV) assessment system, comprising:

capturing, via a first type of sensor carried by a UAV, scan data during a scan of a property during a predefined flight pattern;

comparing the scan data captured by the first type of sensor with at least one of a plurality of data profiles within a library of data profiles;

identifying a data profile within the library of data profiles that matches the scan data captured by the first type of sensor;

identifying a characteristic of the property based on the identified data profile within the library of data profiles that matches the scan data captured by the first type of sensor;

comparing, subsequently, scan data captured by the first type of sensor with a subset of data profiles within the library of data profiles, wherein at least some of the data profiles within the library of data profiles are excluded from the subset of data profiles based on the identified characteristic;

identifying, based on the subsequent comparison of the scan data with the subset of data profiles, a data profile that matches the scan data;

assigning a material type to the property based on the matched data profile from within the subset of data profiles; and

evaluating, via a rule set evaluator, a rule set applicable to the assigned characteristic of the property to determine at least one adaptive action to be taken by the UAV to modify the predefined flight pattern in real-time.

17. The method of claim 16, wherein the assigned material type of the property comprises an identification of a skylight on a roof of a structure and wherein the adaptive action comprises modifying a navigation path of the UAV to capture scan data of the skylight from multiple angles.

18. The method of claim 16, further comprising:

activating, via an adaptive scan system, a supplemental sensor system of a second type to perform additional scanning based on the identified characteristic and assigned material type of the property.