Methods and systems for automatic and semi-automatic geometric and geographic feature extraction

• US 9,292,747 B2
• Filed: 03/15/2013
• Issued: 03/22/2016
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Baker, Anthony Wayne
• Primary Examiner(s): Patel, Jayesh A
• Assistant Examiner(s): Kholdebarin, Iman K
• Application Number:
  US13/839,799
• Publication Number:
  US 20140270359A1
• Time in Patent Office: 1,103 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

Methods and systems for facilitating detecting features in sensor data are described. One example method implemented by a computing device includes receiving a first set of sensor data about a geographical region, and generating a second set of sensor data. The first set of sensor data includes data in a plurality of bands. The second set of sensor data is generated by receiving a first input designating a first sub-region of the geographical region, and determining a single band representation of at least a portion of the first set of sensor data associated with the first sub-region.

Claims

1. A method for facilitating detecting features in sensor data, the method being implemented by a computing device, the method comprising:

receiving, by the computing device, a first set of sensor data about a geographical region, the first set of sensor data comprising data in a plurality of bands; and

generating, by the computing device, a second set of sensor data by;

receiving, by the computing device, a first input designating a first sub-region of the geographical region;

determining, by the computing device, a single band representation of at least a portion of the first set of sensor data associated with the first sub-region;

labeling objects defining substantially closed polygons in at least a portion of the first set of sensor data associated with the first sub-region;

reducing non-corner portions of the labeled objects to straight line segments;

computing a turn angle between adjacent straight line segments

determining, for each labeled object, a total boundary length of said labeled object;

determining, for each labeled object, a total length of straight line segments separated by a turn angle having a value substantially equal to at least a predetermined first angle value;

determining, for each labeled object, a boundary ratio of the total length of straight line segments separated by a turn angle substantially equal to the first angle value to the total boundary length of said labeled object; and

identifying as buildings the labeled objects for which the boundary ratio exceeds a threshold value.

2. A method in accordance with claim 1, wherein said receiving a first input designating a first sub-region further comprises receiving, by the computing device, a designation of at least a selected data element of the first set of sensor data associated with the first sub-region, and wherein said determining a single band representation is based, at least in part, on a value of the selected data element in at least one band of the plurality of bands.

3. A method in accordance with claim 2, wherein said determining a single band representation comprises determining a value for each data element associated with the first sub-region as a function of the difference between an initial value for each said data element and the value of the selected data element in the at least one band of the plurality of bands, and assigning the determined value to that data element.

4. A method in accordance with claim 3, wherein determining a single band representation based on a value of the selected data element in at least one band of the plurality of bands comprises determining a single band representation based on the value of the selected data element in each band of the plurality of bands and a weight assigned to each band of the plurality of bands.

5. A method in accordance with claim 3, wherein determining a value for each data element associated with the first sub-region as a function of the difference between an initial value for each said data element and the value of the selected data element in the at least one band of the plurality of bands comprises determining a value for each data element associated with the first sub-region using a weighted norm metric.

6. A method in accordance with claim 1, wherein generating a second set of sensor data further comprises

displaying, in a user interface, a histogram of the single band representation of the portion of the first set of sensor data associated with the first sub-region;

receiving, by the computing device, an input designating a threshold level based on the histogram; and

filtering the second set of sensor data using the designated threshold level.

7. A method in accordance with claim 1, further comprising identifying vegetation associated with the first set of sensor data based on at least one spectral characteristic of the first set of sensor data by:

generating a first index based on at least a first spectral characteristic of the first set of sensor data;

generating a second index based on at least a second spectral characteristic of the first set of sensor data; and

identifying vegetation associated with the first set of sensor data as a function of the first index and the second index.

8. A method in accordance with claim 7, wherein identifying vegetation associated with the first set of sensor data as a function of the first index and the second index comprises generating a third index as a function of the first index and the second index, and identifying vegetation associated with the first set of sensor data based on the third index.

9. A computing device for facilitating detecting features in sensor data, the computing device comprising a processor and a memory coupled to said processor, wherein said memory comprises computer-executable instructions that, when executed by said processor, cause said computing device to:

receive a first set of sensor data about a geographical region, the first set of sensor data comprising data in a plurality of bands;

generate a second set of sensor data by;

receiving a first input designating a first sub-region of the geographical region; and

determining a single band representation of at least a portion of the first set of sensor data associated with the first sub-region;

label objects defining substantially closed polygons in at least a portion of the first set of sensor data associated with the first sub-region;

reduce non-corner portions of the labeled objects to straight line segments; and

compute a turn angle between adjacent straight line segments

determine, for each labeled object, a total boundary length of said labeled object;

determine, for each labeled object, a total length of straight line segments separated by a turn angle having value substantially equal to at least a predetermined first angle value;

determine, for each labeled object, a boundary ratio of the total length of straight line segments separated by a turn angle substantially equal to the first angle value to the total boundary length of said labeled object; and

identify as buildings the labeled objects for which the boundary ratio exceeds a threshold value.

10. A computing device in accordance with claim 9, wherein receiving a first input designating a first sub-region further comprises receiving a designation of at least a selected data element of the first set of sensor data associated with the first sub-region, and wherein determining a single band representation is based, at least in part, on a value of the selected data element in at least one band of the plurality of bands.

11. A computing device in accordance with claim 10, wherein determining a single band representation comprises determining a value for each data element associated with the first sub-region as a function of a weight assigned to each band of the plurality of bands and the difference between an initial value for each said data element in each band of the plurality of bands and the value of the selected data element in each corresponding band of the plurality of bands.

12. A non-transitory computer-readable storage device having computer-executable instructions embodied thereon, wherein when executed by a computing device comprising a processor and a memory coupled to the processor, said computer-executable instructions cause the computing device to:

receive a first set of sensor data about a geographical region, the first set of sensor data comprising data in a plurality of bands;

generate a second set of sensor data by;

receiving a first input designating a first sub-region of the geographical region; and

determining a single band representation of at least a portion of the first set of sensor data associated with the first sub-region;

label objects defining substantially closed polygons in at least a portion of the first set of sensor data associated with the first sub-region;

reduce non-corner portions of the labeled objects to straight line segments;

compute a turn angle between adjacent straight line segments

determine, for each labeled object, a total boundary length of said labeled object;

determine, for each labeled object, a total length of straight line segments separated by a turn angle having value substantially equal to at least a predetermined first angle value;

determine, for each labeled object, a boundary ratio of the total length of straight line segments separated by a turn angle substantially equal to the first angle value to the total boundary length of said labeled object; and

identify as buildings the labeled objects for which the boundary ratio exceeds a threshold value.

13. A non-transitory computer-readable storage device in accordance with claim 12, wherein receiving a first input designating a first sub-region further comprises receiving a designation of at least a selected data element of the first set of sensor data associated with the first sub-region, and wherein said computer-executable instructions cause said computing device to determine a single band representation based, at least in part, on a value of the selected data element in at least one band of the plurality of bands.

14. A non-transitory computer-readable storage device in accordance with claim 13, wherein said computer-executable instructions cause said computing device to determine a single band representation by determining a value for each data element associated with the first sub-region as a function of a weight assigned to each band of the plurality of bands and the difference between an initial value for each said data element in each band of the plurality of bands and the value of the selected data element in each corresponding band of the plurality of bands.