Irregular feature mapping

• US 9,441,973 B2
• Filed: 06/12/2013
• Issued: 09/13/2016
• Est. Priority Date: 06/12/2012
• Status: Active Grant

• Current Assignee: TRX Systems, Inc.
• Original Assignee: TRX Systems, Inc.
• Inventors: Bandyopadhyay, Amrit, Beisel, Brian, Karvounis, John, Funk, Benjamin, Teolis, Carole, Giles, Christopher
• Primary Examiner(s): To, Tuan C.
• Assistant Examiner(s): Kan, Yuri
• Application Number:
  US13/916,487
• Publication Number:
  US 20150354965A1
• Time in Patent Office: 1,189 Days
• Field of Search: 701/469, 701/494, 701/500, 701/533, 701/28, 701/445, 701/446, 342/70, 345/419, 370/338
• US Class Current: 1/1
• CPC Class Codes: G01C 21/12 executed aboard the object being navigated; Dead reckoning
• CPC Class Codes: G01C 21/1652 with ranging devices, e.g. LIDAR or RADAR
• CPC Class Codes: G01C 21/1654 with electromagnetic compass
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01S 5/013 Identifying areas in a building
• CPC Class Codes: G01S 5/0264 at least one of the systems being a non-radio wave positioning system
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

Disclosed herein are methods and systems for mapping irregular features. In an embodiment, a computer-implemented method may include obtaining tracking data that has dead reckoning tracking data for a tracked subject along a path and performing shape correction on the tracking data to provide a first estimate of the path.

Claims

1. A computer-implemented method of tracking a trackee, the method being implemented by a computer that includes a physical processor, the method comprising:

obtaining tracking data for a tracked subject along a path, the tracking data including data from a dead reckoning sensor; and

performing shape correction on the tracking data to provide a first estimate of the path, wherein performing shape correction includes describing the path by a set of linear segments with a width less than a series of decreasing thresholds corresponding to coarse shape correction and fine shape correction.

2. The method of claim 1, wherein the dead reckoning sensor is at least one of an inertial sensor, and optical flow sensor, or a Doppler velocimeter.

3. The method of claim 1, wherein the performed shape correction further comprises:

grouping a set of linear segments into shapes; and

matching the grouped set of linear segments to a first group of shapes in a threshold proximity.

4. The method of claim 1, further comprising:

performing fine shape correction to the first estimate of the path that provides a second estimate of the path.

5. The method of claim 4, wherein fine shape correction comprises describing the first estimate of the path by a set of linear segments with width less than a second threshold.

6. A computer-implemented method of tracking a trackee, the method being implemented by a computer that includes a physical processor, the method comprising:

obtaining first tracking data for a first tracked subject along a path, the first tracking data including data from a dead reckoning sensor;

determining a unique shape feature in the first tracking data, wherein determining the unique shape feature includes describing the unique shape feature by more than a threshold of points based on using a Ramer-Douglas-Peucker algorithm for a given epsilon; and

determining that the unique shape feature in the first tracking data matches second tracking data for a second tracked subject along the path based on shape matching.

7. The method of claim 6, further comprising:

creating a first estimate of the path based on whether the unique shape feature in the first tracking data matches second tracking data for the second tracked subject along the path.

8. The method of claim 6, wherein the dead reckoning sensor is at least one of an inertial sensor, and optical flow sensor, or a Doppler velocimeter.

9. The method of claim 6, wherein determining the unique shape feature in the first tracking data matches second tracking data for the second tracked subject along the path comprises at least one:

determining a shape feature of the path described by more than a threshold of points based on using the Ramer-Douglas-Peucker algorithm with a parameter epsilon;

determining heading changes over the shape feature of the path are greater than a threshold standard deviation;

or

determining a length of the shape feature of the path is greater than a threshold length.

10. The method of claim 6, wherein the unique shape feature is described by a vector of heading changes over a duration of a path feature.

11. The method of claim 6, wherein determining that the unique shape feature in the first tracking data matches the second tracking data for the second tracked subject along the path comprises at least one of:

comparing vectors of heading changes of a plurality of shape match candidates over a duration of a plurality of features;

or

determining that a difference at each point in the vectors of heading changes of the plurality of shape match candidates over the duration of the plurality of features is less than a threshold.

12. A computing system used to track a trackee, the computing system comprising:

a dead reckoning sensor;

a processor in communication with the dead reckoning sensor; and

a memory coupled to the processor, the memory having stored thereon executable instructions that when executed by the processor cause the processor to effectuate operations comprising;

obtaining first tracking data for a first tracked subject along a path, the first tracking data including data from the dead reckoning sensor;

determining a unique shape feature in the first tracking data of the first tracked subject, wherein determining the unique shape feature includes describing the unique shape feature by more than a threshold of points based on using a Ramer-Douglas-Peucker algorithm for a given epsilon; and

using shape matching to determine whether the unique shape feature in the tracking data matches second tracking data for a second tracked subject along the path.

13. The computing system of claim 12, wherein the dead reckoning sensor is at least one of an inertial sensor, and optical flow sensor, or a Doppler velocimeter.

14. The computing system of claim 12, wherein determining the unique shape feature in the first tracking data of the first tracked subject comprises at least one:

determining a shape feature of the path described by more than a threshold of points based on using the Ramer-Douglas-Peucker algorithm with a parameter epsilon;

determining heading changes over the shape feature of the path are greater than a threshold standard deviation;

or

determining a length of the shape feature of the path is greater than a threshold length.

15. The computing system of claim 12, wherein the unique shape feature is described by a vector of heading changes over a duration of a path feature.

16. The computing system of claim 12, wherein determining the unique shape feature in the first tracking data of the first tracked subject matches second tracking data for the second tracked subject along the path comprises:

comparing heading changes of vectors of a plurality of shape match candidates over a duration of features; and

determining that a difference at each point in the vectors is less than a threshold.