Systems and methods for identifying attributes located along segments of a driving route

• US 9,909,884 B2
• Filed: 10/14/2016
• Issued: 03/06/2018
• Est. Priority Date: 09/16/2010
• Status: Active Grant

• Current Assignee: United Parcel Service Of America Incorporated (United Parcel Service Incorporated)
• Original Assignee: United Parcel Service Of America Incorporated (United Parcel Service Incorporated)
• Inventors: Siris, Marc David
• Primary Examiner(s): RUSHING, MARK S
• Application Number:
  US15/294,072
• Publication Number:
  US 20170030721A1
• Time in Patent Office: 508 Days
• Field of Search: 3409951
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: G01S 19/072 Ionosphere corrections
• CPC Class Codes: G01S 19/13 Receivers
• CPC Class Codes: G01S 19/52 Determining velocity
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

Various embodiments of the present invention provide systems, methods, and computer program products for identify the probability of a particular attribute being located along a segment of interest for a driving route. In general, various embodiments of the invention involve representing the segment of the driving route by patterns of speed variations obtained from GPS elements along the segment of the driving route and using the representation as input for functions representing various types of attributes to determine the probability of a particular type of attribute existing along the segment of the driving route.

Claims

1. A method for providing a prediction of a type of attribute located along a segment of a driving route based on one or more speed variation patterns obtained from Global Positioning System (GPS) elements, the method comprising:

(a) representing, via a processor, the segment of the driving route by a multi-dimensional feature vector capturing the one or more speed variation patterns; and

(b) inputting the multi-dimensional feature vector into a function for the type of attribute and in response to analyzing the multi-dimensional feature vector input in the function, determining the prediction indicating whether an object of the type of attribute is physically located along the segment of the driving route.

2. The method of claim 1, wherein prior to (a) representing the segment, the method further comprises:

(c) retrieving a plurality of GPS elements; and

(d) for each GPS element that corresponds to one or more positions along the segment of the driving route, identifying a portion of the GPS element recorded along the segment to include in an input GPS set.

3. The method of claim 1, wherein the multi-dimensional feature vector being configured is based in part on one or more data points of the input GPS set.

4. The method of claim 1, wherein the attribute comprises at least one of a traffic light, a stop sign, a yield sign, a speed bump, a reduced speed zone, or mixed traffic signals.

5. The method of claim 2, wherein step (d) further comprises the sub-steps of:

producing a topology from the GPS elements that pass along the segment of the driving route;

drawing a rectangle to encompass at least a portion of the segment of the driving route to define a boundary; and

including in the input GPS set the GPS data points located inside the boundary from the portions of the GPS elements that pass along the segment of the driving route.

6. The method of claim 1, wherein the multi-dimensional feature vector comprises an average value of M number of speed variables sampled from each of the GPS elements associated with the segment of the driving route.

7. The method of claim 1, wherein the multi-dimensional feature vector being configured further comprises configuring the multi-dimensional feature vector based in part on sampling a plurality of speed variables obtained from the GPS elements associated with the segment of the driving route.

8. A system for providing a prediction of a type of attribute located along a segment of a driving route based on one or more speed variation patterns obtained from Global Positioning System (GPS) elements, the system comprising:

at least one processor configured to;

(a) represent the segment of the driving route by a multi-dimensional feature vector capturing the one or more speed variation patterns; and

(b) input the multi-dimensional feature vector into a function for the type of attribute and in response to analyzing the multi-dimensional feature vector input in the function, determining the prediction indicating whether an object of the type of attribute is physically located at the segment of the driving route.

9. The system of claim 8, wherein prior to represent the segment, the processor is further configured to:

(c) retrieve a plurality of GPS elements; and

(d) for each GPS element that corresponds to one or more positions along the segment of the driving route, identify a portion of the GPS element recorded along the segment of the driving route to include in an input GPS set.

10. The system of claim 8, wherein the multi-dimensional feature vector being configured is based in part on one or more data points of the input GPS set.

11. The system of claim 8, wherein the attribute comprises a traffic light, a stop sign, a yield sign, a speed bump, a reduced speed zone, or mixed traffic signals.

12. The system of claim 9, wherein the at least one processor is configured to identify the GPS elements that pass along the segment of the driving route and the portions of the GPS elements that pass along the segment of the driving route recorded along the segment of the driving route by:

producing a topology from the GPS elements that pass along the segment of the driving route;

drawing a rectangle to encompass at least a portion of the segment of the driving route to define a boundary; and

including in the input GPS set the GPS data points located inside the boundary from the portions of the GPS elements that pass along the segment of the driving route.

13. The system of claim 8, wherein the multi-dimensional feature vector comprises an average value of M number of speed values sampled from each of the GPS elements associated with the segment of the driving route.

14. The system of claim 8, wherein the at least one processor is further configured to:

configure the multi-dimensional feature vector based in part on sampling a plurality of speed variables obtained from the GPS elements associated with the segment of the driving route.

15. A non-transitory computer-readable medium comprising executable code for providing a prediction of a type of attribute located along a segment of a driving route based on one or more speed variation patterns obtained from Global Positioning System (GPS) elements, that when executed by at least one processor causes the at least one processor to:

(a) represent the segment of the driving route by a multi-dimensional feature vector capturing the one or more speed variation patterns; and

(b) input the multi-dimensional feature vector into a function for the type of attribute and in response to analyzing the multi-dimensional feature vector input in the function, determining the prediction indicating whether an object of the type of attribute is physically located along the segment of the driving route.

16. The computer-readable medium of claim 15, wherein, prior to represent the segment, when the executable code is executed by the at least one processor further causes the at least one processor to:

(c) retrieve a plurality of GPS elements; and

(d) for each GPS element that corresponds to one or more positions along the segment of the driving route, identify a portion of the GPS element recorded along the segment of the driving route to include in an input GPS set.

17. The computer-readable medium of claim 15, wherein the multi-dimensional feature vector being configured is based in part on one or more data points of the input GPS set.

18. The computer-readable medium of claim 15, wherein the attribute comprises a traffic light, a stop sign, a yield sign, a speed bump, a reduced speed zone, or mixed traffic signals.

19. The computer-readable medium of claim 16, wherein when the executable code is executed by the at least one processor further causes the at least one processor to identify the GPS elements that pass along the segment of the driving route and the portions of the GPS elements that pass along the segment of the driving route recorded along the segment of the driving route by:

producing a topology from the GPS elements that pass along the segment of the driving route;

drawing a rectangle to encompass at least a portion of the segment of the driving route to define a boundary; and

including in the input GPS set the GPS data points located inside the boundary from the portions of the GPS elements that pass along the segment of the driving route.

20. The computer-readable medium of claim 15, wherein the multi-dimensional feature vector comprises an average value of M number of speed values sampled from each of the GPS elements associated with the segment of the driving route.

21. The computer readable medium of claim 15, wherein when the executable code is executed by the at least one computer processor further causes the at least one processor to:

configure the multi-dimensional feature vector based in part on sampling a plurality of speed variables obtained from the GPS elements associated with the segment of the driving route.