Detecting foliage using range data

• US 10,521,680 B2
• Filed: 11/08/2018
• Issued: 12/31/2019
• Est. Priority Date: 11/16/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Gerardo Castro, Marcos Paul, Kadetotad, Sneha, Liu, Dongran, Jain, Jinesh J
• Primary Examiner(s): Bekele, Mekonen T
• Application Number:
  US16/184,680
• Publication Number:
  US 20190080184A1
• Time in Patent Office: 418 Days
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 10/40 Extraction of image or video features
• 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

Abstract

A system for detecting and identifying foliage includes a tracking component, a tracking parameters component, and a classification component. The tracking component is configured to detect and track one or more features within range data from one or more sensors. The tracking parameters component is configured to determine tracking parameters for each of the one or more features. The tracking parameters include a tracking age and one or more of a detection consistency and a position variability. The classification component is configured to classify a feature of the one or more features as corresponding to foliage based on the tracking parameters.

Claims

1. A method for detecting foliage, the method comprising:

detecting a data object within range data captured by one or more sensors;

tracking the data object over time to determine tracking parameters for the data object, wherein the tracking parameters comprise;

a position variability indicating a standard deviation of a feature of the data object over time;

a detection consistency indicating how consistently the data object is detected over time; and

a tracking age indicating a time duration the data object has been tracked; and

classifying the data object as corresponding to foliage or non-foliage based on the tracking parameters.

2. The method of claim 1, wherein classifying the data object as corresponding to foliage comprises classifying based on one or more of:

the position variability of the data object exceeding a variability threshold;

the detection consistency of the data object falling below a consistency threshold;

or

the tracking age of the data object falling below an age threshold.

3. The method of claim 1, wherein classifying the data object as corresponding to non-foliage comprises classifying based on one or more of:

the position variability of the data object falling below a variability threshold;

the detection consistency of the data object exceeding a consistency threshold;

or

the tracking age of the data object exceeding an age threshold.

4. The method of claim 1, further comprising determining whether to avoid impacting an obstacle corresponding to the data object based on the classification of the data object.

5. The method of claim 1, further comprising determining a driving maneuver for a vehicle based on the classification of the data object and providing the driving maneuver to an automated driving/assistance system to be executed by the vehicle.

6. The method of claim 5, wherein determining the driving maneuver comprises determining an obstacle corresponding to a data object classified as foliage should be avoided with a lower priority than an obstacle corresponding to a data object classified as non-foliage.

7. The method of claim 1, wherein determining the position variability of the data object comprises determining the standard deviation for one or more of position or orientation of the data object.

8. The method of claim 1, wherein determining the detection consistency of the data object comprises determining a percent or ratio of frames in which the data object has been detected within a time period.

9. The method of claim 1, wherein determining the tracking age comprises determining how many frames the data object has been detected over the time duration.

10. A system comprising:

one or more sensors configured for detecting a data object; and

a processor that is programmable to execute instructions stored in non-transitory computer readable storage media, the instructions comprising;

detecting a data object within range data captured by the one or more sensors;

tracking the data object over time to determine tracking parameters for the data object, wherein the tracking parameters comprise;

a position variability indicating a standard deviation of a feature of the data object over time;

a detection consistency indicating how consistently the data object is detected over time; and

a tracking age indicating a time duration the data object has been tracked; and

classifying the data object as corresponding to foliage or non-foliage based on the tracking parameters.

11. The system of claim 10, wherein classifying the data object as corresponding to foliage comprises classifying based on one or more of:

the position variability of the data object exceeding a variability threshold;

the detection consistency of the data object falling below a consistency threshold;

or

the tracking age of the data object falling below an age threshold.

12. The system of claim 10, wherein the instructions further comprise determining whether to avoid impacting an obstacle corresponding to the data object based on the classification of the data object.

13. The system of claim 10, wherein determining the tracking parameters comprises one or more of:

determining the position variability of the data object by determining a standard deviation for one or more of position or orientation of the data object;

determining the detection consistency of the data object by determining a percent or ratio of frames in which the data object has been detected within a time period;

or

determining the tracking age of the data object by determining how many frames the data object has been detected over the time duration.

14. The system of claim 10, wherein the instructions further comprise determining a driving maneuver for a vehicle based on the classification of the data object as foliage or non-foliage and providing the driving maneuver to an automated driving/assistance system to be executed by the vehicle.

15. Non-transitory computer readable storage media storing instructions that, when executed by one or more processors, cause the one or more processors to:

detect a data object within range data captured by one or more sensors;

track the data object over time to determine tracking parameters for the data object, wherein the tracking parameters comprise;

a position variability indicating a standard deviation of a feature of the data object over time;

a detection consistency indicating how consistently the data object is detected over time; and

a tracking age indicating a time duration the data object has been tracked; and

classify the data object as corresponding to foliage or non-foliage based on the tracking parameters.

16. The non-transitory computer readable storage media of claim 15, wherein the instructions cause the one or more processors to classify the data object as corresponding to foliage based on one or more of:

the position variability of the data object exceeding a variability threshold;

the detection consistency of the data object falling below a consistency threshold;

or

the tracking age of the data object falling below an age threshold.

17. The non-transitory computer readable storage media of claim 15, wherein the instructions further cause the one or more processors to determine whether to avoid impacting an obstacle corresponding to the data object based on the classification of the data object.

18. The non-transitory computer readable storage media of claim 15, wherein the instructions cause the one or more processors to determine one or more of:

the position variability of the data object by determining a standard deviation for one or more of position or orientation of the data object;

the detection consistency of the data object by determining a percent or ratio of frames in which the data object has been detected within a time period;

or

the tracking age of the data object by determining how many frames the data object has been detected over the time duration.

19. The non-transitory computer readable storage media of claim 15, wherein the instructions further cause the one or more processors to determine a driving maneuver for a vehicle based on the classification of the data object as foliage or non-foliage and provide the driving maneuver to an automated driving/assistance system to be executed by the vehicle.

20. The non-transitory computer readable storage media of claim 19, wherein the instructions cause the one or more processors to determine the driving maneuver by determining an obstacle corresponding to a data object classified as foliage should be avoided with a lower priority than an obstacle corresponding to a data object classified as non-foliage.