Method for the target recognition of target objects

Patent metadata

Field	Value
Publication number	US-10168787-B2
Application number	US-201615266599-A
Country	US
Kind code	B2
Filing date	Sep 15, 2016
Priority date	Sep 15, 2015
Publication date	Jan 1, 2019
Grant date	Jan 1, 2019

Abstract

A method for the target recognition of target objects, in particular for the target recognition of the operating elements in a motor vehicle are disclosed herein. The method (and systems which incorporate the method) may employ various gaze tracking device, hand tracking devices, and combine inputs from the two based on a methodology for correlation.

First claim

What is claimed is:

1. A method for target recognition of target objects, comprising:
recognizing a directional vector of a viewing direction of a user and of a directional vector of an indicating device for at least one indicating gesture of a finger ( 8 . 1 ) of the user;
determining a first intersection (XBP; YBP) of the directional vector of the viewing direction with a first target plane (E0) located at a distance (z) from the user, and
determining a second intersection (XZP; YZP) of the directional vector of the indicating direction with the first target plane (E0),
wherein in response to the intersections (XBP; YBP) and (XZP; YZP) simultaneously being within a predetermined tolerance range T0 of a first target object (X0; Y0) arranged in the first target plane (E0), the intersections are associated with the first target object arranged in the first target plane, and
interval tolerance ranges (TBP; TZP) are formed by multiplying the coordinates of the intervals (XBP; YBP) and (XZP; YZP) with a correction factor (α, β, γ, δ),
wherein the correction factor (α, β, γ, δ) is defined by a spatial relationship of the fingertips and the eyes with the first target plane (E0).

2. The method according to claim 1 , wherein an association of a target object (X0/n; Y0/n) is reported acoustically, visually and/or tactilely to the user.

3. The method according to claim 1 , wherein a target object (X0/n; Y0/n) is recognized as a flat element of the target plane (E0).

4. The method according to claim 1 , wherein a target recognition for other target objects (Xn, Yn) is configured to be activated or deactivated by the association of the intersections (XBP; YBP) and (XZP; YZP) with the first target object (X0; Y0).

5. The method according to claim 1 , wherein the coordinates of the first target object (X0; Y0) serve as reference point for a spatial coordinate system.

6. The method according to claim 1 , wherein the first target plane (E0) serves as reference plane for at least one other target plane (En).

7. The method according to claim 1 , wherein a target object is associated with a virtual or real operating element.

8. The method according to claim 1 , wherein a movement pattern of a first intersection (XBP; YBP) and of a second intersection (XZP; YZP) detected on a target plane (E0/En) is associated with an input command.

9. A method for target recognition of target objects, comprising:
recognizing a directional vector of a viewing direction of a user and of a directional vector of an indicating device for at least one indicating gesture of a finger ( 8 . 1 ) of the user;
determining of a first intersection (XBP; YBP) of the directional vector of the viewing direction with a first target plane (E0) located at a distance (z) from the user, and
determining of a second intersection (XZP; YZP) of the directional vector of the indicating direction with the first target plane (E0),
wherein in response to sectional intersection of intersection tolerance ranges (TBP; TZP) formed in the target plane (E0) and of the intersections (XBP; YBP) and (XZP; YZP), and the sectional intersection tolerance ranges being with a predetermined sized plane containing the first target object (X0; Y0) arranged in the first target plane (E0), and
an interval tolerance ranges (TBP; TZP) are formed by multiplying the coordinates of the intervals (XBP; YBP) and (XZP; YZP) with a correction factor (α, β, γ, δ),
wherein the correction factor (α, β, γ, δ) is defined by a spatial relationship of the fingertips and the eyes with the first target plane (E0).

10. The method according to claim 9 , further comprising employing a self-learning algorithm to redefine the correction factor (α, β, γ, δ) based on an iterative process of using a system in which the method is implemented thereon.

11. The method according to claim 9 , wherein the correction factor (α, β, γ, δ) each correspond to a respective one of the intersection vectors.

12. The method according to claim 1 , further comprising:
using the determined intervals of the intersection coordinates from the coordinates of the first target object (X0; Y0) for correction in target recognition of other target objects.

13. An apparatus for target recognition of target objects, comprising:
a processor unit is configured to:
recognize a directional vector of a viewing direction of a user and of a directional vector of an indicating device for at least one indicating gesture of a finger ( 8 . 1 ) of the user;
determine a first intersection (XBP; YBP) of the directional vector of the viewing direction with a first target plane (E0) located at a distance (z) from the user, and
determine a second intersection (XZP; YZP) of the directional vector of the indicating direction with the first target plane (E0),
wherein in response to the intersections (XBP; YBP) and (XZP; YZP) simultaneously being within a predetermined tolerance range T0 of a first target object (X0; Y0) arranged in the first target plane (E0), the intersections are associated with the first target object arranged in the first target plane, and
interval tolerance ranges (TBP; TZP) are formed by multiplying the coordinates of the intervals (XBP; YBP) and (XZP; YZP) with a correction factor (α, β, γ, δ),
wherein the correction factor (α, β, γ, δ) is defined by a spatial relationship of the fingertips and the eyes with the first target plane (E0).

14. The apparatus according to claim 13 , wherein the processor unit is further configured to report an association of a target object (X0/n; Y0/n) acoustically, visually and/or tactilely to the user.

15. The apparatus according to claim 13 , wherein a target object (X0/n; Y0/n) is recognized as a flat element of the target plane (E0).

16. The apparatus according to claim 13 , wherein a target recognition for other target objects (Xn, Yn) is configured to be activated or deactivated by the association of the intersections (XBP; YBP) and (XZP; YZP) with the first target object (X0; Y0).

17. The apparatus according to claim 13 , wherein the coordinates of the first target object (X0; Y0) serve as reference point for a spatial coordinate system.

18. The apparatus according to claim 13 , wherein the first target plane (E0) serves as reference plane for at least one other target plane (En).

19. The apparatus according to claim 13 , wherein a movement pattern of a first intersection (XBP; YBP) and of a second intersection (XZP; YZP) detected on a target plane (E0/En) is associated with an input command.

20. The apparatus according to claim 13 , wherein the processor unit is further configured to use the determined intervals of the intersection coordinates from the coordinates of the first target object (X0; Y0) for correction in target recognition of other target objects.

Assignees

• Van Laack Alexander
• Morris Paul O
• Kirsch Oliver
• Visteon Global Tech Inc

Inventors

• Van Laack Alexander
• Morris Paul O
• Kirsch Oliver

Classifications

• G06K9/00335

  Physics · mapped topic

• G06F3/017 Primary

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G06F2203/0381

  Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer · CPC title

• G06F3/013

  Eye tracking input arrangements (G06F3/015 takes precedence) · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title