Method and device for detecting the gait of a pedestrian for a portable terminal

• US 9,286,689 B2
• Filed: 01/14/2014
• Issued: 03/15/2016
• Est. Priority Date: 07/14/2011
• Status: Active Grant

• Current Assignee: Bayerische Motoren Werke AG
• Original Assignee: Bayerische Motoren Werke AG
• Inventors: Isert, Carsten, Gusenbauer, Dominik, Aubeck, Ferenc
• Primary Examiner(s): Akhavannik, Hadi
• Application Number:
  US14/154,602
• Publication Number:
  US 20140169628A1
• Time in Patent Office: 791 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01C 22/006 Pedometers
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A method and system for recognizing a pedestrian'"'"'s step is provided for a portable terminal. The portable terminal has an acquisition unit. In an image of a sequence of images acquired by the acquisition unit, an object is, in each case, detected which represents at least a part of a foot, a shoe, and/or a leg. The position of the object is determined in the respective image, and a pedestrian'"'"'s step is recognized as a function of a position change of the object between at least two images of the sequence of images.

Claims

1. A method of operating a portable terminal for recognizing a pedestrians step, the method comprising the acts of:

acquiring, via an acquisition unit of the portable terminal operated by the pedestrian, a sequence of images of the pedestrian;

detecting, in each image of the sequence of images, an object representing at least a part of a foot, a shoe, and/or a leg of the pedestrian;

determining a position of the object in the respective image;

recognizing a step of the pedestrian as a function of a position change of the object between at least two images of the sequence of images; and

signaling to the pedestrian at least one of a current position and a determined route of the portable terminal based in part on the recognized step.

2. The method according to claim 1, wherein the object is detected as a function of a similarity comparison of a specified model with the respective image.

3. The method according to claim 2, wherein the model is determined as a function of an image detail of one acquired image, which one acquired image comprises at least a tip of the foot and/or shoe of the pedestrian.

4. The method according to claim 1, wherein a course of the position of the object is determined for the sequence of images, and the step of the pedestrian is recognized as a function of the course.

5. The method according to claim 2, wherein

the image is subdivided into several image details,

the similarity comparison with the model is carried out for each of the several image details, and

the position of the object is determined as a function of the image detail having a greatest similarity to model.

6. The method according to claim 3, wherein

the image is subdivided into several image details,

the similarity comparison with the model is carried out for each of the several image details, and

the position of the object is determined as a function of the image detail having a greatest similarity to model.

7. The method according to claim 5, wherein

a respective image has a matrix of pixels,

for one central pixel respectively, representing a center point of the respective image detail, one comparison value is determined that represents a measurement for the similarity of the model to the respective image detail, and

as a function of the determined comparison values, the position of the object is determined.

8. The method according to claim 6, wherein

a respective image has a matrix of pixels,

for one central pixel respectively, representing a center point of the respective image detail, one comparison value is determined that represents a measurement for the similarity of the model to the respective image detail, and

as a function of the determined comparison values, the position of the object is determined.

9. The method according to claim 7, wherein

as a function of the determined comparison values, a maximal comparison value is determined, and

when the maximal comparison value falls below a specified limit value, the model is adapted.

10. The method according to claim 8, wherein

as a function of the determined comparison values, a maximal comparison value is determined, and

when the maximal comparison value falls below a specified limit value, the model is adapted.

11. The method according to claim 7, wherein

pixels of the image have one color value respectively for a specified quantity of color channels, and

for at least one portion of the quantity of color channels, the determined comparison values are determined for the respective color channel.

12. The method according to claim 9, wherein

pixels of the image have one color value respectively for a specified quantity of color channels, and

for at least one portion of the quantity of color channels, the determined comparison values are determined for the respective color channel.

13. The method according to claim 7, wherein pixels of the image each have a gray value from a specified quantity of gray values, and

wherein before the similarity comparison,

an average gray value of the image is determined as a function of the gray values of at least a portion of the pixels, and

the image is converted to a binary image in which respective pixels assume only one of two possible gray values such that, as a function of the average value and the gray value of the respective pixel, the respective pixel has a specified first or second gray value.

14. The method according to claim 9, wherein pixels of the image each have a gray value from a specified quantity of gray values, and

wherein before the similarity comparison,

an average gray value of the image is determined as a function of the gray values of at least a portion of the pixels, and

the image is converted to a binary image in which respective pixels assume only one of two possible gray values such that, as a function of the average value and the gray value of the respective pixel, the respective pixel has a specified first or second gray value.

16. The method of claim 1, wherein said signaling to the pedestrian comprises displaying, on a display of the portable terminal, the at least one of the current position and the determined route of the portable terminal based in part on the recognized step.

17. The system of claim 1, wherein the control unit is operatively configured to signal to the pedestrian by displaying, on a display of the portable terminal, the at least one of the current position and the determined route of the portable terminal based in part on the recognized step.

15. A system for recognizing a pedestrians step, comprising:

a portable terminal operated by a pedestrian, wherein the portable terminal comprises;

an image acquisition unit operatively configured to acquire a sequence of images;

an image processing unit operatively configured to, in each case, detect an object in acquired images which represents at least part of a foot, a shoe, and/or a leg of the pedestrian;

a control unit operatively configured to;

determine a position of the object in a respective image,

recognize a step of the pedestrian as a function of a position change of the object in at least two images of the sequence of images, and

signal to the pedestrian at least one of a current position and a determined route of the portable terminal based in part on the recognized step.