User location system

• US 9,165,371 B2
• Filed: 03/15/2013
• Issued: 10/20/2015
• Est. Priority Date: 12/24/2012
• Status: Active Grant

• Current Assignee: Harman International Industries Incorporated (Samsung Electronics Co. Ltd.)
• Original Assignee: Harman International Industries Incorporated (Samsung Electronics Co. Ltd.)
• Inventors: Hampiholi, Vallabha Vasant, Lakkundi, Ravi
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US13/838,137
• Publication Number:
  US 20140270357A1
• Time in Patent Office: 949 Days
• Field of Search: 382/100, 382103-107, 382/154, 382/157, 382/162, 382/168, 382/173, 382/181, 382/199, 382/206, 382/209, 382/224, 382/232, 382/243, 382/254, 382/274, 382/276, 382285-295, 382/305, 382/312, 382/225, 280/735, 455/418
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/44 using image operators, e.g. filters, edge density metrics or local histograms
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

A user location system (ULS) can use images, such as video or still images, captured from at least one camera of an electronic device, such as a mobile device, to determine, via at least edge detection and image uniformity analysis, location of a user in an environment, such as in a cabin of a vehicle. The determined location of the user can then be used as an input to control at least one aspect of the environment. In the case of a vehicle, such input may be used to facilitate control of speed, safety features, climate, and/or audio playback, for example.

Claims

1. A method, comprising:

determining, via a processor, an edge density from one or more images of an environment, the one or more images provided from an electronic device of a user in the environment;

determining, via the processor, a location of the edge density;

determining, via the processor, a location of the user in the environment based at least on the determined location of the edge density;

determining, via the processor, uniformity of the one or more images;

determining further, via the processor, the location of the user in the environment based at least on the determined uniformity of the one or more images; and

outputting, via an interface communicatively coupled to the processor, to a control device of the environment, the determined location of the user in the environment.

2. The method of claim 1, where the determining of the location of the edge density is based at least on one or more irregularities in the one or more images.

3. The method of claim 1, where the determining of the location of the edge density is based at least on image segmentation.

4. The method of claim 1, comprising removing, via the processor, noise from the one or more images.

5. The method of claim 1, comprising enhancing, via the processor, the one or more images using histogram equalization.

6. The method of claim 5, where the enhancing of the one or more images is with respect to brightness of the one or more images.

7. The method of claim 6, comprising determining, via the processor, an image of the one or more images is captured by a rear-facing camera of the electronic device.

8. The method of claim 7, comprising analyzing, via the processor, with respect to brightness, a histogram of the histogram equalization.

9. The method of claim 8, comprising confirming, via the processor, the determined location of the user in the environment based at least on the analysis of the histogram.

10. The method of claim 1, where the environment is a cabin of a vehicle.

11. The method of claim 10, where the determined location of the user in the environment includes a seat position of the vehicle.

12. The method of claim 1, comprising transforming, via the processor, the one or more images from a spatial domain to a frequency domain, where the determining of the uniformity of the one or more images is based at least on the one or more transformed images.

13. The method of claim 12, where the determining of the uniformity of the one or more images is based at least on an amount of frequency domain coefficients over a threshold of the one or more transformed images.

14. The method of claim 1, comprising:

segmenting, via the processor, the one or more images into blocks;

analyzing, via the processor, the blocks; and

determining, via the processor, the uniformity of the one or more images based at least on the analysis of the blocks.

15. The method of claim 14, where the analysis of the blocks is based at least on entropy of the blocks, the entropy of the blocks being one or more differences of neighboring blocks.

16. The method of claim 14, where the analysis of the blocks is based at least on homogeneity of the blocks.

17. The method of claim 1, where the determining of the edge density in the one or more images is based at least on a Sobel operator, a Canny edge detector, a Roberts edge detector, a Prewitt edge detector, or any combination thereof.

18. A system, comprising:

a processor;

processor executable instructions stored in memory executable to;

determine an edge density and an edge density location in one or more images of a vehicle;

determine a location of a passenger in the vehicle based at least on the determined edge density and the determined edge density location; and

determine uniformity of the one or more images using one or more of an entropy calculation or a transformation of the one or more images from a spatial domain to a frequency domain; and

determine further the location of the passenger based at least on the determined uniformity of the one or more images; and

an interface operable to output to a control device of the vehicle, the determined location of the passenger.

19. The system of claim 18, where the determining of the location of the edge density is based at least on image segmentation.

20. A computer readable medium comprising instructions, the instructions executable to:

determine an edge density and an edge density location in a front-facing image of a user of an electronic device, the front-facing image provided by the electronic device;

determine a location of the user based at least on the determined edge density and the determined edge density location;

determine uniformity of the front-facing image using one or more of an entropy calculation or a transformation of the front-facing image from a spatial domain to a frequency domain;

determine the location of the user based at least on the determined uniformity of the front-facing image; and

confirm the location of the user based at least on brightness of a rear-facing image, the rear-facing image provided by the electronic device.