Method and system for gesture identification based on object tracing

• US 9,721,343 B2
• Filed: 01/15/2016
• Issued: 08/01/2017
• Est. Priority Date: 10/08/2012
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: PixArt Imaging Incorporated
• Inventors: Huang, Yu-Hao, Hsu, En-Feng
• Primary Examiner(s): Abdi, Amara
• Application Number:
  US14/996,777
• Publication Number:
  US 20160133024A1
• Time in Patent Office: 564 Days
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 23/56 provided with illuminating means

Abstract

A method and system provide light to project to an operation space so that a received image from the operation space will include, if an object is in the operation space, a bright region due to the reflection of light by the object, and identify a gesture according to the variation of a barycenter position, an average brightness, or an area of the bright region in successive images, for generating a corresponding command. Only simple operation and calculation is required to detect the motion of an object moving in the X, Y, or Z axis of an image, for identifying a gesture represented by the motion of the object.

Claims

1. A method for gesture identification based on object tracing, the method comprising:

projecting light to an operation space;

capturing, by an image sensor, images from the operation space to generate a plurality of successive images;

detecting a bright region in each of the successive images, wherein a sensible range of pixel intensity of said each image is divided into predetermined levels and pixels having brightness greater than an intensity threshold among the predetermined levels are determined as the bright region;

performing object tracing based on a variation of a barycenter position of the bright region without recognizing a shape of the bright region; and

comparing a result of the object tracing based on the variation of the barycenter position with predetermined gesture definitions to identify an operation gesture in an X axis and a Y axis.

2. The method of claim 1, further comprising:

normalizing a size of the successive images.

3. The method of claim 1, further comprising:

calculating an average brightness of the bright region by calculating a sum of the brightness of pixels contained in the bright region and dividing the sum by a number of the pixels contained in the bright region; and

evaluating a variation of the average brightness to identify an operation gesture in a Z axis.

4. The method of claim 1, further comprising:

calculating an area of the bright region by calculating a number of pixels contained in the bright region; and

evaluating a variation of the area to identify an operation gesture in a Z axis.

5. The method of claim 1, further comprising:

switching intensity of the light projected to the operation space.

6. The method of claim 1, further comprising:

switching a projecting angle of the light projected to the operation space.

7. The method of claim 1, further comprising:

switching an operation distance between the operation space and the image sensor.

8. The method of claim 1, further comprising:

capturing a part of one of the successive images to achieve an effect as of switching an operation distance between the operation space and the image sensor.

9. A system for gesture identification based on object tracing, the system comprising:

a controlled light-emitting unit configured to project light to an operation space;

an image sensor configured to capture images from the operation space to generate a plurality of successive images; and

a processor connected to the light-emitting unit and the image sensor, wherein the processor is configured to

receive the successive images from the image sensor,

detect a bright region in each of the successive images, wherein a sensible range of pixel intensity of said each image is divided into predetermined levels and pixels having brightness greater than an intensity threshold among the predetermined levels are determined as the bright region,

perform object tracing based on a variation of a barycenter position of the bright region without recognizing a shape of the bright region, and

compare a result of the object tracing based on the variation of the barycenter position with predetermined gesture definitions to identify an operation gesture in an X axis and a Y axis.

10. The system of claim 9, wherein the image sensor is configured to normalize a size of the successive images.

11. The system of claim 9, wherein the processor is further configured to

calculate an average brightness of the bright region by calculating a sum of the brightness of pixels contained in the bright region and dividing the sum by a number of the pixels contained in the bright region, and

evaluate a variation of the average brightness to identify an operation gesture in a Z axis.

12. The system of claim 9, wherein the processor is further configured to

calculate an area of the bright region by calculating a number of pixels contained in the bright region, and

evaluate a variation of the area to identify an operation gesture in a Z axis.

13. The system of claim 9, wherein the processor is configured to control the image sensor to switch a viewing angle of the image sensor.

14. The system of claim 9, wherein the processor is configured to control the image sensor to switch a light sensitivity of the image sensor.

15. The system of claim 9, wherein the processor is configured to control the light-emitting unit to switch intensity of the light to be projected to the operation space.

16. The system of claim 9, wherein the processor is configured to control the light-emitting unit to switch a light-emitting angle of the light-emitting unit.

17. The system of claim 9, wherein the processor is configured to identify the operation gesture based on the variation of the barycenter position in the successive images without computing depth information of the successive images.