Global and local light detection in optical sensor systems

Patent metadata

Field	Value
Publication number	US-9430095-B2
Application number	US-201414162440-A
Country	US
Kind code	B2
Filing date	Jan 23, 2014
Priority date	Jan 23, 2014
Publication date	Aug 30, 2016
Grant date	Aug 30, 2016

Abstract

Global and local light detection techniques in optical sensor systems are described. In one or more implementations, a global lighting value is generated that describes a global lighting level for a plurality of optical sensors based on a plurality of inputs received from the plurality of optical sensors. An illumination map is generated that describes local lighting conditions of respective ones of the plurality of optical sensors based on the plurality of inputs received from the plurality of optical sensors. Object detection is performed using an image captured using the plurality of optical sensors along with the global lighting value and the illumination map.

First claim

What is claimed is:

1. A method comprising:
generating a global lighting value that describes a global lighting level for a plurality of optical sensors based on a plurality of inputs received from the plurality of optical sensors, the global lighting value determined based on a comparison of a histogram indicating pixel intensity in the image to pre-trained histograms, each of the pre-trained histograms representative of a class indicative of a respective global lighting value;
generating an illumination map that describes local lighting conditions of respective ones of the plurality of optical sensors based on the plurality of inputs received from the plurality of optical sensors; and
performing object detection using an image captured using the plurality of optical sensors along with the global lighting value and the illumination map.

2. A method as described in claim 1 , further comprising recognizing a gesture as a result of the performing, the gesture usable to initiate one or more functions of a computing device that is configured to perform the generating of the global lighting value, the generating of the illumination map, and the performing of the object detection.

3. A method as described in claim 1 , further comprising calculating the plurality of pre-trained histograms by assigning histograms of a plurality of training images to respective said classes.

4. A method as described in claim 3 , wherein the respective said classes are specified by a user.

5. A method as described in claim 3 , wherein the respective said classes are specified automatically and without user intervention.

6. A method as described in claim 1 , wherein the generating of the illumination map includes selecting portion of values obtained from neighboring ones of a subset of the optical sensors and collecting intensity values for the sensors.

7. A method as described in claim 6 , wherein the portion is defined using a Bresenham circle.

8. A method as described in claim 6 , wherein the generating of the illumination map includes measuring an arc-length using the portions such that each of the values of the optical sensors on the arc are brighter than a value of an optical sensor at a center of the portion.

9. A method as described in claim 1 , wherein the generating of the illumination map includes use of a blur kernel.

10. A method as described in claim 1 , wherein the plurality of optical sensors are configured in accordance with a sensor-in-pixel configuration of a display device of a computing device.

11. A system comprising:
a plurality of optical sensors; and
modules implemented at least partially in hardware, the one or more modules configured to implement:
a global lighting module configured to generate a global lighting value that describes a global lighting level for the plurality of optical sensors based on a plurality of inputs received from the plurality of optical sensors, the global lighting value generated by comparing a histogram indicating intensity of pixels in the image to a plurality of pre-trained histograms of intensity corresponding to different global lighting values;
a local lighting module configured to generate an illumination map that describes local lighting conditions of respective ones of the plurality of optical sensors based on the plurality of inputs received from the plurality of optical sensors; and
an object detection module configured to perform object detection using an image captured using the plurality of optical sensors along with the global lighting value and the illumination map.

12. A system as described in claim 11 , further comprising a gesture module configured to recognize a gesture as a result of the performance of the object detection.

13. A system as described in claim 11 , wherein the local lighting module is configured to generate the illumination map at least in part by selecting a portion of values obtained from neighboring ones of a subset of the optical sensors and collecting intensity values for the sensors.

14. A system as described in claim 13 , wherein the generating of the illumination map includes measuring an arc-length using the portions such that each of the values of the optical sensors on the arc are brighter than a value of an optical sensor at a center of the portion.

15. A system as described in claim 11 , wherein the generating of the illumination map includes use of a blur kernel.

16. A computing device comprising;
a processing system; and
one or more computer readable storage media comprising instructions that, when executed by the processing system, cause the computing device to perform operations for object detection including:
generating a global lighting value that describes a global lighting level for a plurality of optical sensors based on a plurality of inputs received from the plurality of optical sensors, the global lighting value determined based on a comparison of a histogram indicating pixel intensity in the image to pre-trained histograms of intensity corresponding to different global lighting values;
generating an illumination map that describes local lighting conditions of respective ones of the plurality of optical sensors based on the plurality of inputs received from the plurality of optical sensors; and
performing object detection using an image captured using the plurality of optical sensors along with the global lighting value and the illumination map.

17. A computing device as described in claim 16 , wherein the instructions, when executed by the processing system, further cause the computing device to perform operations including: recognizing a gesture as a result of the performing, the gesture usable to initiate one or more functions of the computing device.

18. A computing device as described in claim 16 , wherein the generating of the illumination map includes selecting portion of values obtained from neighboring ones of a subset of the optical sensors and collecting intensity values for the sensors.

19. A computing device as described in claim 18 , wherein the portion is defined using a Bresenham circle.

20. A computing device as described in claim 18 , wherein the generating of the illumination map includes measuring an arc-length using the portions such that each of the values of the optical sensors on the arc are brighter than a value of an optical sensor at a center of the portion.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Pradeep Vivek
• Wang Liang
• Sala Pablo
• Cabrera-Cordon Luis Eduardo
• Bathiche Steven Nabil

Classifications

• G06F3/042

  by opto-electronic means · CPC title

• G06K9/4642

  Physics · mapped topic

• G06F3/0416 Primary

  Control or interface arrangements specially adapted for digitisers · CPC title

• G06F3/0425 Primary

  using a single imaging device like a video camera for tracking the absolute position of a single or a plurality of objects with respect to an imaged reference surface, e.g. video camera imaging a display or a projection screen, a table or a wall surface, on which a computer generated image is displayed or projected (tracking a projected light spot to determine a position on a display surface G06F3/0386) · CPC title