Methods and systems for marker identification

• US 10,095,928 B2
• Filed: 12/20/2016
• Issued: 10/09/2018
• Est. Priority Date: 12/22/2015
• Status: Active Grant

• Current Assignee: Worldviz LLC
• Original Assignee: Worldviz LLC
• Inventors: Beall, Andrew C., Pusch, Matthias
• Primary Examiner(s): Wang, Carol
• Application Number:
  US15/385,557
• Publication Number:
  US 20170177939A1
• Time in Patent Office: 658 Days
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• CPC Class Codes: G06V 20/20 in augmented reality scenes

Abstract

A marker tracking system configured to detect light patterns (e.g., infrared light patterns) generated by one or more markers is described. A given marker is configured with a code which identifies the marker in a motion tracking camera field of view. Motion tracking camera(s) record the emitted infrared light and are configured to directly, or in conjunction with an associated computing device, computationally distinguish a given marker with high accuracy and efficiently.

Claims

1. A marker identification system comprising:

a motion tracking camera, wherein the motion tracking camera is configured to detect infrared light;

a marker, the marker configured to emit a pattern of infrared light pulses that encodes 5 or more binary bits;

a computing system comprising;

a computing device; and

non-transitory media that stores instructions readable by the computing device, that when executed by the computing device, cause the computing system to;

record via the motion tracking camera a plurality of images including at least a first recorded image set, a second recorded image set, a third recorded image set, a fourth recorded image set, and a fifth recorded image set;

identify, within a given recorded image of the first recorded image set, a cluster of adjacent pixels corresponding to infrared light emitted from the marker;

determine a count of how many saturated pixels are within a given identified cluster of adjacent pixels of a given recorded image of the first recorded image set;

determine a highest count of saturated pixels from respective counts of saturated pixels of respective given identified clusters of respective given recorded images of the first recorded image set;

calculate a radius for a circular perimeter by at least multiplying the highest count of saturated pixels by a first factor;

identify a first area, bounded by the circular perimeter, of a first image of the first recorded image set encompassing a highest number of infrared light pixels within a cluster of adjacent pixels;

for pixels within the first area, identify a first set of pixels having a highest intensity as compared to other sets of pixels in the first area, wherein the first set of pixels has a count equal to the highest count of saturated pixels;

excluding the first set of pixels, determine a sum of infrared light intensities of the first area;

determine respective sum of infrared light intensities for respective areas in the remaining one or more images of the first recorded image set;

based at least in part on the determined respective sum of infrared light intensities of the respective areas of respective images of the first recorded image set, assign a binary value to the first recorded image set;

determine respective sum of infrared light intensities for respective areas in at least the second recorded image set, the third recorded image set, the fourth recorded image set, and the fifth recorded image set;

based at least in part on the determined respective sum of infrared light intensities for respective areas in the second recorded image set, the third recorded image set, the fourth recorded image set, and the fifth recorded image set, assign a respective binary value to the respective second recorded image set, third recorded image set, fourth recorded image set, and fifth recorded image set;

compare the respective assigned binary values to the configured pattern of infrared light pulses of the marker; and

based at least in part on the comparison of the respective assigned binary values to the configured pattern of infrared light pulses of the marker, identify the marker.

2. The marker identification system of claim 1, wherein a position in space of the marker in a first recorded image corresponds to a center of a respective area of the first recorded image bounded by the circular perimeter.

3. The marker identification system of claim 1, wherein a respective recorded image set comprises multiple frames.

4. The marker identification system of claim 1, wherein the marker is user configurable to emit a plurality of infrared light pulses patterns corresponding to a plurality of binary code sets.

5. The marker identification system of claim 1, further comprising a plurality of markers configured to be attached to a user to enable at least in part, the marker identification system to determine a corresponding orientation of the user.

6. The marker identification system of claim 1, wherein the marker is configured to be attached to a user to enable at least in part, the marker identification system to determine a corresponding position of the user.

7. The system of claim 1, wherein the instructions are further configured to cause the computing device to determine if the respective sum of infrared light intensities for the respective areas of respective images of the recorded image sets correspond to a set of consecutive images of medium intensities.

8. The system of claim 1, wherein the instructions are further configured to cause the computing device to determine if the respective sum of infrared light intensities for the respective areas of respective images of the recorded image sets corresponds to a set of consecutive images of low intensities followed by a set of consecutive images of high intensities.

9. A system comprising:

a motion tracking camera, wherein the motion tracking camera is configured to detect infrared light;

a marker, the marker configured to emit a binary pattern of infrared light pulses that encodes one or more binary bits;

a computing system comprising;

a computing device; and

non-transitory media that stores instructions readable by the computing device, that when executed by the computing device, cause the computing device to;

record via the motion tracking camera a plurality of images;

identify, within a given recorded image, a cluster of adjacent pixels corresponding to infrared light emitted from the marker;

determine a count of how many saturated pixels are within a given identified cluster of adjacent pixels of a given recorded image;

determine a highest count of saturated pixels from respective counts of saturated pixels of respective given identified clusters of respective given recorded images;

calculate a radius for a circular perimeter by at least multiplying the highest count of saturated pixels by a first factor;

identify a first area, bounded by the circular perimeter, of a first image of the plurality of images encompassing a highest number of infrared light pixels within a cluster of adjacent pixels;

for pixels within the first area, identify a first set of pixels having a highest intensity as compared to other sets of pixels in the first area, wherein the first set of pixels has a count equal to the highest count of saturated pixels;

excluding the first set of pixels, determine a sum of infrared light intensities of the first area;

determine respective sum of infrared light intensities for respective areas in the remaining one or more images of the plurality of images; and

based at least in part on the determined respective sum of infrared light intensities of the respective areas of respective images of the plurality of images,

assign a binary value to the plurality of images.

10. The system of claim 9, wherein the instructions are further configured to cause the computing device to determine if the respective sum of infrared light intensities for the respective areas of the respective images of the plurality of images correspond to a set of consecutive images of medium intensities.

11. The system of claim 9, wherein the instructions are further configured to cause the computing device to determine if the respective sum of infrared light intensities for the respective areas of the respective images of the plurality of images corresponds to a set of consecutive images of low intensities followed by a set of consecutive images of high intensities.

12. The system of claim 9, wherein a position in space of the marker in a given image corresponds to a center of a respective area bounded by the circular perimeter.

13. The system of claim 9, wherein the marker is user configurable to generate a plurality of distinguishable infrared light pulses patterns corresponding to a binary code set.

14. The system of claim 9, further comprising a plurality of markers, wherein the plurality of markers are configured to be attached to a user to enable at least in part, the system to determine a corresponding orientation of the user.

15. The system of claim 9, wherein the marker is configured to be attached to a user to enable at least in part, the system to determine a corresponding position of the user.

16. The system of claim 9, the system further configured to combine the binary value with other assigned binary values to a respective subsequent plurality of recorded images to define a binary code set.

17. The system of claim 9, the system further configured to:

combine the binary value with other assigned binary values to a respective subsequent plurality of recorded images to define a binary code set;

compare the defined binary code set to configured binary values of the marker; and

based at least in part on the comparison of the defined binary code set to the configured binary values of the marker, identify the marker.

18. A method of marker identification comprising:

identifying, within a given recorded image of a plurality of images captured by a camera, a cluster of adjacent pixels corresponding to infrared light emitted from a marker;

determining a count of how many saturated pixels are within a given identified cluster of adjacent pixels of a given recorded image of the plurality of images;

determining a highest count of saturated pixels from respective counts of saturated pixels of respective given identified clusters of respective given recorded images;

calculating a radius for a circular perimeter by at least multiplying the highest count of saturated pixels by a first factor;

identifying a first area, bounded by the circular perimeter, of a first image of the plurality of images encompassing a highest number of infrared light pixels within a cluster of adjacent pixels;

for pixels within the first area, identifying a first set of pixels having a highest intensity as compared to other sets of pixels in the first area, wherein the first set of pixels has a count equal to the highest count of saturated pixels;

excluding the first set of pixels, determining a sum of infrared light intensities of the first area;

determining respective sum of infrared light intensities for respective areas in the remaining one or more images of the plurality of images; and

based at least in part on the determined respective sum of infrared light intensities of the respective areas of respective images of the plurality of images,

assigning a binary value to the plurality of images.

19. The method of claim 18, the method further comprising:

determining if the respective sum of infrared light intensities for the respective areas of the respective images of the plurality of images correspond to a set of consecutive images of medium intensities.

20. The method of claim 18, the method further comprising:

determining if the respective sum of infrared light intensities for the respective areas of the respective images of the plurality of images corresponds to a set of consecutive images of low intensities followed by a set of consecutive images of high intensities.