Systems and methods for detecting blood alcohol level

• US 9,002,067 B2
• Filed: 03/28/2013
• Issued: 04/07/2015
• Est. Priority Date: 03/28/2013
• Status: Active Grant

• Current Assignee: Bytelogics Incorporated
• Original Assignee: Bytelogics Incorporated
• Inventors: Siilats, Keith
• Primary Examiner(s): Carter, Aaron W
• Assistant Examiner(s): Zohrabyan, Narek
• Application Number:
  US13/852,070
• Publication Number:
  US 20140294245A1
• Time in Patent Office: 740 Days
• Field of Search: None
• US Class Current: 382/107
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: A61B 5/0082 adapted for particular medical purposes
• CPC Class Codes: A61B 5/4845 Toxicology, e.g. by detection of alcohol, drug or toxic products A61B5/4848 takes precedence
• CPC Class Codes: A61B 5/4863 Measuring or inducing nystagmus
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30041 Eye; Retina; Ophthalmic
• 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 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

Provided are systems and methods for detecting blood alcohol level. The system for detecting blood alcohol level comprises a receiver configurable to receive an input video of an eye of a user and a processor configurable to: stabilize the input video; analyze the input video; based on the analysis, detect a horizontal gaze nystagmus level; and based on the horizontal gaze nystagmus level, determine an equivalent blood alcohol level of the user. The system outputs data associated with the equivalent blood alcohol level via an interface. Additionally, the system comprises a screen configurable to display a moving object. The input video captures eye movements of the user following the moving object. To illuminate the eye of the user, the system may generate red light.

Claims

1. A system for detecting a blood alcohol level, the system comprising:

a receiver configurable to receive an input video of an eye of a user;

a processor configurable to;

stabilize the input video, the stabilizing including;

detecting an eye area in the input video;

creating a mask to mask the eye area in a plurality of frames of the input video, thereby separating the input video into a masked portion and an unmasked portion;

using the unmasked portion of the input video to stabilize the input video and to detect a shaking movement of the receiver; and

applying the shaking movement to the mask;

analyze the input video, the analysis including identifying a pupil of the user in the mask;

based on the analysis, detect a horizontal gaze nystagmus level, the detection including;

estimating a velocity of the pupil between the plurality of frames of the input video;

based on the estimation, identifying one or more shifts in the velocity; and

based on the one or more shifts, determining the horizontal gaze nystagmus level according to a lookup table;

based on the horizontal gaze nystagmus level, determine an equivalent blood alcohol level of the user; and

an interface to output data associated with the equivalent blood alcohol level.

2. The system of claim 1, wherein the determining of the equivalent blood alcohol level is adjusted based on one or more calibration tests associated with the user.

3. The system of claim 1, further comprising a light source configurable to generate red light to illuminate the eye of the user.

4. The system of claim 1, wherein the input video is 30 seconds long.

5. The system of claim 1, further comprising a screen configurable to display a moving object, wherein the input video captures eye movements of the user following the moving object.

6. The system of claim 5, wherein the moving object moves from one side of the screen to the opposite side of the screen, the move being repeated at least twice.

7. The system of claim 1, further comprising generating safety recommendations regarding one or more actions of the user based on the output equivalent blood alcohol level, the one or more actions including driving, alcohol consumption, and operating heavy equipment.

8. A system for detecting a blood alcohol level, the system comprising:

a receiver configurable to receive an input video of an eye of a user;

a processor configurable to;

stabilize the input video;

analyze the input video;

based on the analysis, detect a horizontal gaze nystagmus level;

based on the horizontal gaze nystagmus level, determine an equivalent blood alcohol level of the user; and

an interface to output data associated with the equivalent blood alcohol level; and

wherein the stabilizing includes;

using a compressed sensing algorithm and thereby separating the input video into a low-rank component and a sparse component; and

using the sparse component as the eye area.

9. A system for detecting a blood alcohol level, the system comprising:

a receiver configurable to receive an input video of an eye of a user;

a processor configurable to;

stabilize the input video;

analyze the input video;

based on the analysis, detect a horizontal gaze nystagmus level;

based on the horizontal gaze nystagmus level, determine an equivalent blood alcohol level of the user; and

an interface to output data associated with the equivalent blood alcohol level; and

wherein the stabilizing includes;

detecting an eye area in the input video;

using a compressed sensing algorithm and thereby separating the input video into a low-rank component and a sparse component;

creating a mask to mask area outside the eye area in a plurality of frames of the sparse component video; and

using the masked sparse component as the eye area.

10. A method for detecting a blood alcohol level, the method comprising:

receiving an input video of an eye of a user;

detecting an eye area in the input video;

creating a mask to mask the eye area in a plurality of frames of the input video, thereby creating a masked portion and an unmasked portion;

stabilizing the input video based on the unmasked portion of the input video, thereby detecting a shaking movement of the receiver; and

applying the shaking movement to the mask;

identifying a pupil of the user in the mask;

based on the identification, estimating a velocity of the pupil between the plurality of frames of the input video;

based on the estimation, identifying one or more shifts in the velocity;

based on the one or more shifts, determining the horizontal gaze nystagmus level;

based on the horizontal gaze nystagmus level, determining an equivalent blood alcohol level of the user; and

outputting the equivalent blood alcohol level to a screen.

11. The method of claim 10, further comprising adjusting the equivalent blood alcohol level based on one or more calibration tests associated with the user.

12. The method of claim 10, wherein the input video is captured in a red light provided by a light source.

13. The method of claim 10, further comprising displaying, on the screen, a moving object, wherein the input video captures eye movements of the user following the moving object.

14. The method of claim 13, wherein the moving object moves from one side of the screen to the opposite side of the screen, the move being repeated at least twice.

15. The method of claim 10, further comprising providing, based on the output equivalent blood alcohol level, safety recommendations associated with one or more actions of the user, the one or more actions including driving, alcohol consumption, and operating heavy equipment.

16. A method for detecting a blood alcohol level, the method comprising:

receiving an input video of an eye of a user;

stabilizing the input video;

analyzing the input video;

based on the analysis, detecting a horizontal gaze nystagmus level;

based on the horizontal gaze nystagmus level, determining an equivalent blood alcohol level of the user;

outputting the equivalent blood alcohol level to a screen; and

wherein the stabilizing includes;

separating the input video into a low rank component and a sparse component using a compressed sensing algorithm; and

using the sparse component as the eye.

17. The method of claim 16, wherein the analysis includes identifying a pupil of the user in the mask.

18. The method of claim 17, wherein the detection of the horizontal gaze nystagmus level includes:

estimating a velocity of the pupil between the plurality of frames of the input video;

based on the estimation, identifying one or more shifts in the velocity; and

based on the one or more shifts, determining the horizontal gaze nystagmus level.

19. A non-transitory machine-readable medium comprising instructions that, when executed, perform the following operations:

display, on a screen, a moving object;

receive an input video of an eye of a user, wherein the input video captures the eye of the user following the moving object;

detect an eye area in the input video;

create a mask to mask the eye area in a plurality of frames of the input video, thereby creating an unmasked portion and a masked portion of the input video;

based on the unmasked portion of the input video, stabilize the input video to detect a shaking movement of the receiver;

apply the shaking movement to the mask;

identify a pupil of the user in the mask;

based on the identification, estimate a velocity of the pupil between the plurality of frames of the input video;

based on the estimation, identify one or more shifts in the velocity;

determine a horizontal gaze nystagmus level associated with the one or more shifts in a lookup table;

based on the horizontal gaze nystagmus level, detect an equivalent blood alcohol level; and

output the equivalent blood alcohol level to the screen.

20. A non-transitory machine-readable medium comprising instructions that, when executed, perform the following operations:

display, on a screen, a moving object;

receive an input video of an eye of a user, wherein the input video captures the eye of the user following the moving object;

detect an eye area in the input video;

separate the video into a low rank component and a sparse component;

erase pixels outside the detected eye area from the sparse component to generate a masked sparse component;

identify a pupil of the user in the masked sparse component;

based on the identification, estimate a velocity of the pupil between the plurality of frames of the input video;

based on the estimation, identify one or more shifts in the velocity;

determine a horizontal gaze nystagmus level associated with the one or more shifts in a lookup table;

based on the horizontal gaze nystagmus level, detect an equivalent blood alcohol level; and

output the equivalent blood alcohol level to the screen.