Systems and methods for detecting blood alcohol level
First Claim
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.
1 Assignment
0 Petitions
Accused Products
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.
-
Citations
20 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. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
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. - View Dependent Claims (11, 12, 13, 14, 15)
-
-
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. - View Dependent Claims (17, 18)
-
-
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.
-
Specification