DISTRACTION DETECTION APPARATUS, DISTRACTION DETECTION METHOD, AND COMPUTER PROGRAM

• US 20100241021A1
• Filed: 06/03/2010
• Published: 09/23/2010
• Est. Priority Date: 09/19/2008
• Status: Active Grant

• Current Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Terada, Yoshihisa, Nakada, Tour, MORIKAWA, Koji
• Granted Patent: US 8,239,015 B2
• Time in Patent Office: Days
• US Class Current: 600/544
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/374 Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The distraction detection apparatus includes: an electroencephalogram detection section for detecting an electroencephalogram signal of a driver; an arousal level estimation section for retaining a first rule of mapping parameter values of an electroencephalogram signal to arousal levels, and estimating an arousal level based on the detected electroencephalogram signal and the first rule; an attention allocation estimation section for retaining a second rule of mapping parameter values of an electroencephalogram signal to attention allocations, and estimating an attention allocation based on the detected electroencephalogram signal and the second rule; a driver state estimation section for retaining a third rule of deriving an amount of attention from an arousal level and an attention allocation, estimating an amount of attention of the driver paid to driving based on the estimated arousal level and attention allocation and the third rule, and classifying a state of the driver into a normal state, a state of reduced attention, or a state of reduced arousal level; and an output section for performing an intervention for the driver based on a result of classification by the driver state classification section.

Claims

1. A distraction detection apparatus comprising:

an electroencephalogram detection section for detecting an electroencephalogram signal of a driver;

an arousal level estimation section for retaining a first rule of mapping parameter values of an electroencephalogram signal to arousal levels, and estimating an arousal level based on the detected electroencephalogram signal and the first rule;

an attention allocation estimation section for retaining a second rule of mapping parameter values of an electroencephalogram signal to attention allocations, and estimating an attention allocation based on the detected electroencephalogram signal and the second rule;

a driver state estimation section for retaining a third rule of deriving an amount of attention from an arousal level and an attention allocation, estimating an amount of attention of the driver paid to driving based on the estimated arousal level and attention allocation and the third rule, and classifying a state of the driver into a normal state, a state of reduced attention, or a state of reduced arousal level; and

an output section for performing an intervention for the driver based on a result of classification by the driver state classification section.

2. The distraction detection apparatus of claim 1, wherein,

the first rule maps frequency intensities of an electroencephalogram signal to arousal levels;

and

the arousal level estimation section calculates a frequency intensity of the detected electroencephalogram signal, and estimates the arousal level based on a result of calculation and the first rule.

3. The distraction detection apparatus of claim 2, wherein,

a plurality of groups are previously defined in the arousal level estimation section, each group being defined based on a frequency intensity of an electroencephalogram signal;

and

the arousal level estimation section classifies frequency intensities of the detected electroencephalogram signal as calculated at a plurality of points in time, each frequency intensity being classified into one of the plurality of groups, and estimates the arousal level based on at least one frequency intensity that is classified into one of the plurality of groups and on the first rule.

4. The distraction detection apparatus of claim 1, wherein,

the second rule maps amplitudes of event-related potentials of an electroencephalogram signal to attention allocations;

and

the attention allocation estimation section calculates an amplitude of an event-related potential of the detected electroencephalogram signal, and estimates the attention allocation based on a result of calculation and the second rule.

5. The distraction detection apparatus of claim 4, wherein,

a plurality of groups are previously defined in the attention allocation estimation section, each group being defined based on an amplitude of an event-related potential;

and

the attention allocation estimation section classifies amplitudes of the event-related potential of the detected electroencephalogram signal as calculated at a plurality of points in time, each amplitude of the event-related potential being classified into one of the plurality of groups, and estimates the attention allocation based on at least one amplitude of the event-related potential that is classified into one of the plurality of groups and on the second rule.

6. The distraction detection apparatus of claim 1 further comprising an external environment detection section for detecting an external environment, wherein

the driver state estimation section has a rule of deriving a required amount of attention based on a detected external environment, and compares the amount of attention paid to driving as estimated by the driver state estimation section against a required amount of attention derived by applying the rule to the external environment detected by the external environment detection section, thus determining whether the driver is paying attention to complexity in the external environment.

7. The distraction detection apparatus of claim 1, wherein the driver state estimation section calculates an amount of attention of the driver paid to driving by multiplying the arousal level estimated by the arousal level estimation section and an attention allocation to driving estimated by the attention allocation estimation section.

8. The distraction detection apparatus of claim 1, wherein,

the attention allocation estimation section has a rule defining a relationship between an attention allocation to a task other than driving and an attention allocation to driving, and is capable of estimating an attention allocation to driving based on an attention allocation to the task other than driving and the rule;

and

the driver state estimation section calculates an amount of attention of the driver paid to driving by multiplying the arousal level estimated by the arousal level estimation section and the attention allocation to driving estimated by the attention allocation estimation section.

9. A distraction detection method, comprising the steps of:

providing a first rule of mapping parameter values of an electroencephalogram signal to arousal levels;

providing a second rule of mapping parameter values of an electroencephalogram signal to attention allocations;

providing a third rule of deriving an amount of attention from an arousal level and an attention allocation;

detecting an electroencephalogram signal of a driver;

estimating an arousal level based on the detected electroencephalogram signal and the first rule;

estimating an attention allocation based on the detected electroencephalogram signal and the second rule;

estimating an amount of attention of the driver paid to driving based on the estimated arousal level and attention allocation and the third rule, and classifying a state of the driver into a normal state, a state of reduced attention, or a state of reduced arousal level; and

performing an intervention for the driver based on a result of classification by the classifying step.

10. A computer program stored on a non-transitory computer-readable medium, the computer program being executed by a computer and causing the computer to execute the steps of:

receiving an electroencephalogram signal of a driver;

estimating an arousal level based on the detected electroencephalogram signal of the driver and a first rule of mapping parameter values of an electroencephalogram signal to arousal levels;

estimating an attention allocation based on the detected electroencephalogram signal and a second rule of mapping parameter values of an electroencephalogram signal to attention allocations;

estimating an amount of attention of the driver paid to driving based on the estimated arousal level and attention allocation and a third rule of deriving an amount of attention from an arousal level and an attention allocation, and classifying a state of the driver into a normal state, a state of reduced attention, or a state of reduced arousal level; and

performing an intervention for the driver based on a result of classification by the classifying step.