IP Library Granted Patent US 12,633,141
Granted Patent B2
US 12,633,141 · App. 18/381,452 · Granted May 19, 2026

Prediction device and method for driver microsleep based on eye closure duration

Inventors: Chisato Imamura (Osaka, JP); Takayoshi Koyama (Osaka, JP); Wataru Nakai (Tokyo, JP); Soichi Kimura (Osaka, JP)
Assignee: PANASONIC AUTOMOTIVE SYSTEMS CO., LTD.
G06V20/597B60W40/08G06V10/98G06V40/166G06V40/171G06V40/19B60W2040/0827G07C5/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,633,141
App. No.
18/381,452
Granted
May 19, 2026
Kind
B2
Abstract

A prediction device includes a state detector that detects a state related to sleepiness of a driver; an eye-closure duration detector that detects an eye-closure duration of the driver; and a microsleep predictor that predicts that the driver is in the microsleep state, on conditions that the state detector detects the state related to the sleepiness of the driver and that the eye-closure duration detector detects the eye-closure duration that is no shorter than a first duration and no longer than a second duration.

Claims (45)

1 . A vehicle that predicts that a driver is in a microsleep state, the vehicle comprising:

a biosensor that detects biological information of the driver;

an image sensor that captures image information of the driver;

a state detecting circuit that detects, based on the biological information detected by the biosensor, a state related to sleepiness of the driver;

an eye-closure duration detecting circuit that detects an eye-closure duration of the driver based on the image information captured by the image sensor;

a microsleep predicting circuit that predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the state related to the sleepiness of the driver and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than a first duration and no longer than a second duration; and

an execution determining circuit that determines that the microsleep predicting circuit is to perform prediction about the microsleep state of the driver when the state detecting circuit detects the state related to the sleepiness of the driver, and determines that the microsleep predicting circuit is not to perform prediction about the microsleep state of the driver when the state detecting circuit does not detect the state related to the sleepiness of the driver.

2 . The vehicle according to claim 1 ,

wherein the first duration is 0.5 seconds and the second duration is 3 seconds.

3 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects life log information about life of the driver as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the life log information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

4 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects facial-feature movement information indicating a movement of a facial feature of the driver as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the facial-feature movement information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

5 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects head movement information indicating a movement of a head of the driver as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the head movement information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

6 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects in-vehicle information indicating a state inside the vehicle as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the in-vehicle information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

7 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects vital information on the driver as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the vital information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

8 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects vehicle state information indicating state of the vehicle as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the vehicle state information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

9 . The vehicle according to claim 1 ,

wherein the state detecting circuit detects body movement information indicating a body movement of the driver as the state related to the sleepiness of the driver, and

the microsleep predicting circuit predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the body movement information and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than the first duration and no longer than the second duration.

10 . A vehicle that predicts that a driver is in a microsleep state, the vehicle comprising:

a biosensor that detects biological information of the driver;

an image sensor that captures image information of the driver;

a state detecting circuit that detects, based on the biological information detected by the biosensor, a state related to sleepiness of the driver;

an eye-closure duration detecting circuit that detects an eye-closure duration of the driver based on the image information captured by the image sensor;

a microsleep predicting circuit that predicts that the driver is in the microsleep state, on conditions that the state detecting circuit detects the state related to the sleepiness of the driver and that the eye-closure duration detecting circuit detects the eye-closure duration that is no shorter than a first duration and no longer than a second duration; and

an erroneous-prediction situation detecting circuit that detects an erroneous prediction situation that affects prediction about the microsleep state of the driver made by the microsleep predicting circuit,

wherein the microsleep predicting circuit is not to perform prediction about the microsleep state of the driver when the erroneous-prediction situation detecting circuit detects the erroneous prediction situation.

11 . A prediction method of predicting that a driver of a vehicle is in a microsleep state, the prediction method comprising:

detecting, by a biosensor of the vehicle, biological information of the driver;

capturing, by an image sensor of the vehicle, image information of the driver;

detecting, by a state detecting circuit of the vehicle and based on the biological information detected by the biosensor, a state related to sleepiness of the driver;

detecting, by an eye-closure duration detecting circuit of the vehicle, an eye-closure duration of the driver based on the image information captured by the image sensor; and

predicting, by a microsleep predicting circuit of the vehicle, that the driver is in the microsleep state, on conditions that the state related to the sleepiness of the driver is detected by the state detecting circuit and that the eye-closure duration that is no shorter than a first duration and no longer than a second duration is detected by the eye-closure duration detecting circuit; and

determining, by an execution determining circuit of the vehicle, that the microsleep predicting circuit is to perform prediction about the microsleep state of the driver when the state detecting circuit detects the state related to the sleepiness of the driver, and determines that the microsleep predicting circuit is not to perform prediction about the microsleep state of the driver when the state detecting circuit does not detect the state related to the sleepiness of the driver.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 6, 2024
From: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
To: PANASONIC AUTOMOTIVE SYSTEMS CO., LTD.
Reel/Frame 068328/0764 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 15, 2024
From: IMAMURA, CHISATO; KOYAMA, TAKAYOSHI; NAKAI, WATARU; KIMURA, SOICHI
To: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
Reel/Frame 067102/0673 →
Priority Claims (1)
JP 2022-171478 · Oct 26, 2022 · national
Continuity (1)
Related Publication 20240144702A1 · May 2, 2024
References Cited (14)
US 20170345276A1 · Stoltz · 2017 [cited by examiner]
US 20200276978A1 · Satou · 2020 [cited by examiner]
JP 3852294B2 · 2006 [cited by applicant]
JP 2009048605A · 2009 [cited by applicant]
JP 2010155072A · 2010 [cited by applicant]
JP 2012068841A · 2012 [cited by applicant]
JP 5007975B2 · 2012 [cited by applicant]
JP 2018508870A · 2018 [cited by applicant]
WO 2020184581A1 · 2020 [cited by applicant]
WO 2022113275A1 · 2022 [cited by applicant]
Caffier, P.P., Erdmann, U. & Ullsperger, P. Experimental evaluation of eye-blink parameters as a drowsiness measure. Eur J Appl Physiol 89, 319-325 (2003). (Year: 2003). [cited by examiner]
Y. Dong, Z. Hu, K. Uchimura and N. Murayama, “Driver Inattention Monitoring System for Intelligent Vehicles: A Review,” in IEEE Transactions on Intelligent Transportation Systems, vol. 12, No. 2, pp. 596-614, Jun. 2011.… [cited by examiner]
A. Chowdhury, R. Shankaran, M. Kavakli and M. M. Haque, “Sensor Applications and Physiological Features in Drivers, Drowsiness Detection: A Review,” in IEEE Sensors Journal, vol. 18, No. 8, pp. 3055-3067, 15 Apr. 15, 20… [cited by examiner]
Office Action dated Feb. 24, 2026 issued in Japanese Patent Application No. 2022-171478 along with an English translation. [cited by applicant]