US 11,810,373 B2
Cognitive function estimation device, learning device, and cognitive function estimation method
Shusaku Takamoto, Tokyo (JP)
Assigned to Mitsubishi Electric Corporation, Tokyo (JP)
Appl. No. 17/637,310
Filed by Mitsubishi Electric Corporation, Tokyo (JP)
PCT Filed Sep. 19, 2019, PCT No. PCT/JP2019/036686
§ 371(c)(1), (2) Date Feb. 22, 2022,
PCT Pub. No. WO2021/053780, PCT Pub. Date Mar. 25, 2021.
Prior Publication US 2022/0277570 A1, Sep. 1, 2022
Int. Cl. G06V 20/59 (2022.01); G06V 10/80 (2022.01); G06V 40/16 (2022.01); G06V 10/40 (2022.01); G06V 20/56 (2022.01); A61B 5/16 (2006.01); A61B 5/18 (2006.01)
CPC G06V 20/597 (2022.01) [A61B 5/162 (2013.01); A61B 5/18 (2013.01); G06V 10/40 (2022.01); G06V 10/806 (2022.01); G06V 20/56 (2022.01); G06V 40/168 (2022.01)] 10 Claims
OG exemplary drawing
 
1. A cognitive function estimation device, comprising:
processing circuitry
to acquire vehicle outside information on a situation around a vehicle;
to acquire face information on a face of a driver of the vehicle;
to acquire biological information of the driver;
to acquire vehicle information on the vehicle;
to extract a vehicle outside information feature amount for estimation of a cognitive function of the driver on a basis of the vehicle outside information acquired;
to extract, in accordance with the vehicle outside information feature amount extracted, a face information feature amount for the estimation of the cognitive function of the driver on a basis of the face information acquired;
to extract, in accordance with the vehicle outside information feature amount extracted, a to extract, in accordance with the vehicle outside information feature amount extracted, a biological information feature amount for the estimation of the cognitive function of the driver on a basis of the biological information acquired;
to extract, in accordance with the vehicle outside information feature amount extracted, a to extract, in accordance with the vehicle outside information feature amount extracted, a vehicle information feature amount for the estimation of the cognitive function of the driver on a basis of the vehicle information acquired; and
to estimate whether or not the cognitive function of the driver is low on a basis of a machine learning model, the vehicle outside information feature amount extracted, and at least one of the face information feature amount extracted, the biological information feature amount extracted, or the vehicle information feature amount extracted,
wherein, in response to extracting a first vehicle outside information feature amount, the processing circuitry extracts the face information feature amount without extracting the biological information feature amount, and
wherein, in response to extracting a second vehicle outside information feature amount, the processing circuitry extracts both of the face information feature amount and the biological information feature amount.