Occupant modeling device, occupant modeling method, and occupant modeling program

Patent metadata

Field	Value
Publication number	US-11210497-B2
Application number	US-201916578686-A
Country	US
Kind code	B2
Filing date	Sep 23, 2019
Priority date	Sep 27, 2018
Publication date	Dec 28, 2021
Grant date	Dec 28, 2021

Abstract

An occupant modeling device includes: an acquisition section acquiring an image by imaging a region where there is a probability that a face of an occupant is present; a model fitting section generating a model of the face based on a first image acquired by the acquisition section; a tracking section adapting the model to a second image acquired after the first image; a determination section determining correctness of a facial part position included in the second image to which the model is adapted, by using learned information obtained through learning based on correct information and incorrect information regarding the facial part position; and a processing section determining whether a process in the tracking section is to be continuously executed or a process in the model fitting section is to be executed again according to a determination result in the determination section.

First claim

What is claimed is:

1. An occupant modeling device comprising:
at least one processor configured to implement:
an acquisition section that acquires an image obtained by imaging a region in which there is a probability that a face of an occupant is present in a vehicle;
a model fitting section that generates a model of the face based on a first image acquired by the acquisition section;
a tracking section that adapts the model to a second image acquired after the first image acquired by the acquisition section;
a determination section that determines correctness of a facial part position included in the second image to which the model is adapted, by using learned information obtained through learning based on correct information and incorrect information regarding the facial part position of the face; and
a processing section that determines whether a process in the tracking section is to be continuously executed or a process in the model fitting section is to be executed again according to a determination result in the determination section,
wherein the determination section executes a first determination of determining correctness of a position of an eye of the face as the facial part position and a second determination of determining correctness of positions of a plurality of facial parts other than an eye included in the face.

2. The occupant modeling device according to claim 1 , wherein
the determination section specifies a facial part position of the second image based on information recognized as a facial part position through the process in the tracking section, and determines correctness with the learned information.

3. An occupant modeling method comprising:
an acquisition step of acquiring an image obtained by imaging a region in which there is a probability that a face of an occupant is present in a vehicle;
a model fitting step of generating a model of the face based on a first image acquired in the acquisition step;
a tracking step of adapting the model to a second image acquired after the first image acquired in the acquisition step;
a determination step of determining correctness of a facial part position included in the second image, by using learned information obtained through learning based on correct information and incorrect information regarding the facial part position of the face; and
a processing step of determining whether a process in the tracking step is to be continuously executed or a process in the model fitting step is to be executed again according to a determination result in the determination step,
wherein the determining step determines the correctness of a facial part by executing a first determination of determining correctness of a position of an eye of the face as the facial part position and a second determination of determining correctness of positions of a plurality of facial parts other than an eye included in the face.

4. An occupant modeling program stored on a non-transitory computer readable medium causing a computer to execute:
an acquisition step of acquiring an image obtained by imaging a region in which there is a probability that a face of an occupant is present in a vehicle;
a model fitting step of generating a model of the face based on a first image acquired in the acquisition step;
a tracking step of adapting the model to a second image acquired after the first image acquired in the acquisition step;
a determination step of determining correctness of a facial part position included in the second image, by using learned information obtained through learning based on correct information and incorrect information regarding the facial part position of the face; and
a processing step of determining whether a process in the tracking step is to be continuously executed or a process in the model fitting step is to be executed again according to a determination result in the determination step;
wherein the determining step determines the correctness of a facial part by executing a first determination of determining correctness of a position of an eye of the face as the facial part position and a second determination of determining correctness of positions of a plurality of facial parts other than an eye included in the face.

Assignees

• Aisin Seiki

Inventors

• Osuga Shin
• Kato Takashi
• Yamada Yoshiyuki
• Hattori Tetsuya

Classifications

• G06T2207/20121

  Active appearance model [AAM] · CPC title

• B60R21/01552

  detecting position of specific human body parts, e.g. face, eyes or hands · CPC title

• G06T2207/10048

  Infrared image · CPC title

• G06V20/597

  Recognising the driver's state or behaviour, e.g. attention or drowsiness · CPC title

• B60R21/01538

  for image processing, e.g. cameras or sensor arrays · CPC title