IDENTIFICATION DEVICE, IDENTIFICATION METHOD, AND RECORDING MEDIUM RECORDING IDENTIFICATION PROGRAM

• US 20170316255A1
• Filed: 04/10/2017
• Published: 11/02/2017
• Est. Priority Date: 04/28/2016
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Inventors: ARATA, KOJI
• Granted Patent: US 10,255,485 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/96 Management of image or video recognition tasks
• CPC Class Codes: G06V 20/593 Recognising seat occupancy
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G06V 40/107 Static hand or arm
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

An identification device includes an inputter which receives image information of a person photographed by a camera, and a controller which identifies the person and detects parts, which are at least a head and hands, of the person based on the image information, thereby identifying a motion of the person based on the identified person, the detected parts, and a motion model in which a motion of a person is registered for every person, and outputs the identified motion of the person.

Claims

1. An identification device comprising:

an inputter which receives image information of a person photographed by a camera; and

a controller which

identifies the person,

detects parts being at least a head and hands, of the person based on the image information, thereby identifying a motion of the person based on the identified person, the detected parts, and a motion model in which a motion of a person is registered for every person, and

outputs the identified motion of the person.

2. The identification device according to claim 1, wherein

the controller

detects a skeleton position of the person based on the image information,

identifies a motion of the person based on the detected skeleton position,

outputs the identified motion of the person,

generates a motion model based on the identified person, the detected skeleton position, and the identified motion of the person, and

stores the generated motion model.

3. The identification device according to claim 1, wherein

the controller

determines whether or not a skeleton position is detectable based on the image information,

in a case of determination that the skeleton position is undetectable, identifies the motion of the person based on the identified person, the detected parts, and the motion model and outputs the identified motion of the person, and

in a case of determination that the skeleton position is detectable, identifies a motion of the person based on the detected skeleton position and outputs the identified motion of the person.

4. The identification device according to claim 3, wherein

the controller

further determines whether or not the motion model is available in a case of the determination that the skeleton position is undetectable, and

identifies the motion of the person based on the identified person, the detected parts, and the motion model and outputs the identified motion of the person, in a case of determination that the motion model is available.

5. An identification method comprising:

receiving image information of a person photographed by a camera;

performing identification of the person and detection of parts being at least a head and hands, of the person based on the image information; and

identifying a motion of the person based on the identified person, the detected parts, and a motion model in which a motion of a person is registered for every person.

6. A recording medium that is a non-transitory computer readable recording medium recording an identification program which is executed in a computer, the computer identifying a posture of a person, and which makes the computer execute:

receiving image information of a person photographed by a camera;

performing identification of the person and detection of parts being at least a head and hands, of the person based on the image information; and

identifying a motion of the person based on the identified person, the detected parts, and a motion model in which a motion of a person is registered for every person.