Parameterized model of 2d articulated human shape

Michael J Black; Oren Freifeld; Alexander W Weiss; Matthew M Loper; Peng Guan

Parameterized model of 2d articulated human shape

Michael J Black (Inventor), Oren Freifeld (Inventor), Alexander W Weiss (Inventor), Matthew M Loper (Inventor), Peng Guan (Inventor)

Department of Computer Science

Research output: Patent

Abstract

The parameters of the estimated 2D body can be used to discriminatively predict 3D body shape using a learned mapping approach. The prediction framework can be used to estimate/predict the 3D shape of a person from a cluttered video sequence and/or from several snapshots taken with a digital camera or a cell phone.

Original language	English
Patent number	US2016275693
IPC	G06T 17/ 20 A I
Priority date	12/02/16
State	Published - 22 Sep 2016

Cite this

@misc{dec989edfa7e42749a6b380330e29610,

title = "Parameterized model of 2d articulated human shape",

abstract = "The parameters of the estimated 2D body can be used to discriminatively predict 3D body shape using a learned mapping approach. The prediction framework can be used to estimate/predict the 3D shape of a person from a cluttered video sequence and/or from several snapshots taken with a digital camera or a cell phone.",

author = "Black, {Michael J} and Oren Freifeld and Weiss, {Alexander W} and Loper, {Matthew M} and Peng Guan",

year = "2016",

month = sep,

day = "22",

language = "English",

type = "Patent",

note = "US2016275693; G06T 17/ 20 A I",

}

TY - PAT

T1 - Parameterized model of 2d articulated human shape

AU - Black, Michael J

AU - Freifeld, Oren

AU - Weiss, Alexander W

AU - Loper, Matthew M

AU - Guan, Peng

PY - 2016/9/22

Y1 - 2016/9/22

N2 - The parameters of the estimated 2D body can be used to discriminatively predict 3D body shape using a learned mapping approach. The prediction framework can be used to estimate/predict the 3D shape of a person from a cluttered video sequence and/or from several snapshots taken with a digital camera or a cell phone.

AB - The parameters of the estimated 2D body can be used to discriminatively predict 3D body shape using a learned mapping approach. The prediction framework can be used to estimate/predict the 3D shape of a person from a cluttered video sequence and/or from several snapshots taken with a digital camera or a cell phone.

M3 - Patent

M1 - US2016275693

ER -

Parameterized model of 2d articulated human shape

Abstract

Fingerprint

Cite this