CLASSIFICATION WITH MODEL AND LOCALIZATION UNCERTAINTY

Yuri Feldman; Vadim Indelman

CLASSIFICATION WITH MODEL AND LOCALIZATION UNCERTAINTY

Yuri Feldman (Inventor), Vadim Indelman (Inventor)

Aerospace Engineering

Technion - Israel Institute of Technology

Research output: Patent

Abstract

Methods and systems are provided for fusing responses of a classifier that provides a model uncertainty measure, while accounting for viewpoint-dependent variations in object appearance and correlations in classifier responses, and accounting for localization uncertainty.

Original language	American English
Patent number	WO2020031188
IPC	G06K 9/ 62 A I
Priority date	8/08/18
State	Published - 13 Feb 2020

Cite this

@misc{e9d2ffeed8b64da1ab9ceab9debe8311,

title = "CLASSIFICATION WITH MODEL AND LOCALIZATION UNCERTAINTY",

abstract = "Methods and systems are provided for fusing responses of a classifier that provides a model uncertainty measure, while accounting for viewpoint-dependent variations in object appearance and correlations in classifier responses, and accounting for localization uncertainty.",

author = "Yuri Feldman and Vadim Indelman",

year = "2020",

month = feb,

day = "13",

language = "American English",

type = "Patent",

note = "WO2020031188; G06K 9/ 62 A I",

}

TY - PAT

T1 - CLASSIFICATION WITH MODEL AND LOCALIZATION UNCERTAINTY

AU - Feldman, Yuri

AU - Indelman, Vadim

PY - 2020/2/13

Y1 - 2020/2/13

N2 - Methods and systems are provided for fusing responses of a classifier that provides a model uncertainty measure, while accounting for viewpoint-dependent variations in object appearance and correlations in classifier responses, and accounting for localization uncertainty.

AB - Methods and systems are provided for fusing responses of a classifier that provides a model uncertainty measure, while accounting for viewpoint-dependent variations in object appearance and correlations in classifier responses, and accounting for localization uncertainty.

M3 - Patent

M1 - WO2020031188

ER -