Designing a boosted classifier on riemannian manifolds

Fatih Porikli; Oncel Tuzel; Peter Meer

doi:10.1007/978-3-319-22957-7_13

Designing a boosted classifier on riemannian manifolds

Fatih Porikli, Oncel Tuzel, Peter Meer

School of Engineering, Electrical & Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Chapter

6 Scopus citations

Abstract

It is not trivial to build a classifier where the domain is the space of symmetric positive definite matrices such as non-singular region covariance descriptors lying on a Riemannian manifold. This chapter describes a boosted classification approach that incorporates the a priori knowledge of the geometry of the Riemannian space. The presented classifier incorporated into a rejection cascade and applied to single image human detection task. Results on INRIA and DaimlerChrysler pedestrian datasets are reported.

Original language	English (US)
Title of host publication	Riemannian Computing in Computer Vision
Publisher	Springer International Publishing
Pages	281-301
Number of pages	21
ISBN (Electronic)	9783319229577
ISBN (Print)	9783319229560
DOIs	https://doi.org/10.1007/978-3-319-22957-7_13
State	Published - Jan 1 2015

All Science Journal Classification (ASJC) codes

Engineering(all)
Computer Science(all)
Mathematics(all)

Access to Document

10.1007/978-3-319-22957-7_13

Cite this

@inbook{584f9bd478334145bcd2a780a4115a81,

title = "Designing a boosted classifier on riemannian manifolds",

abstract = "It is not trivial to build a classifier where the domain is the space of symmetric positive definite matrices such as non-singular region covariance descriptors lying on a Riemannian manifold. This chapter describes a boosted classification approach that incorporates the a priori knowledge of the geometry of the Riemannian space. The presented classifier incorporated into a rejection cascade and applied to single image human detection task. Results on INRIA and DaimlerChrysler pedestrian datasets are reported.",

author = "Fatih Porikli and Oncel Tuzel and Peter Meer",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.",

year = "2015",

month = jan,

day = "1",

doi = "10.1007/978-3-319-22957-7_13",

language = "English (US)",

isbn = "9783319229560",

pages = "281--301",

booktitle = "Riemannian Computing in Computer Vision",

publisher = "Springer International Publishing",

}

TY - CHAP

T1 - Designing a boosted classifier on riemannian manifolds

AU - Porikli, Fatih

AU - Tuzel, Oncel

AU - Meer, Peter

PY - 2015/1/1

Y1 - 2015/1/1

N2 - It is not trivial to build a classifier where the domain is the space of symmetric positive definite matrices such as non-singular region covariance descriptors lying on a Riemannian manifold. This chapter describes a boosted classification approach that incorporates the a priori knowledge of the geometry of the Riemannian space. The presented classifier incorporated into a rejection cascade and applied to single image human detection task. Results on INRIA and DaimlerChrysler pedestrian datasets are reported.

AB - It is not trivial to build a classifier where the domain is the space of symmetric positive definite matrices such as non-singular region covariance descriptors lying on a Riemannian manifold. This chapter describes a boosted classification approach that incorporates the a priori knowledge of the geometry of the Riemannian space. The presented classifier incorporated into a rejection cascade and applied to single image human detection task. Results on INRIA and DaimlerChrysler pedestrian datasets are reported.

UR - http://www.scopus.com/inward/record.url?scp=84957031335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957031335&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-22957-7_13

DO - 10.1007/978-3-319-22957-7_13

M3 - Chapter

AN - SCOPUS:84957031335

SN - 9783319229560

SP - 281

EP - 301

BT - Riemannian Computing in Computer Vision

PB - Springer International Publishing

ER -

Designing a boosted classifier on riemannian manifolds

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this