Locally important pattern clustering code for pedestrian classification

Young Chul Lim; Minsung Kang

doi:10.1587/transfun.E98.A.1875

Locally important pattern clustering code for pedestrian classification

Young Chul Lim
, Minsung Kang

Division of Automotive Technology

Daegu Gyeongbuk Institute of Science and Technology

Research output: Contribution to journal › Article › peer-review

Abstract

In this letter, a local pattern coding scheme is proposed to reduce the dimensionality of feature vectors in the local ternary pattern. The proposed method encodes the ternary patterns into a binary pattern by clustering similar ternary patterns. The experimental results show that the proposed method outperforms the previous methods.

Original language	English
Pages (from-to)	1875-1878
Number of pages	4
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E98A
Issue number	8
DOIs	https://doi.org/10.1587/transfun.E98.A.1875
State	Published - 1 Aug 2015

Bibliographical note

Publisher Copyright:
Copyright © 2015 The Institute of Electronics, Information and Communication Engineers.

Keywords

Clustering code
Feature extraction
Local binary pattern
Local ternary pattern
Pedestrian classification

Access to Document

10.1587/transfun.E98.A.1875

Cite this

@article{9cde84f80d0c4b25b8d163154cc24019,

title = "Locally important pattern clustering code for pedestrian classification",

abstract = "In this letter, a local pattern coding scheme is proposed to reduce the dimensionality of feature vectors in the local ternary pattern. The proposed method encodes the ternary patterns into a binary pattern by clustering similar ternary patterns. The experimental results show that the proposed method outperforms the previous methods.",

keywords = "Clustering code, Feature extraction, Local binary pattern, Local ternary pattern, Pedestrian classification",

author = "Lim, \{Young Chul\} and Minsung Kang",

note = "Publisher Copyright: Copyright {\textcopyright} 2015 The Institute of Electronics, Information and Communication Engineers.",

year = "2015",

month = aug,

day = "1",

doi = "10.1587/transfun.E98.A.1875",

language = "English",

volume = "E98A",

pages = "1875--1878",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "8",

}

TY - JOUR

T1 - Locally important pattern clustering code for pedestrian classification

AU - Lim, Young Chul

AU - Kang, Minsung

PY - 2015/8/1

Y1 - 2015/8/1

N2 - In this letter, a local pattern coding scheme is proposed to reduce the dimensionality of feature vectors in the local ternary pattern. The proposed method encodes the ternary patterns into a binary pattern by clustering similar ternary patterns. The experimental results show that the proposed method outperforms the previous methods.

AB - In this letter, a local pattern coding scheme is proposed to reduce the dimensionality of feature vectors in the local ternary pattern. The proposed method encodes the ternary patterns into a binary pattern by clustering similar ternary patterns. The experimental results show that the proposed method outperforms the previous methods.

KW - Clustering code

KW - Feature extraction

KW - Local binary pattern

KW - Local ternary pattern

KW - Pedestrian classification

UR - https://www.scopus.com/pages/publications/84938932067

U2 - 10.1587/transfun.E98.A.1875

DO - 10.1587/transfun.E98.A.1875

M3 - Article

AN - SCOPUS:84938932067

SN - 0916-8508

VL - E98A

SP - 1875

EP - 1878

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 8

ER -

Locally important pattern clustering code for pedestrian classification

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this