Pedestrian detection using gradient local binary patterns

Ning Jiang, Jiu Xu, Satoshi Goto

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In recent years, local pattern based features have attracted increasing interest in object detection and recognition systems. Local Binary Pattern (LBP) feature is widely used in texture classification and face detection. But the original definition of LBP is not suitable for human detection. In this paper, we propose a novel feature named gradient local binary patterns (GLBP) for human detection. In this feature, original 256 local binary patterns are reduced to 56 patterns. These 56 patterns named uniform patterns are used for generating a 56-bin histogram. And gradient value of each pixel is set as the weight which is always same in LBP based features in histogram calculation to computing the values in 56 bins for histogram. Experiments are performed on INRIA dataset, which shows the proposal GLBP feature is discriminative than histogram of orientated gradient (HOG), Semantic Local Binary Patterns (S-LBP) and histogram of template (HOT). In our experiments, the window size is fixed. That means the performance can be improved by boosting methods. And the computation of GLBP feature is parallel, which make it easy for hardware acceleration. These factors make GLBP feature possible for real-time pedestrian detection.

Original languageEnglish
Pages (from-to)1280-1287
Number of pages8
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE95-A
Issue number8
DOIs
Publication statusPublished - 2012 Aug

Fingerprint

Pedestrian Detection
Bins
Binary
Gradient
Object recognition
Face recognition
Textures
Pixels
Experiments
Semantics
Histogram
Hardware
Human Detection
Hardware Acceleration
Texture Classification
Face Detection
Object Detection
Object Recognition
Boosting
Object detection

Keywords

  • Feature extraction
  • Gradient local binary pattern
  • Local binary pattern
  • Pedestrian detection
  • Support vector machine

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics
  • Signal Processing

Cite this

Pedestrian detection using gradient local binary patterns. / Jiang, Ning; Xu, Jiu; Goto, Satoshi.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E95-A, No. 8, 08.2012, p. 1280-1287.

Research output: Contribution to journalArticle

@article{924f9c6eaaf5400ab3767aa643953162,
title = "Pedestrian detection using gradient local binary patterns",
abstract = "In recent years, local pattern based features have attracted increasing interest in object detection and recognition systems. Local Binary Pattern (LBP) feature is widely used in texture classification and face detection. But the original definition of LBP is not suitable for human detection. In this paper, we propose a novel feature named gradient local binary patterns (GLBP) for human detection. In this feature, original 256 local binary patterns are reduced to 56 patterns. These 56 patterns named uniform patterns are used for generating a 56-bin histogram. And gradient value of each pixel is set as the weight which is always same in LBP based features in histogram calculation to computing the values in 56 bins for histogram. Experiments are performed on INRIA dataset, which shows the proposal GLBP feature is discriminative than histogram of orientated gradient (HOG), Semantic Local Binary Patterns (S-LBP) and histogram of template (HOT). In our experiments, the window size is fixed. That means the performance can be improved by boosting methods. And the computation of GLBP feature is parallel, which make it easy for hardware acceleration. These factors make GLBP feature possible for real-time pedestrian detection.",
keywords = "Feature extraction, Gradient local binary pattern, Local binary pattern, Pedestrian detection, Support vector machine",
author = "Ning Jiang and Jiu Xu and Satoshi Goto",
year = "2012",
month = "8",
doi = "10.1587/transfun.E95.A.1280",
language = "English",
volume = "E95-A",
pages = "1280--1287",
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 - Pedestrian detection using gradient local binary patterns

AU - Jiang, Ning

AU - Xu, Jiu

AU - Goto, Satoshi

PY - 2012/8

Y1 - 2012/8

N2 - In recent years, local pattern based features have attracted increasing interest in object detection and recognition systems. Local Binary Pattern (LBP) feature is widely used in texture classification and face detection. But the original definition of LBP is not suitable for human detection. In this paper, we propose a novel feature named gradient local binary patterns (GLBP) for human detection. In this feature, original 256 local binary patterns are reduced to 56 patterns. These 56 patterns named uniform patterns are used for generating a 56-bin histogram. And gradient value of each pixel is set as the weight which is always same in LBP based features in histogram calculation to computing the values in 56 bins for histogram. Experiments are performed on INRIA dataset, which shows the proposal GLBP feature is discriminative than histogram of orientated gradient (HOG), Semantic Local Binary Patterns (S-LBP) and histogram of template (HOT). In our experiments, the window size is fixed. That means the performance can be improved by boosting methods. And the computation of GLBP feature is parallel, which make it easy for hardware acceleration. These factors make GLBP feature possible for real-time pedestrian detection.

AB - In recent years, local pattern based features have attracted increasing interest in object detection and recognition systems. Local Binary Pattern (LBP) feature is widely used in texture classification and face detection. But the original definition of LBP is not suitable for human detection. In this paper, we propose a novel feature named gradient local binary patterns (GLBP) for human detection. In this feature, original 256 local binary patterns are reduced to 56 patterns. These 56 patterns named uniform patterns are used for generating a 56-bin histogram. And gradient value of each pixel is set as the weight which is always same in LBP based features in histogram calculation to computing the values in 56 bins for histogram. Experiments are performed on INRIA dataset, which shows the proposal GLBP feature is discriminative than histogram of orientated gradient (HOG), Semantic Local Binary Patterns (S-LBP) and histogram of template (HOT). In our experiments, the window size is fixed. That means the performance can be improved by boosting methods. And the computation of GLBP feature is parallel, which make it easy for hardware acceleration. These factors make GLBP feature possible for real-time pedestrian detection.

KW - Feature extraction

KW - Gradient local binary pattern

KW - Local binary pattern

KW - Pedestrian detection

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84864743157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864743157&partnerID=8YFLogxK

U2 - 10.1587/transfun.E95.A.1280

DO - 10.1587/transfun.E95.A.1280

M3 - Article

AN - SCOPUS:84864743157

VL - E95-A

SP - 1280

EP - 1287

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

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

SN - 0916-8508

IS - 8

ER -