Rotation-invariant histogram of oriented gradients for target description

Derong Chen; Wenbin Wang; Bingtai Liu; Wei Jiang; Da Yu; Jiulu Gong

doi:10.11999/JEIT150546

Rotation-invariant histogram of oriented gradients for target description

Derong Chen, Wenbin Wang, Bingtai Liu, Wei Jiang, Da Yu, Jiulu Gong^*

^*Corresponding author for this work

School of Mechatronical Engineering

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

2 Citations (Scopus)

Abstract

A rotation-invariant feature descripts method called Rotation Invariant Histogram of Oriented Gradients (RI-HOG) is proposed for automatic target recognition. RI-HOG calculates gradient of image first, then the image window is divided into a set of un-overlapped annular regions, called sells, and the Histogram of Gradient (HoG) is used to calculate a feature vector for each cells. After that the HoG of each circle is accumulated to get the main angle of the target area, and then it is rotated due to the main angle to make a normalization of the main angle. At last, the HoG of each circle after rotating is linked to generate the rotation-invariant target feature vector. Experiment results show that target detection method using RI-HOG can find the target under arbitrary rotations. RI-HOG is a rotation-invariant target feature descriptor.

Original language	English
Pages (from-to)	21-28
Number of pages	8
Journal	Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology
Volume	38
Issue number	1
DOIs	https://doi.org/10.11999/JEIT150546
Publication status	Published - 1 Jan 2016

Keywords

Automatic target recognition
Feature description method
Histogram of Gradient (HoG)
Rotation invariant

Access to Document

10.11999/JEIT150546

Cite this

@article{6b657ba4e3744705a17c3294332272be,

title = "Rotation-invariant histogram of oriented gradients for target description",

abstract = "A rotation-invariant feature descripts method called Rotation Invariant Histogram of Oriented Gradients (RI-HOG) is proposed for automatic target recognition. RI-HOG calculates gradient of image first, then the image window is divided into a set of un-overlapped annular regions, called sells, and the Histogram of Gradient (HoG) is used to calculate a feature vector for each cells. After that the HoG of each circle is accumulated to get the main angle of the target area, and then it is rotated due to the main angle to make a normalization of the main angle. At last, the HoG of each circle after rotating is linked to generate the rotation-invariant target feature vector. Experiment results show that target detection method using RI-HOG can find the target under arbitrary rotations. RI-HOG is a rotation-invariant target feature descriptor.",

keywords = "Automatic target recognition, Feature description method, Histogram of Gradient (HoG), Rotation invariant",

author = "Derong Chen and Wenbin Wang and Bingtai Liu and Wei Jiang and Da Yu and Jiulu Gong",

year = "2016",

month = jan,

day = "1",

doi = "10.11999/JEIT150546",

language = "English",

volume = "38",

pages = "21--28",

journal = "Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology",

issn = "1009-5896",

publisher = "Science China Press",

number = "1",

}

TY - JOUR

T1 - Rotation-invariant histogram of oriented gradients for target description

AU - Chen, Derong

AU - Wang, Wenbin

AU - Liu, Bingtai

AU - Jiang, Wei

AU - Yu, Da

AU - Gong, Jiulu

PY - 2016/1/1

Y1 - 2016/1/1

N2 - A rotation-invariant feature descripts method called Rotation Invariant Histogram of Oriented Gradients (RI-HOG) is proposed for automatic target recognition. RI-HOG calculates gradient of image first, then the image window is divided into a set of un-overlapped annular regions, called sells, and the Histogram of Gradient (HoG) is used to calculate a feature vector for each cells. After that the HoG of each circle is accumulated to get the main angle of the target area, and then it is rotated due to the main angle to make a normalization of the main angle. At last, the HoG of each circle after rotating is linked to generate the rotation-invariant target feature vector. Experiment results show that target detection method using RI-HOG can find the target under arbitrary rotations. RI-HOG is a rotation-invariant target feature descriptor.

AB - A rotation-invariant feature descripts method called Rotation Invariant Histogram of Oriented Gradients (RI-HOG) is proposed for automatic target recognition. RI-HOG calculates gradient of image first, then the image window is divided into a set of un-overlapped annular regions, called sells, and the Histogram of Gradient (HoG) is used to calculate a feature vector for each cells. After that the HoG of each circle is accumulated to get the main angle of the target area, and then it is rotated due to the main angle to make a normalization of the main angle. At last, the HoG of each circle after rotating is linked to generate the rotation-invariant target feature vector. Experiment results show that target detection method using RI-HOG can find the target under arbitrary rotations. RI-HOG is a rotation-invariant target feature descriptor.

KW - Automatic target recognition

KW - Feature description method

KW - Histogram of Gradient (HoG)

KW - Rotation invariant

UR - http://www.scopus.com/inward/record.url?scp=84958037772&partnerID=8YFLogxK

U2 - 10.11999/JEIT150546

DO - 10.11999/JEIT150546

M3 - Article

AN - SCOPUS:84958037772

SN - 1009-5896

VL - 38

SP - 21

EP - 28

JO - Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology

JF - Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology

IS - 1

ER -

Rotation-invariant histogram of oriented gradients for target description

Abstract

Keywords

Access to Document

Other files and links

Cite this