A study on the feature matching performance of randomized trees

Yong Tian Wang; Jing Dun Lin; Jing Chen; Jun Wei Guo; Wei Liu; Kang Xue

A study on the feature matching performance of randomized trees

Yong Tian Wang^*, Jing Dun Lin, Jing Chen, Jun Wei Guo, Wei Liu, Kang Xue

^*Corresponding author for this work

School of Optics and Photonics

Beijing Institute of Technology

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

4 Citations (Scopus)

Abstract

In order to improve the augmented reality systems, is presented an evaluation of the randomized tree algorithm for augmented reality feature matching, and compared it with the scale-invariant feature transform algorithm. Tests including the adaptability and matching speed on rotation, scale and illumination changes were carried out. Experimental results showed that random tree can achieve 30 frames per second of real-time feature matching, and moreover, can reach more than 50% of the matching rate when illumination changes, however its matching accuracy still needs to be improved.

Original language	English
Pages (from-to)	988-993
Number of pages	6
Journal	Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
Volume	29
Issue number	11
Publication status	Published - Nov 2009

Keywords

Augment reality
Feature matching
Randomized tree

Cite this

@article{46ce982d7bc6499a894e7014b9754d75,

title = "A study on the feature matching performance of randomized trees",

abstract = "In order to improve the augmented reality systems, is presented an evaluation of the randomized tree algorithm for augmented reality feature matching, and compared it with the scale-invariant feature transform algorithm. Tests including the adaptability and matching speed on rotation, scale and illumination changes were carried out. Experimental results showed that random tree can achieve 30 frames per second of real-time feature matching, and moreover, can reach more than 50% of the matching rate when illumination changes, however its matching accuracy still needs to be improved.",

keywords = "Augment reality, Feature matching, Randomized tree",

author = "Wang, {Yong Tian} and Lin, {Jing Dun} and Jing Chen and Guo, {Jun Wei} and Wei Liu and Kang Xue",

year = "2009",

month = nov,

language = "English",

volume = "29",

pages = "988--993",

journal = "Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology",

issn = "1001-0645",

publisher = "Beijing Institute of Technology",

number = "11",

}

TY - JOUR

T1 - A study on the feature matching performance of randomized trees

AU - Wang, Yong Tian

AU - Lin, Jing Dun

AU - Chen, Jing

AU - Guo, Jun Wei

AU - Liu, Wei

AU - Xue, Kang

PY - 2009/11

Y1 - 2009/11

N2 - In order to improve the augmented reality systems, is presented an evaluation of the randomized tree algorithm for augmented reality feature matching, and compared it with the scale-invariant feature transform algorithm. Tests including the adaptability and matching speed on rotation, scale and illumination changes were carried out. Experimental results showed that random tree can achieve 30 frames per second of real-time feature matching, and moreover, can reach more than 50% of the matching rate when illumination changes, however its matching accuracy still needs to be improved.

AB - In order to improve the augmented reality systems, is presented an evaluation of the randomized tree algorithm for augmented reality feature matching, and compared it with the scale-invariant feature transform algorithm. Tests including the adaptability and matching speed on rotation, scale and illumination changes were carried out. Experimental results showed that random tree can achieve 30 frames per second of real-time feature matching, and moreover, can reach more than 50% of the matching rate when illumination changes, however its matching accuracy still needs to be improved.

KW - Augment reality

KW - Feature matching

KW - Randomized tree

UR - http://www.scopus.com/inward/record.url?scp=71949125559&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:71949125559

SN - 1001-0645

VL - 29

SP - 988

EP - 993

JO - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

JF - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

IS - 11

ER -

A study on the feature matching performance of randomized trees

Abstract

Keywords

Other files and links

Fingerprint

Cite this