Optimal features and classes for estimating mobile robot orientation based on support vector machine

Zainal Fitri Mohd Zolkifli, Mohamad Farif Jemili, Fadzilah Hashim, Siti Norul Huda Sheikh Abdullah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In order for a mobile robot to perform its assigned tasks, it often requires a representation of its environment such as knowledge of how to navigate in its environment, and a method for determining its position in the environment. A major problem in computer vision and machine learning is to achieve a good feature as it can largely determine the performance of a vision system. A good feature should be informative, invariant to noise or a given set of transformations, and fast to compute. Also, in certain settings sparsity of the feature response, either across images or within a single image, is desired. Our objective of this paper is to obtain optimal features as well as determining the optimal class of angle in order to estimate mobile robot orientation single or unified images from two camera orientations. We introduce feature selection process before classifying features based on support vector machine classifier. We achieve better accuracy rate by only reducing its feature number from 30 features down to only 17 features on unified images. Furthermore, we also find that only 5 classes of robot angles are sufficient to estimate robot orientation correctly.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
Pages270-279
Number of pages10
Volume212 CCIS
DOIs
Publication statusPublished - 2011
Event14th FIRA RoboWorld Congress on Next Wave in Robotics, FIRA 2011 - Kaohsiung
Duration: 26 Aug 201130 Aug 2011

Publication series

NameCommunications in Computer and Information Science
Volume212 CCIS
ISSN (Print)18650929

Other

Other14th FIRA RoboWorld Congress on Next Wave in Robotics, FIRA 2011
CityKaohsiung
Period26/8/1130/8/11

Fingerprint

Mobile robots
Support vector machines
Robots
Computer vision
Learning systems
Feature extraction
Classifiers
Cameras

Keywords

  • feature reduction
  • image calibration
  • mobile robot orientation
  • robot soccer
  • Support Vector Machine

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Zolkifli, Z. F. M., Jemili, M. F., Hashim, F., & Sheikh Abdullah, S. N. H. (2011). Optimal features and classes for estimating mobile robot orientation based on support vector machine. In Communications in Computer and Information Science (Vol. 212 CCIS, pp. 270-279). (Communications in Computer and Information Science; Vol. 212 CCIS). https://doi.org/10.1007/978-3-642-23147-6_33

Optimal features and classes for estimating mobile robot orientation based on support vector machine. / Zolkifli, Zainal Fitri Mohd; Jemili, Mohamad Farif; Hashim, Fadzilah; Sheikh Abdullah, Siti Norul Huda.

Communications in Computer and Information Science. Vol. 212 CCIS 2011. p. 270-279 (Communications in Computer and Information Science; Vol. 212 CCIS).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zolkifli, ZFM, Jemili, MF, Hashim, F & Sheikh Abdullah, SNH 2011, Optimal features and classes for estimating mobile robot orientation based on support vector machine. in Communications in Computer and Information Science. vol. 212 CCIS, Communications in Computer and Information Science, vol. 212 CCIS, pp. 270-279, 14th FIRA RoboWorld Congress on Next Wave in Robotics, FIRA 2011, Kaohsiung, 26/8/11. https://doi.org/10.1007/978-3-642-23147-6_33
Zolkifli ZFM, Jemili MF, Hashim F, Sheikh Abdullah SNH. Optimal features and classes for estimating mobile robot orientation based on support vector machine. In Communications in Computer and Information Science. Vol. 212 CCIS. 2011. p. 270-279. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-642-23147-6_33
Zolkifli, Zainal Fitri Mohd ; Jemili, Mohamad Farif ; Hashim, Fadzilah ; Sheikh Abdullah, Siti Norul Huda. / Optimal features and classes for estimating mobile robot orientation based on support vector machine. Communications in Computer and Information Science. Vol. 212 CCIS 2011. pp. 270-279 (Communications in Computer and Information Science).
@inproceedings{a3e556c889e24f7594bd673bec86b53a,
title = "Optimal features and classes for estimating mobile robot orientation based on support vector machine",
abstract = "In order for a mobile robot to perform its assigned tasks, it often requires a representation of its environment such as knowledge of how to navigate in its environment, and a method for determining its position in the environment. A major problem in computer vision and machine learning is to achieve a good feature as it can largely determine the performance of a vision system. A good feature should be informative, invariant to noise or a given set of transformations, and fast to compute. Also, in certain settings sparsity of the feature response, either across images or within a single image, is desired. Our objective of this paper is to obtain optimal features as well as determining the optimal class of angle in order to estimate mobile robot orientation single or unified images from two camera orientations. We introduce feature selection process before classifying features based on support vector machine classifier. We achieve better accuracy rate by only reducing its feature number from 30 features down to only 17 features on unified images. Furthermore, we also find that only 5 classes of robot angles are sufficient to estimate robot orientation correctly.",
keywords = "feature reduction, image calibration, mobile robot orientation, robot soccer, Support Vector Machine",
author = "Zolkifli, {Zainal Fitri Mohd} and Jemili, {Mohamad Farif} and Fadzilah Hashim and {Sheikh Abdullah}, {Siti Norul Huda}",
year = "2011",
doi = "10.1007/978-3-642-23147-6_33",
language = "English",
isbn = "9783642231469",
volume = "212 CCIS",
series = "Communications in Computer and Information Science",
pages = "270--279",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Optimal features and classes for estimating mobile robot orientation based on support vector machine

AU - Zolkifli, Zainal Fitri Mohd

AU - Jemili, Mohamad Farif

AU - Hashim, Fadzilah

AU - Sheikh Abdullah, Siti Norul Huda

PY - 2011

Y1 - 2011

N2 - In order for a mobile robot to perform its assigned tasks, it often requires a representation of its environment such as knowledge of how to navigate in its environment, and a method for determining its position in the environment. A major problem in computer vision and machine learning is to achieve a good feature as it can largely determine the performance of a vision system. A good feature should be informative, invariant to noise or a given set of transformations, and fast to compute. Also, in certain settings sparsity of the feature response, either across images or within a single image, is desired. Our objective of this paper is to obtain optimal features as well as determining the optimal class of angle in order to estimate mobile robot orientation single or unified images from two camera orientations. We introduce feature selection process before classifying features based on support vector machine classifier. We achieve better accuracy rate by only reducing its feature number from 30 features down to only 17 features on unified images. Furthermore, we also find that only 5 classes of robot angles are sufficient to estimate robot orientation correctly.

AB - In order for a mobile robot to perform its assigned tasks, it often requires a representation of its environment such as knowledge of how to navigate in its environment, and a method for determining its position in the environment. A major problem in computer vision and machine learning is to achieve a good feature as it can largely determine the performance of a vision system. A good feature should be informative, invariant to noise or a given set of transformations, and fast to compute. Also, in certain settings sparsity of the feature response, either across images or within a single image, is desired. Our objective of this paper is to obtain optimal features as well as determining the optimal class of angle in order to estimate mobile robot orientation single or unified images from two camera orientations. We introduce feature selection process before classifying features based on support vector machine classifier. We achieve better accuracy rate by only reducing its feature number from 30 features down to only 17 features on unified images. Furthermore, we also find that only 5 classes of robot angles are sufficient to estimate robot orientation correctly.

KW - feature reduction

KW - image calibration

KW - mobile robot orientation

KW - robot soccer

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=80052816954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052816954&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-23147-6_33

DO - 10.1007/978-3-642-23147-6_33

M3 - Conference contribution

AN - SCOPUS:80052816954

SN - 9783642231469

VL - 212 CCIS

T3 - Communications in Computer and Information Science

SP - 270

EP - 279

BT - Communications in Computer and Information Science

ER -