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 language | English |
|---|---|
| Title of host publication | Communications in Computer and Information Science |
| Pages | 270-279 |
| Number of pages | 10 |
| Volume | 212 CCIS |
| DOIs | |
| Publication status | Published - 2011 |
| Event | 14th FIRA RoboWorld Congress on Next Wave in Robotics, FIRA 2011 - Kaohsiung Duration: 26 Aug 2011 → 30 Aug 2011 |
Publication series
| Name | Communications in Computer and Information Science |
|---|---|
| Volume | 212 CCIS |
| ISSN (Print) | 18650929 |
Other
| Other | 14th FIRA RoboWorld Congress on Next Wave in Robotics, FIRA 2011 |
|---|---|
| City | Kaohsiung |
| Period | 26/8/11 → 30/8/11 |
Fingerprint
Keywords
- feature reduction
- image calibration
- mobile robot orientation
- robot soccer
- Support Vector Machine
ASJC Scopus subject areas
- Computer Science(all)
Cite this
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 proceeding › Conference contribution
}
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 -