Mosaicking images: Panoramic imaging for miniature robots

Christian C. Dos Santos, Sascha A. Stoeter, Paul E. Rybski, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Two methods of mosaicking images were developed, one for the general case and one for the simple case of a shift between two following images. The general method was evaluated by merging three images into a mosaic. When executed manually, the success rate of the method was 60%. With human assistance in selecting an appropriate number of corners to base the correlation on, the success rate increased to 89%. The operation took four minutes on a Pentium II 450 MHz Linux workstation, with most of this time spent on finding the correspondences. For the simple method, the shift was determined correctly in 95% of the tests runs for less noisy images. For noisy images, the success rate of properly merging all images of a mosaic was 20%. To increase the success rate, a function that determines the noise level was added. If too much noise was detected, the image is discarded and another one taken. This way, the error rate dropped to 10%.

Original languageEnglish (US)
Pages (from-to)62-68
Number of pages7
JournalIEEE Robotics and Automation Magazine
Volume11
Issue number4
DOIs
StatePublished - Dec 1 2004

Fingerprint

Merging
Robots
Imaging techniques
Linux

Keywords

  • Miniature robots
  • Mosaicking
  • Omnidirectional camera systems
  • Panoramic imaging

Cite this

Mosaicking images : Panoramic imaging for miniature robots. / Dos Santos, Christian C.; Stoeter, Sascha A.; Rybski, Paul E.; Papanikolopoulos, Nikolaos P.

In: IEEE Robotics and Automation Magazine, Vol. 11, No. 4, 01.12.2004, p. 62-68.

Research output: Contribution to journalArticle

Dos Santos, Christian C. ; Stoeter, Sascha A. ; Rybski, Paul E. ; Papanikolopoulos, Nikolaos P. / Mosaicking images : Panoramic imaging for miniature robots. In: IEEE Robotics and Automation Magazine. 2004 ; Vol. 11, No. 4. pp. 62-68.
@article{11ecef02c8834fd38ea940342c8a4555,
title = "Mosaicking images: Panoramic imaging for miniature robots",
abstract = "Two methods of mosaicking images were developed, one for the general case and one for the simple case of a shift between two following images. The general method was evaluated by merging three images into a mosaic. When executed manually, the success rate of the method was 60{\%}. With human assistance in selecting an appropriate number of corners to base the correlation on, the success rate increased to 89{\%}. The operation took four minutes on a Pentium II 450 MHz Linux workstation, with most of this time spent on finding the correspondences. For the simple method, the shift was determined correctly in 95{\%} of the tests runs for less noisy images. For noisy images, the success rate of properly merging all images of a mosaic was 20{\%}. To increase the success rate, a function that determines the noise level was added. If too much noise was detected, the image is discarded and another one taken. This way, the error rate dropped to 10{\%}.",
keywords = "Miniature robots, Mosaicking, Omnidirectional camera systems, Panoramic imaging",
author = "{Dos Santos}, {Christian C.} and Stoeter, {Sascha A.} and Rybski, {Paul E.} and Papanikolopoulos, {Nikolaos P}",
year = "2004",
month = "12",
day = "1",
doi = "10.1109/MRA.2004.1371610",
language = "English (US)",
volume = "11",
pages = "62--68",
journal = "IEEE Robotics and Automation Magazine",
issn = "1070-9932",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Mosaicking images

T2 - Panoramic imaging for miniature robots

AU - Dos Santos, Christian C.

AU - Stoeter, Sascha A.

AU - Rybski, Paul E.

AU - Papanikolopoulos, Nikolaos P

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Two methods of mosaicking images were developed, one for the general case and one for the simple case of a shift between two following images. The general method was evaluated by merging three images into a mosaic. When executed manually, the success rate of the method was 60%. With human assistance in selecting an appropriate number of corners to base the correlation on, the success rate increased to 89%. The operation took four minutes on a Pentium II 450 MHz Linux workstation, with most of this time spent on finding the correspondences. For the simple method, the shift was determined correctly in 95% of the tests runs for less noisy images. For noisy images, the success rate of properly merging all images of a mosaic was 20%. To increase the success rate, a function that determines the noise level was added. If too much noise was detected, the image is discarded and another one taken. This way, the error rate dropped to 10%.

AB - Two methods of mosaicking images were developed, one for the general case and one for the simple case of a shift between two following images. The general method was evaluated by merging three images into a mosaic. When executed manually, the success rate of the method was 60%. With human assistance in selecting an appropriate number of corners to base the correlation on, the success rate increased to 89%. The operation took four minutes on a Pentium II 450 MHz Linux workstation, with most of this time spent on finding the correspondences. For the simple method, the shift was determined correctly in 95% of the tests runs for less noisy images. For noisy images, the success rate of properly merging all images of a mosaic was 20%. To increase the success rate, a function that determines the noise level was added. If too much noise was detected, the image is discarded and another one taken. This way, the error rate dropped to 10%.

KW - Miniature robots

KW - Mosaicking

KW - Omnidirectional camera systems

KW - Panoramic imaging

UR - http://www.scopus.com/inward/record.url?scp=12444302283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12444302283&partnerID=8YFLogxK

U2 - 10.1109/MRA.2004.1371610

DO - 10.1109/MRA.2004.1371610

M3 - Article

VL - 11

SP - 62

EP - 68

JO - IEEE Robotics and Automation Magazine

JF - IEEE Robotics and Automation Magazine

SN - 1070-9932

IS - 4

ER -