Visual novelty detection with automatic scale selection

This paper presents experiments with an autonomous inspection robot, whose task was to highlight novel features in its environment from camera images. The experiments used two different attention mechanisms–saliency map and multi-scale Harris detector–and two different novelty detection mechanisms —...

Full description

Saved in:
Bibliographic Details
Published inRobotics and autonomous systems Vol. 55; no. 9; pp. 693 - 701
Main Authors Vieira Neto, Hugo, Nehmzow, Ulrich
Format Journal Article
LanguageEnglish
Published Elsevier B.V 30.09.2007
Subjects
Automated inspection
Online novelty detection
Scale invariance
Online novelty detection
Scale invariance
Automated inspection
Online AccessGet full text

Cover

More Information
Summary:This paper presents experiments with an autonomous inspection robot, whose task was to highlight novel features in its environment from camera images. The experiments used two different attention mechanisms–saliency map and multi-scale Harris detector–and two different novelty detection mechanisms — the Grow-When-Required (GWR) neural network and an incremental Principal Component Analysis (PCA). For all mechanisms we compared fixed-scale image encoding with automatically scaled image patches. Results show that automatic scale selection provides a more efficient representation of the visual input space, but that performance is generally better using a fixed-scale image encoding.
ISSN:0921-8890
1872-793X
DOI:10.1016/j.robot.2007.05.012