Illumination-invariant image-based novelty detection in a cognitive mobile robot's environment

Image-based scene representations enable a mobile robot to make a realistic prediction of its environment. Hence, it is able to rapidly detect changes in its surroundings by comparing a virtual image generated from previously acquired reference images and its current observation. This facilitates at...

Full description

Saved in:
Bibliographic Details
Main Authors: Maier, Werner, Fengqing Bao, Mair, Elmar, Steinbach, Eckehard, Burschka, Darius
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Cognitive robotics
Image sequences
Layout
Lighting
Mobile robots
Reflectivity
Rendering (computer graphics)
Robot kinematics
Robotics and automation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image-based scene representations enable a mobile robot to make a realistic prediction of its environment. Hence, it is able to rapidly detect changes in its surroundings by comparing a virtual image generated from previously acquired reference images and its current observation. This facilitates attentional control to novel events. However, illumination effects can impair attentional control if the robot does not take them into account. To address this issue, we present in this paper an approach for the acquisition of illumination-invariant scene representations. Using multiple spatial image sequences which are captured under varying illumination conditions the robot computes an illumination-invariant image-based environment model. With this representation and statistical models about the illumination behavior, the robot is able to robustly detect texture changes in its environment under different lighting. Experimental results show high-quality images which are free of illumination effects as well as more robust novelty detection compared to state-of-the-art methods.
ISSN:1050-4729
2577-087X
DOI:10.1109/ROBOT.2010.5509354