Learning visual obstacle detection using color histogram features

Authors:
Saskia Metzler;Matthias Nieuwenhuisen;Sven Behnke
Affiliations:
Autonomous Intelligent Systems Group, Institute for Computer Science VI, University of Bonn, Germany;Autonomous Intelligent Systems Group, Institute for Computer Science VI, University of Bonn, Germany;Autonomous Intelligent Systems Group, Institute for Computer Science VI, University of Bonn, Germany
Venue:
Robot Soccer World Cup XV
Year:
2012

Citing 7
Cited 0

An Introduction to the Kalman Filter

An Introduction to the Kalman Filter
Handwritten digit recognition using k nearest-neighbor, radial-basis function, and backpropagation neural networks

Neural Computation
Appearance-Based Robot Discrimination Using Eigenimages

RoboCup 2006: Robot Soccer World Cup X
Robot detection with a cascade of boosted classifiers based on haar-like features

RoboCup 2010
Robot detection with a cascade of boosted classifiers based on haar-like features

RoboCup 2010
Neural robot detection in robocup

Biomimetic Neural Learning for Intelligent Robots
Realtime object recognition using decision tree learning

RoboCup 2004

Quantified Score

Hi-index	0.00

Visualization

Abstract

Perception of the environment is crucial in terms of successfully playing soccer. Especially the detection of other players improves game play skills, such as obstacle avoidance and path planning. Such information can help refine reactive behavioral strategies, and is conducive to team play capabilities. Robot detection in the RoboCup Standard Platform League is particularly challenging as the Nao robots are limited in computing resources and their appearance is predominantly white in color like the field lines. This paper describes a vision-based multilevel approach which is integrated into the B-Human Software Framework and evaluated in terms of speed and accuracy. On the basis of color segmented images, a feed-forward neural network is trained to discriminate between robots and non-robots. The presented algorithm initially extracts image regions which potentially depict robots and prepares them for classification. Preparation comprises calculation of color histograms as well as linear interpolation in order to obtain network inputs of a specific size. After classification by the neural network, a position hypothesis is generated.