by D Schröter, T. Weber, M Beetz and B Radig
Abstract:
The automatic acquisition of structured object maps requires sophisticated perceptual mechanisms that enable the robot to recognize the objects that are to be stored in the robot map. This paper investigates a particular object recognition problem: the automatic detection and classification of gateways in office environments based on laser range data. We will propose, discuss, and empirically evaluate a sensor model for crossing gateways and different approaches to gateway classification including simple maximum classifiers and HMM-based classification of observation sequences.
Reference:
Detection and Classification of Gateways for the Acquisition of Structured Robot Maps (D Schröter, T. Weber, M Beetz and B Radig), In Proc. of 26th Pattern Recognition Symposium (DAGM), Tübingen/Germany, 2004.
Bibtex Entry:
@inproceedings{schroter_detection_2004,
author = {D Schröter and T. Weber and M Beetz and B Radig},
title = {Detection and Classification of Gateways for the Acquisition of Structured
Robot Maps},
booktitle = {Proc. of 26th Pattern Recognition Symposium ({DAGM)}, {Tübingen/Germany}},
year = {2004},
abstract = {The automatic acquisition of structured object maps requires sophisticated
perceptual mechanisms that enable the robot to recognize the objects
that are to be stored in the robot map. This paper investigates a
particular object recognition problem: the automatic detection and
classification of gateways in office environments based on laser
range data. We will propose, discuss, and empirically evaluate a
sensor model for crossing gateways and different approaches to gateway
classification including simple maximum classifiers and {HMM-based}
classification of observation sequences.},
}