TY - GEN
T1 - Applying Probabilistic Mixture Models to Semantic Place Classification in Mobile Robotics
AU - Premebida, Cristiano
AU - Faria, Diego R.
AU - Souza, Francisco A. de
AU - Nunes, Urbano
PY - 2015
Y1 - 2015
N2 - n this paper a study is made of the problem of classifying scenarios, in terms of semantic categories, based on data gathered from sensors mounted on-board mobile robots operating indoors. Once the data are transformed to feature space, supervised classification is performed by a probabilistic approach called Dynamic Bayesian Mixture Models (DBMM). This approach combines class-conditional probabilities from supervised learning models and incorporates past inferences. In this work, several experiments on multi-class semantic place classification are reported based on publicly available datasets. Such experiments were conducted in a such way that generalization aspects are emphasized, which is particularly important in real-world applications. Benchmark results show the effectiveness and competitive performance of the DBMM method, in terms of classification rates, using features extracted from 2D range data and from a RGB-D (Kinect) sensor.
AB - n this paper a study is made of the problem of classifying scenarios, in terms of semantic categories, based on data gathered from sensors mounted on-board mobile robots operating indoors. Once the data are transformed to feature space, supervised classification is performed by a probabilistic approach called Dynamic Bayesian Mixture Models (DBMM). This approach combines class-conditional probabilities from supervised learning models and incorporates past inferences. In this work, several experiments on multi-class semantic place classification are reported based on publicly available datasets. Such experiments were conducted in a such way that generalization aspects are emphasized, which is particularly important in real-world applications. Benchmark results show the effectiveness and competitive performance of the DBMM method, in terms of classification rates, using features extracted from 2D range data and from a RGB-D (Kinect) sensor.
UR - http://ieeexplore.ieee.org/document/7353981/
U2 - 10.1109/IROS.2015.7353981
DO - 10.1109/IROS.2015.7353981
M3 - Conference publication
SP - 4265
EP - 4270
BT - IEEE/RSJ IEEE IROS'15: International Conference on Intelligent Robots and Systems
ER -