Applying probabilistic Mixture Models to semantic place classification in mobile robotics

@article{Premebida2015ApplyingPM,
  title={Applying probabilistic Mixture Models to semantic place classification in mobile robotics},
  author={Cristiano Premebida and Diego R. Faria and Francisco A. Souza and Urbano Nunes},
  journal={2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2015},
  pages={4265-4270}
}
In 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… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • These results allow us to conclude that DBMM achieved an average classification performance of 91.67% and 85.82%, which surpass SVM (narrow bars depicted within the gray-bars), and also the solution in [9].

Citations

Publications citing this paper.
SHOWING 1-7 OF 7 CITATIONS

Dynamic Bayesian network for semantic place classification in mobile robotics

VIEW 5 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Place Classification With a Graph Regularized Deep Neural Network

  • IEEE Transactions on Cognitive and Developmental Systems
  • 2017
VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Affective facial expressions recognition for human-robot interaction

  • 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
  • 2017
VIEW 1 EXCERPT
CITES METHODS

Social activity recognition based on probabilistic merging of skeleton features with proximity priors from RGB-D data

  • 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2016
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Towards robust place recognition for robot localization

  • 2008 IEEE International Conference on Robotics and Automation
  • 2008
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Towards simultaneous place classification and object detection based on conditional random field with multiple cues

  • 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A probabilistic approach for human everyday activities recognition using body motion from RGB-D images

  • The 23rd IEEE International Symposium on Robot and Human Interactive Communication
  • 2014
VIEW 1 EXCERPT

A transfer learning approach for multi-cue semantic place recognition

  • 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2013
VIEW 2 EXCERPTS

Application of semi-supervised learning with Voronoi Graph for place classification

  • 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2012
VIEW 2 EXCERPTS