Unsupervised Identification of Useful Visual Landmarks Using Multiple Segmentations and Top-Down Feedback

Unsupervised Identification of Useful Visual Landmarks Using Multiple Segmentations and Top-Down Feedback. Espinace, P., Langdon, D., & Soto, A. Robotics and Autonomous Systems, 56(6):538-548, 2008.

Paper abstract bibtex 1 download

In this paper, we tackle the problem of unsupervised selection and posterior recognition of visual landmarks in images sequences acquired by an indoor mobile robot. This is a highly valuable perceptual capability for a wide variety of robotic applications, in particular autonomous navigation. Our method combines a bottom-up data driven approach with top-down feedback provided by high level semantic representations. The bottom-up approach is based on three main mechanisms: visual attention, area segmentation, and landmark characterization. As there is no segmentation method that works properly in every situation, we integrate multiple segmentation algorithms in order to increase the robustness of the approach. In terms of the top-down feedback, this is provided by two information sources: i) An estimation of the robot position that reduces the searching scope for potential matches with previously selected landmarks, ii) A set of weights that, according to the results of previous recognitions, controls the influence of each segmentation algorithm in the recognition of each landmark. We test our approach with encouraging results in three datasets corresponding to real-world scenarios.

@Article{	  espinace:soto:2008a,
  author	= {P. Espinace and D. Langdon and A. Soto},
  title		= {Unsupervised Identification of Useful Visual Landmarks
		  Using Multiple Segmentations and Top-Down Feedback},
  journal	= {Robotics and Autonomous Systems},
  volume	= {56},
  number	= {6},
  pages		= {538-548},
  year		= {2008},
  abstract	= {In this paper, we tackle the problem of unsupervised
		  selection and posterior recognition of visual landmarks in
		  images sequences acquired by an indoor mobile robot. This
		  is a highly valuable perceptual capability for a wide
		  variety of robotic applications, in particular autonomous
		  navigation. Our method combines a bottom-up data driven
		  approach with top-down feedback provided by high level
		  semantic representations. The bottom-up approach is based
		  on three main mechanisms: visual attention, area
		  segmentation, and landmark characterization. As there is no
		  segmentation method that works properly in every situation,
		  we integrate multiple segmentation algorithms in order to
		  increase the robustness of the approach. In terms of the
		  top-down feedback, this is provided by two information
		  sources: i) An estimation of the robot position that
		  reduces the searching scope for potential matches with
		  previously selected landmarks, ii) A set of weights that,
		  according to the results of previous recognitions, controls
		  the influence of each segmentation algorithm in the
		  recognition of each landmark. We test our approach with
		  encouraging results in three datasets corresponding to
		  real-world scenarios. },
  url		= {http://saturno.ing.puc.cl/media/papers_alvaro/Pablo-RAS-08.pdf}
}

Downloads: 1