Indoor Scene Recognition by a Mobile Robot Through Adaptive Object Detection

Indoor Scene Recognition by a Mobile Robot Through Adaptive Object Detection. Espinace, P., Kollar, T., Roy, N., & Soto, A. Robotics and Autonomous Systems, 2013.

Paper abstract bibtex 6 downloads

Mobile Robotics has achieved notably progress, however, to increase the complexity of the tasks that mobile robots can perform in natural environments, we need to provide them with a greater semantic understanding of their surrounding. In particular, identifying indoor scenes, such as an office or a kitchen, is a highly valuable perceptual ability for an indoor mobile robot, and in this paper we propose a new technique to achieve this goal. As a distinguishing feature, we use common objects, such as doors or furnitures, as a key intermediate representation to recognize indoor scenes. We frame our method as a generative probabilistic hierarchical model, where we use object category classifiers to associate low-level visual features to objects, and contextual relations to associate objects to scenes. The inherent seman- tic interpretation of common objects allows us to use rich sources of online data to populate the probabilistic terms of our model. In contrast to alterna- tive computer vision based methods, we boost performance by exploiting the embedded and dynamic nature of a mobile robot. In particular, we increase detection accuracy and efficiency by using a 3D range sensor that allows us to implement a focus of attention mechanism based on geometric and struc- tural information. Furthermore, we use concepts from information theory to propose an adaptive scheme that limits computational load by selectively guiding the search for informative objects. The operation of this scheme is facilitated by the dynamic nature of a mobile robot that is constantly changing its field of view. We test our approach using real data captured by a mo- bile robot navigating in office and home environments. Our results indicate that the proposed approach outperforms several state-of-the-art techniques

@Article{	  espinace:etal:2013,
  author	= {P. Espinace and T. Kollar and N. Roy and A. Soto},
  title		= {Indoor Scene Recognition by a Mobile Robot Through
		  Adaptive Object Detection},
  journal	= {Robotics and Autonomous Systems},
  volume	= {61},
  number	= {9},
  year		= {2013},
  abstract	= {Mobile Robotics has achieved notably progress, however, to
		  increase the complexity of the tasks that mobile robots can
		  perform in natural environments, we need to provide them
		  with a greater semantic understanding of their surrounding.
		  In particular, identifying indoor scenes, such as an office
		  or a kitchen, is a highly valuable perceptual ability for
		  an indoor mobile robot, and in this paper we propose a new
		  technique to achieve this goal. As a distinguishing
		  feature, we use common objects, such as doors or
		  furnitures, as a key intermediate representation to
		  recognize indoor scenes. We frame our method as a
		  generative probabilistic hierarchical model, where we use
		  object category classifiers to associate low-level visual
		  features to objects, and contextual relations to associate
		  objects to scenes. The inherent seman- tic interpretation
		  of common objects allows us to use rich sources of online
		  data to populate the probabilistic terms of our model. In
		  contrast to alterna- tive computer vision based methods, we
		  boost performance by exploiting the embedded and dynamic
		  nature of a mobile robot. In particular, we increase
		  detection accuracy and efficiency by using a 3D range
		  sensor that allows us to implement a focus of attention
		  mechanism based on geometric and struc- tural information.
		  Furthermore, we use concepts from information theory to
		  propose an adaptive scheme that limits computational load
		  by selectively guiding the search for informative objects.
		  The operation of this scheme is facilitated by the dynamic
		  nature of a mobile robot that is constantly changing its
		  field of view. We test our approach using real data
		  captured by a mo- bile robot navigating in office and home
		  environments. Our results indicate that the proposed
		  approach outperforms several state-of-the-art techniques },
  url		= {http://saturno.ing.puc.cl/media/papers_alvaro/Final-RAS-2013.pdf}
}

Downloads: 6