Now showing items 170-189 of 211

    • Rao-Blackwellized Importance Sampling of Camera Parameters from Simple User Input with Visibility Preprocessing in Line Space 

      Quennesson, Kevin; Dellaert, Frank (Georgia Institute of Technology, 2006-06)
      Users know what they see before where they are: it is more natural to talk about high level visibility information ("I see such object") than about one's location or orientation. In this paper we introduce a method to find ...
    • A Rao-Blackwellized MCMC Algorithm for Recovering Piecewise Planar 3D Models From Multiple View RGBD Images 

      Srinivasan, Natesh; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-10)
      In this paper, we propose a reconstruction technique that uses 2D regions/superpixels rather than point features. We use pre-segmented RGBD data as input and obtain piecewise planar 3D models of the world. We ...
    • A Rao-Blackwellized Particle Filter for EigenTracking 

      Khan, Zia; Balch, Tucker; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2004-06)
      Subspace representations have been a popular way to model appearance in computer vision. In Jepson and Black’s influential paper on EigenTracking, they were successfully applied in tracking. For noisy targets, optimi ...
    • A Rao-Blackwellized Particle Filter for Topological Mapping 

      Ranganathan, Ananth; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2006-05)
      We present a particle filtering algorithm to construct topological maps of an uninstrument environment. The algorithm presented here constructs the posterior on the space of all possible topologies given measurements, ...
    • A Rao-Blackwellized Parts-Constellation Tracker 

      Schindler, Grant; Dellaert, Frank (Georgia Institute of TechnologySpringer Berlin / Heidelberg, 2005)
      We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully applied to object recognition and tracking. ...
    • Real-Time Human Detection Using Contour Cues 

      Wu, Jianxin; Geyer, Christopher; Rehg, James M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2011-05)
      A real-time and accurate human detector, C⁴, is proposed in this paper. C⁴ achieves 20 fps speed and stateof- the-art detection accuracy, using only one processing thread without resorting to special hardwares like GPU. ...
    • Recognizing Water-Based Activities in the Home Through Infrastructure-Mediated Sensing 

      Thomaz, Edison; Bettadapura, Vinay; Reyes, Gabriel; Sandesh, Megha; Schindler, Grant; Plötz, Thomas; Abowd, Gregory D.; Essa, Irfan (Georgia Institute of TechnologyAssociation for Computing Machinery, 2012-09)
      Activity recognition in the home has been long recognized as the foundation for many desirable applications in fields such as home automation, sustainability, and healthcare. However, building a practical home activity ...
    • Reconstruction of Objects with Jagged Edges through Rao-Blackwellized Fitting of Piecewise Smooth Subdivision Curves 

      Kaess, Michael; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2003-10)
      In some applications objects are known to have non-smooth or “jagged” edges, which are not well approximated by smooth curves. We use subdivision curves as a simple but flexible curve representation, which allows tagging ...
    • Rigid Components Identification and Rigidity Enforcement in Bearing-Only Localization using the Graph Cycle Basis 

      Tron, Roberto; Carlone, Luca; Dellaert, Frank; Daniilidis, Kostas (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2015)
      Bearing-only localization can be formulated in terms of optimal graph embedding: one has to assign a 2-D or 3-D position to each node in a graph while satisfying as close as possible all the bearing-only constraints on ...
    • RIGOR: Reusing Inference in Graph Cuts for generating Object Regions 

      Humayun, Ahmad; Li, Fuxin; Rehg, James M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-06)
      Popular figure-ground segmentation algorithms generate a pool of boundary-aligned segment proposals that can be used in subsequent object recognition engines. These algorithms can recover most image objects with high ...
    • Robust Generative Subspace Modeling: The Subspace t Distribution 

      Khan, Zia; Dellaert, Frank (Georgia Institute of Technology, 2004)
      Linear latent variable models such as statistical factor analysis (SFA) and probabilistic principal component analysis (PPCA) assume that the data are distributed according to a multivariate Gaussian. A drawback of this ...
    • Saliency Detection and Model-based Tracking: a Two Part Vision System for Small Robot Navigation in Forested Environments 

      Roberts, Richard; Ta, Duy-Nguyen; Straub, Julian; Ok, Kyel; Dellaert, Frank (Georgia Institute of TechnologySPIE, 2012-05-01)
      Towards the goal of fast, vision-based autonomous flight, localization, and map building to support local planning and control in unstructured outdoor environments, we present a method for incrementally building a map of ...
    • A Sample of Monte Carlo Methods in Robotics and Vision 

      Dellaert, Frank (Georgia Institute of TechnologyThe Institute of Statistical Mathematics (ISM), 2003-12)
      Approximate inference by sampling from an appropriately constructed posterior has recently seen a dramatic increase in popularity in both the robotics and computer vision community. In this paper, I will describe a number ...
    • The Secrets of Salient Object Segmentation 

      Li, Yin; Hou, Xiaodi; Koch, Christof; Rehg, James M.; Yuille, Alan L. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-06)
      In this paper we provide an extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets. Our analysis identifies serious design flaws of existing salient ...
    • Segmental Switching Linear Dynamic Systems 

      Oh, Sang Min; Rehg, James M.; Dellaert, Frank (Georgia Institute of Technology, 2005)
      We introduce Segmental Switching Linear Dynamic Systems (S-SLDS), which improve on standard SLDSs by explicitly incorporating duration modeling capabilities. We show that S-SLDSs can adopt arbitrary finite-sized duration ...
    • Selecting Good Measurements via ℓ₁ Relaxation: A Convex Approach for Robust Estimation Over Graphs 

      Carlone, Luca; Censi, Andrea; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-09)
      Pose graph optimization is an elegant and efficient formulation for robot localization and mapping. Experimental evidence suggests that, in real problems, the set of measurements used to estimate robot ...
    • Semantic Modeling of Places using Objects 

      Ranganathan, Ananth; Dellaert, Frank (Georgia Institute of TechnologyMIT Press, 2007-06)
      While robot mapping has seen massive strides recently, higher level abstractions in map representation are still not widespread. Maps containing semantic concepts such as objects and labels are essential for many tasks ...
    • Semantic SLAM for Collaborative Cognitive Workspaces 

      Dellaert, Frank; Bruemmer, David (Georgia Institute of Technology, 2004)
    • SLAM with Object Discovery, Modeling and Mapping 

      Choudhary, Siddharth; Trevor, Alexander J. B.; Christensen, Henrik I.; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-09)
      Object discovery and modeling have been widely studied in the computer vision and robotics communities. SLAM approaches that make use of objects and higher level features have also recently ...
    • Social Interactions: A First-Person Perspective 

      Fathi, Alireza; Hodgins, Jessica K.; Rehg, James M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-06)
      This paper presents a method for the detection and recognition of social interactions in a day-long first-person video of a social event, like a trip to an amusement park. The location and orientation of faces are ...