Now showing items 104-123 of 211

    • Lagrangian Duality in 3D SLAM: Verification Techniques and Optimal Solutions 

      Carlone, Luca; Rosen, David M.; Calafiore, Giuseppe; Leonard, John J.; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2015)
      State-of-the-art techniques for simultaneous localization and mapping (SLAM) employ iterative nonlinear optimization methods to compute an estimate for robot poses. While these techniques often work well in practice, ...
    • Large Scale Experimental Design for Decentralized SLAM 

      Cunningham, Alexander; Dellaert, Frank (Georgia Institute of TechnologySPIE, 2012-05-01)
      This paper presents an analysis of large scale decentralized SLAM under a variety of experimental conditions to illustrate design trade-o s relevant to multi-robot mapping in challenging environments. As a part of ...
    • Large-Scale Dense 3D Reconstruction from Stereo Imagery 

      Alcantarilla, Pablo F.; Beall, Chris; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-11)
      In this paper we propose a novel method for large-scale dense 3D reconstruction from stereo imagery. Assuming that stereo camera calibration and camera motion are known, our method is able to reconstruct accurately dense ...
    • Large-Scale Image Annotation using Visual Synset 

      Tsai, David; Jing, Yushi; Liu, Yi; Rowley, Henry A.; Ioffe, Sergey; Rehg, James M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2011-11)
      We address the problem of large-scale annotation of web images. Our approach is based on the concept of visual synset, which is an organization of images which are visually-similar and semantically-related. Each ...
    • Learning and Inference in Parametric Switching Linear Dynamic Systems 

      Oh, Sang Min; Rehg, James M.; Balch, Tucker; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2005-10)
      We introduce parametric switching linear dynamic systems (P-SLDS) for learning and interpretation of parametrized motion, i.e., motion that exhibits systematic temporal and spatial variations. Our motivating example is ...
    • Learning and Inferring Motion Patterns using Parametric Segmental Switching Linear Dynamic Systems 

      Oh, Sang Min; Rehg, James M.; Balch, Tucker; Dellaert, Frank (Georgia Institute of Technology, 2006)
      Switching Linear Dynamic System (SLDS) models are a popular technique for modeling complex nonlinear dynamic systems. An SLDS has significantly more descriptive power than an HMM by using continuous hidden states. However, ...
    • Learning and Inferring Motion Patterns Using Parametric Segmental Switching Linear Dynamic Systems 

      Oh, Sang Min; Rehg, James M.; Balch, Tucker; Dellaert, Frank (Georgia Institute of TechnologySpringer Berlin / Heidelberg, 2008)
      Switching Linear Dynamic System (SLDS) models are a popular technique for modeling complex nonlinear dynamic systems. An SLDS provides the possibility to describe complex temporal patterns more concisely and accurately ...
    • Learning Contact Locations for Pushing and Orienting Unknown Objects 

      Hermans, Tucker; Li, Fuxin; Rehg, James M.; Bobick, Aaron F. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-10)
      We present a method by which a robot learns to predict effective contact locations for pushing as a function of object shape. The robot performs push experiments at many contact locations on multiple objects and records ...
    • Learning General Optical Flow Subspaces for Egomotion Estimation and Detection of Motion Anomalies 

      Roberts, Richard; Potthast, Christian; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2009)
      This paper deals with estimation of dense optical flow and ego-motion in a generalized imaging system by exploiting probabilistic linear subspace constraints on the flow. We deal with the extended motion of the imaging ...
    • Learning Sparse Covariance Patterns for Natural Scenes 

      Wang, Liwei; Li, Yin; Jia, Jiaya; Sun, Jian; Wipf, David; Rehg, James M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-06)
      For scene classification, patch-level linear features do not always work as well as hand-crafted features. In this paper, we present a new model to greatly improve the discrimination power of linear features in ...
    • Learning Stable Pushing Locations 

      Hermans, Tucker; Li, Fuxin; Rehg, James M.; Bobick, Aaron F. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-08)
      We present a method by which a robot learns to predict effective push-locations as a function of object shape. The robot performs push experiments at many contact locations on multiple objects and records local and ...
    • Learning to Recognize Daily Actions using Gaze 

      Fathi, Alireza; Li, Yin; Rehg, James M. (Georgia Institute of Technology, 2012-10)
      We present a probabilistic generative model for simultaneously recognizing daily actions and predicting gaze locations in videos recorded from an egocentric camera. We focus on activities requiring eye-hand coordination ...
    • Learning to Recognize Objects in Egocentric Activities 

      Fathi, Alireza; Ren, Xiaofeng; Rehg, James M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2011-06)
      This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know only the names of the objects which are ...
    • Learning Visibility of Landmarks for Vision-Based Localization 

      Alcantarilla, Pablo F.; Oh, Sang Min; Mariottini, Gian Luca; Bergasa, Luis M.; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2010)
      We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from the image with the map elements at the current ...
    • Leveraging Context to Support Automated Food Recognition in Restaurants 

      Bettadapura, Vinay; Thomaz, Edison; Parnam, Aman; Abowd, Gregory D.; Essa, Irfan (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2015-01)
      The pervasiveness of mobile cameras has resulted in a dramatic increase in food photos, which are pictures re- flecting what people eat. In this paper, we study how tak- ing pictures of what we eat in restaurants ...
    • Line-Based Structure From Motion for Urban Environments 

      Schindler, Grant; Krishnamurthy, Panchapagesan; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2006-06)
      We present a novel method for recovering the 3D-line structure of a scene from multiple widely separated views. Traditional optimization-based approaches to line-based structure from motion minimize the error between ...
    • Linear-Time Estimation with Tree Assumed Density Filtering and Low-Rank Approximation 

      Ta, Duy-Nguyen; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-09)
      We present two fast and memory-efficient approximate estimation methods, targeting obstacle avoidance applications on small robot platforms. Our methods avoid a main bottleneck of traditional ...
    • Linguistic Transfer of Human Assembly Tasks to Robots 

      Dantam, Neil; Essa, Irfan; Stilman, Mike (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-10)
      We demonstrate the automatic transfer of an assembly task from human to robot. This work extends efforts showing the utility of linguistic models in verifiable robot control policies by now performing real visual analysis ...
    • Loopy SAM 

      Ranganathan, Ananth; Kaess, Michael; Dellaert, Frank (Georgia Institute of TechnologyIJCAI, 2007-01)
      Smoothing approaches to the Simultaneous Localization and Mapping (SLAM) problem in robotics are superior to the more common filtering approaches in being exact, better equipped to deal with non-linearities, and computing ...
    • Map-based Priors for Localization 

      Oh, Sang Min; Tariq, Sarah; Walker, Bruce N.; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2004-09)
      Localization from sensor measurements is a fundamental task for navigation. Particle filters are among the most promising candidates to provide a robust and realtime solution to the localization problem. They instantiate the ...