Now showing items 72-91 of 211

    • Generalized Subgraph Preconditioners for Large-Scale Bundle Adjustment 

      Jian, Yong-Dian; Balcan, Doru C.; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2011-11)
      We present a generalized subgraph preconditioning (GSP) technique to solve large-scale bundle adjustment problems efficiently. In contrast with previous work which uses either direct or iterative methods as the linear ...
    • Geometric Context from Videos 

      Raza, S. Hussain; Grundmann, Matthias; Essa, Irfan A. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-06)
      We present a novel algorithm for estimating the broad 3D geometric structure of outdoor video scenes. Leveraging spatio-temporal video segmentation, we decompose a dynamic scene captured by a video into geometric ...
    • The Georgia Tech Yellow Jackets: A Marsupial Team for Urban Search and Rescue 

      Dellaert, Frank; Balch, Tucker; Kaess, Michael; Ravichandran, Ram; Alegre, Fernando; Berhault, Marc; McGuire, Robert; Merrill, Ernest; Moshkina, Lilia; Walker, Daniel (Georgia Institute of TechnologyAAAI Press, 2002)
      We describe our entry in the AAAI 2002 Urban Search and Rescue (USAR) competition, a marsupial team consisting of a larger wheeled robot and several small legged robots, carried around by the larger robot. This setup ...
    • Grammatical Methods in Computer Vision: An Overview 

      Chanda, Gaurav; Dellaert, Frank (Georgia Institute of Technology, 2004)
      We review various methods and applications that have used grammars for solving inference problems in computer vision and pattern recognition. Grammars have been useful because they are intuitively simple to understand, and ...
    • GroupSAC: Efficient Consensus in the Presence of Groupings 

      Ni, Kai; Jin, Hailin; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2009-09)
      We present a novel variant of the RANSAC algorithm that is much more efficient, in particular when dealing with problems with low inlier ratios. Our algorithm assumes that there exists some grouping in the data, based ...
    • Guided Pushing for Object Singulation 

      Hermans, Tucker; Rehg, James M.; Bobick, Aaron (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-10)
      We propose a novel method for a robot to separate and segment objects in a cluttered tabletop environment. The method leverages the fact that external object boundaries produce visible edges within an object cluster. ...
    • Haptic Classification and Recognition of Objects Using a Tactile Sensing Forearm 

      Bhattacharjee, Tapomayukh; Rehg, James M.; Kemp, Charles C. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-10)
      In this paper, we demonstrate data-driven inference of mechanical properties of objects using a tactile sensor array (skin) covering a robot’s forearm. We focus on the mobility (sliding vs. fixed), compliance (soft vs. ...
    • A Hierarchical Wavelet Decomposition for Continuous-Time SLAM 

      Anderson, Sean; Dellaert, Frank; Barfoot, Timothy D. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014)
      This paper proposes using hierarchical wavelets as a basis in parametric continuous-time batch estimation. The need for a continuous-time robot pose in the simultaneous localization and mapping (SLAM) problem has arisen ...
    • How A.I. and multi-robot systems research will accelerate our understanding of social animal behavior 

      Balch, Tucker; Dellaert, Frank; Feldman, Adam; Guillory, Andrew; Isbell, Charles; Khan, Zia; Pratt, Stephen; Stein, Andrew; Wilde, Hank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2006-07)
      Our understanding of social insect behavior has significantly influenced A.I. and multi-robot systems’ research (e.g. ant algorithms and swarm robotics). In this work, however, we focus on the opposite question, namely: ...
    • HyperSfM 

      Ni, Kai; Dellaert, Frank (Georgia Institute of Technology, 2012-10)
      We propose a novel algorithm that solves the Structure from Motion problem in a divide and conquer manner by exploiting its bipartite graph structure. Recursive partitioning has a rich history, stemming from sparse ...
    • An Image Based Approach to Recovering the Gravitational Field of Asteroids 

      Melim, Andrew; Dellaert, Frank (Georgia Institute of TechnologyBritish Machine Vision Association, 2014)
      NASA’s DAWN spacecraft is on a mission to recover the gravity and structure of the asteroids Vesta and Ceres. Current approaches for developing a gravitational map of a celestial body rely upon use of the Deep ...
    • IMU Preintegration on Manifold for Efficient Visual-Inertial Maximum-a-Posteriori Estimation 

      Forster, Christian; Carlone, Luca; Dellaert, Frank; Scaramuzza, Davide (Georgia Institute of Technology, 2015)
      Recent results in monocular visual-inertial navigation (VIN) have shown that optimization-based approaches outperform filtering methods in terms of accuracy due to their capability to relinearize past states. However, the ...
    • An In Depth View of Saliency 

      Ciptadi, Arridhana; Hermans, Tucker; Rehg, James M. (Georgia Institute of Technology, 2013-09)
      Visual saliency is a computational process that identifies important locations and structure in the visual field. Most current methods for saliency rely on cues such as color and texture while ignoring depth information, ...
    • Incremental Distributed Robust Inference from Arbitrary Robot Poses via EM and Model Selection 

      Indelman, Vadim; Michael, Nathan; Dellaert, Frank (Georgia Institute of Technology, 2014-07)
      We present a novel approach for multi-robot distributed and incremental inference over variables of interest, such as robot trajectories, considering the initial relative poses between the robots and multi-robot data ...
    • Incremental Light Bundle Adjustment 

      Indelman, Vadim; Roberts, Richard; Beall, Chris; Dellaert, Frank (Georgia Institute of Technology, 2012-09)
      Fast and reliable bundle adjustment is essential in many applications such as mobile vision, augmented reality, and robotics. Two recent ideas to reduce the associated computational cost are structure-less SFM (structure ...
    • Incremental Light Bundle Adjustment for Robotics Navigation 

      Indelman, Vadim; Melim, Andrew; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-11)
      This paper presents a new computationally-efficient method for vision-aided navigation (VAN) in autonomous robotic applications. While many VAN approaches are capable of processing incoming visual observations, incorporating ...
    • Incremental Light Bundle Adjustment for Structure From Motion and Robotics 

      Indelman, Vadim; Roberts, Richard; Dellaert, Frank (Georgia Institute of TechnologyElsevier B.V., 2015)
      Bundle adjustment (BA) is essential in many robotics and structure-from-motion applications. In robotics, often a bundle adjustment solution is desired to be available incrementally as new poses and 3D points are observed. ...
    • Incremental Sparse GP Regression for Continuous-time Trajectory Estimation & Mapping 

      Yan, Xinyan; Indelman, Vadim; Boots, Byron (Georgia Institute of Technology, 2015-09)
      Recent work on simultaneous trajectory estimation and mapping (STEAM) for mobile robots has found success by representing the trajectory as a Gaussian process. Gaussian processes can represent a continuous-time trajectory, ...
    • Incremental Sparse GP Regression for Continuous-time Trajectory Estimation & Mapping 

      Yan, Xinyan; Indelman, Vadim; Boots, Byron (Georgia Institute of Technology, 2015-07)
      Recent work on simultaneous trajectory estimation and mapping (STEAM) for mobile robots has found success by representing the trajectory as a Gaussian process. Gaussian processes can represent a ...
    • Incremental Sparse GP Regression for Continuous-time Trajectory Estimation & Mapping 

      Yan, Xinyan; Indelman, Vadim; Boots, Byron (Georgia Institute of Technology, 2014-12)
      Recent work has investigated the problem of continuous-time trajectory estimation and mapping for mobile robots by formulating the problem as sparse Gaussian process regression. Gaussian processes provide a continuous-time ...