Now showing items 54-73 of 211

    • Efficient and Effective Visual Codebook Generation Using Additive Kernels 

      Wu, Jianxin; Tan, Wei-Chian; Rehg, James M. (Georgia Institute of Technology, 2011-11)
      Common visual codebook generation methods used in a bag of visual words model, for example, k-means or Gaussian Mixture Model, use the Euclidean distance to cluster features into visual code words. However, most popular ...
    • Efficient Hierarchical Graph-Based Segmentation of RGBD Videos 

      Hickson, Steven; Birchfield, Stan; Essa, Irfan; Christensen, Henrik I. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-06)
      We present an efficient and scalable algorithm for segmenting 3D RGBD point clouds by combining depth, color, and temporal information using a multistage, hierarchical graph-based approach. Our algorithm processes a moving ...
    • Efficient Hierarchical Graph-Based Video Segmentation 

      Grundmann, Matthias; Kwatra, Vivek; Han, Mei; Essa, Irfan (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2010-06)
      We present an efficient and scalable technique for spatiotemporal segmentation of long video sequences using a hierarchical graph-based algorithm. We begin by oversegmenting a volumetric video graph into space-time ...
    • Efficient Particle Filter-Based Tracking of Multiple Interacting Targets Using an MRF-based Motion Model 

      Khan, Zia; Balch, Tucker; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2003-10)
      We describe a multiple hypothesis particle filter for tracking targets that will be influenced by the proximity and/or behavior of other targets. Our contribution is to show how a Markov random field motion prior, built ...
    • Egocentric Field-of-View Localization Using First-Person Point-of-View Devices 

      Bettadapura, Vinay; Essa, Irfan; Pantofaru, Caroline (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2015-01)
      We present a technique that uses images, videos and sensor data taken from first-person point-of-view devices to perform egocentric field-of-view (FOV) localization. We define egocentric FOV localization as capturing the ...
    • Eliminating Conditionally Independent Sets in Factor Graphs: A Unifying Perspective based on Smart Factors 

      Carlone, Luca; Kira, Zsolt; Beall, Chris; Indelman, Vadim; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014)
      Factor graphs are a general estimation framework that has been widely used in computer vision and robotics. In several classes of problems a natural partition arises among variables involved in the estimation. ...
    • EM, MCMC, and Chain Flipping for Structure from Motion with Unknown Correspondence 

      Dellaert, Frank; Seitz, Steven M.; Thorpe, Charles E.; Thrun, Sebastian (Georgia Institute of TechnologyKluwer Academic Publishers, 2003)
      Learning spatial models from sensor data raises the challenging data association problem of relating model parameters to individual measurements. This paper proposes an EM-based algorithm, which solves the model learning ...
    • The Expectation Maximization Algorithm 

      Dellaert, Frank (Georgia Institute of Technology, 2002)
      This note represents my attempt at explaining the EM algorithm. This is just a slight variation on Tom Minka's tutorial, perhaps a little easier (or perhaps not). It includes a graphical example to provide some intuition.
    • An Experimental Study of Robust Distributed Multi-Robot Data Association from Arbitrary Poses 

      Nelson, Erik; Indelman, Vadim; Michael, Nathan; Dellaert, Frank (Georgia Institute of Technology, 2014-06)
      In this work, we experimentally investigate the problem of computing the relative transformation between multiple vehicles from corresponding interrobot observations during autonomous operation in a common unknown ...
    • Exploiting Locality in SLAM by Nested Dissection 

      Krauthausen, Peter; Kipp, Alexander; Dellaert, Frank (Georgia Institute of TechnologyMIT Press, 2006-08)
      The computational complexity of SLAM is dominated by the cost of factorizing a matrix derived from the measurements into a square root form, which has cubic complexity in the worst case. However, the matrices associated ...
    • A Factor Graph Approach to Estimation and Model Predictive Control on Unmanned Aerial Vehicles 

      Ta, Duy-Nguyen; Kobilarov, Marin; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-05)
      n this paper, we present a factor graph framework to solve both estimation and deterministic optimal control problems, and apply it to an obstacle avoidance task on Unmanned Aerial Vehicles (UAVs). We show that factor ...
    • Factor Graph Based Incremental Smoothing in Inertial Navigation Systems 

      Indelman, Vadim; Williams, Stephen; Kaess, Michael; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-07)
      This paper describes a new approach for information fusion in inertial navigation systems. In contrast to the commonly used filtering techniques, the proposed approach is based on a non-linear optimization for processing ...
    • Fast 3D Pose Estimation With Out-of-Sequence Measurements 

      Ranganathan, Ananth; Kaess, Michael; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2007-10)
      We present an algorithm for pose estimation using fixed-lag smoothing. We show that fixed-lag smoothing enables inclusion of measurements from multiple asynchronous measurement sources in an optimal manner. Since ...
    • Fast Incremental Square Root Information Smoothing 

      Kaess, Michael; Ranganathan, Ananth; Dellaert, Frank (Georgia Institute of TechnologyIJCAI, 2007-01)
      We propose a novel approach to the problem of simultaneous localization and mapping (SLAM) based on incremental smoothing, that is suitable for real-time applications in large-scale environments. The main advantages ...
    • Feasibility of Identifying Eating Moments from First-Person Images Leveraging Human Computation 

      Thomaz, Edison; Parnami, Aman; Essa, Irfan; Abowd, Gregory D. (Georgia Institute of TechnologyAssociation for Computing Machinery, 2013-11)
      There is widespread agreement in the medical research community that more effective mechanisms for dietary assessment and food journaling are needed to fight back against obesity and other nutrition-related diseases. ...
    • Flow Separation for Fast and Robust Stereo Odometry 

      Kaess, Michael; Ni, Kai; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2009-05)
      Separating sparse flow provides fast and robust stereo visual odometry that deals with nearly degenerate situations that often arise in practical applications.We make use of the fact that in outdoor situations different ...
    • Fully Distributed Scalable Smoothing and Mapping with Robust Multi-robot Data Association 

      Cunningham, Alexander; Wurm, Kai M.; Burgard, Wolfram; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2012-05)
      In this paper we focus on the multi-robot perception problem, and present an experimentally validated endto- end multi-robot mapping framework, enabling individual robots in a team to see beyond their individual sensor ...
    • Gaussian Process Regression Flow for Analysis of Motion Trajectories 

      Kim, Kihwan; Lee, Dongryeol; Essa, Irfan (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2011-11)
      Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new representation specifically aimed at ...
    • 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 ...