Person:
Dellaert,
Frank
Dellaert,
Frank
Permanent Link
Associated Organization(s)
Organizational Unit
School of Interactive Computing
School established in 2007
ORCID
ArchiveSpace Name Record
Publication Search Results
Now showing
1 - 10 of 26
-
ItemStereo Tracking and Three-Point/One-Point Algorithms - A Robust Approach in Visual Odometry(Georgia Institute of Technology, 2006-10) Ni, Kai ; Dellaert, FrankIn this paper, we present an approach of calculating visual odometry for outdoor robots equipped with a stereo rig. Instead of the typical feature matching or tracking, we use an improved stereo-tracking method that simultaneously decides the feature displacement in both cameras. Based on the matched features, a three-point algorithm for the resulting quadrifocal setting is carried out in a RANSAC framework to recover the unknown odometry. In addition, the change in rotation can be derived from infinity homography, and the remaining translational unknowns can be obtained even faster consequently . Both approaches are quite robust and deal well with challenging conditions such as wheel slippage.
-
ItemRao-Blackwellized Importance Sampling of Camera Parameters from Simple User Input with Visibility Preprocessing in Line Space(Georgia Institute of Technology, 2006-06) Quennesson, Kevin ; Dellaert, FrankUsers 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 in 3D worlds a density of viewpoints of camera locations from high level visibility constraints on objects in this world. Our method is based on Rao-Blackwellized importance sampling. For efficiency purposes, the proposal distribution used for sampling is extracted from a visibility preprocessing technique adapted from computer graphics. We apply the method for finding in a 3D city model of Atlanta the virtual locations of real-world cameras and viewpoints.
-
ItemA Rao-Blackwellized Particle Filter for Topological Mapping(Georgia Institute of Technology, 2006-05) Ranganathan, Ananth ; Dellaert, FrankWe 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, and is based on our previous work on a Bayesian inference framework for topological maps [21]. Constructing the posterior solves the perceptual aliasing problem in a general, robust manner. The use of a Rao-Blackwellized Particle Filter (RBPF) for this purpose makes the inference in the space of topologies incremental and run in real-time. The RBPF maintains the joint posterior on topological maps and locations of landmarks. We demonstrate that, using the landmark locations thus obtained, the global metric map can be obtained from the topological map generated by our algorithm through a simple post-processing step. A data-driven proposal is provided to overcome the degeneracy problem inherent in particle filters. The use of a Dirichlet process prior on landmark labels is also a novel aspect of this work. We use laser range scan and odometry measurements to present experimental results on a robot.
-
ItemOn-line Learning of the Traversability of Unstructured Terrain for Outdoor Robot Navigation(Georgia Institute of Technology, 2006) Oh, Sang Min ; Rehg, James M. ; Dellaert, Frank
-
ItemSquare Root SAM Simultaneous Localization and Mapping via Square Root Information Smoothing(Georgia Institute of Technology, 2006) Dellaert, Frank ; Kaess, MichaelSolving the SLAM problem is one way to enable a robot to explore, map, and navigate in a previously unknown environment. We investigate smoothing approaches as a viable alternative to extended Kalman filter-based solutions to the problem. In particular, we look at approaches that factorize either the associated information matrix or the measurement Jacobian into square root form. Such techniques have several significant advantages over the EKF: they are faster yet exact, they can be used in either batch or incremental mode, are better equipped to deal with non-linear process and measurement models, and yield the entire robot trajectory, at lower cost for a large class of SLAM problems. In addition, in an indirect but dramatic way, column ordering heuristics automatically exploit the locality inherent in the geographic nature of the SLAM problem. In this paper we present the theory underlying these methods, along with an interpretation of factorization in terms of the graphical model associated with the SLAM problem. We present both simulation results and actual SLAM experiments in large-scale environments that underscore the potential of these methods as an alternative to EKF-based approaches.
-
ItemData-Driven MCMC for Learning and Inference in Switching Linear Dynamic Systems(Georgia Institute of Technology, 2005-07) Oh, Sang Min ; Rehg, James M. ; Balch, Tucker ; Dellaert, FrankSwitching 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, but inference in SLDS models is computationally intractable. This paper describes a novel inference algorithm for SLDS models based on the Data- Driven MCMC paradigm. We describe a new proposal distribution which substantially increases the convergence speed. Comparisons to standard deterministic approximation methods demonstrate the improved accuracy of our new approach. We apply our approach to the problem of learning an SLDS model of the bee dance. Honeybees communicate the location and distance to food sources through a dance that takes place within the hive. We learn SLDS model parameters from tracking data which is automatically extracted from video. We then demonstrate the ability to successfully segment novel bee dances into their constituent parts, effectively decoding the dance of the bees.
-
ItemMixture Trees for Modeling and Fast Conditional Sampling with Applications in Vision and Graphics(Georgia Institute of Technology, 2005-06) Dellaert, Frank ; Kwatra, Vivek ; Oh, Sang MinWe introduce mixture trees, a tree-based data-structure for modeling joint probability densities using a greedy hierarchical density estimation scheme. We show that the mixture tree models data efficiently at multiple resolutions, and present fast conditional sampling as one of many possible applications. In particular, the development of this datastructure was spurred by a multi-target tracking application, where memory-based motion modeling calls for fast conditional sampling from large empirical densities. However, it is also suited to applications such as texture synthesis, where conditional densities play a central role. Results will be presented for both these applications.
-
ItemA Multi-Camera Pose Tracker for Assisting the Visually Impaired(Georgia Institute of Technology, 2005-06) Dellaert, Frank ; Tariq, Sarah6DOF Pose tracking is useful in many contexts, e.g., in augmented reality (AR) applications. In particular, we seek to assist visually impaired persons by providing them with an auditory interface to their environment through sonification. For this purpose, accurate head tracking in mixed indoor/outdoor settings is the key enabling technology. Most of the work to date has concentrated on single-camera systems with a relatively small field of view, but this presents a fundamental limit on the accuracy of such systems. We present a multi-camera pose tracker that handles an arbitrary configuration of cameras rigidly fixed to the object of interest. By using multiple cameras, we increase both the robustness and the accuracy by which a 6-DOF pose is tracked. However, in a multi-camera rig setting, earlier methods for determining the unknown pose from three world-to-camera correspondences are no longer applicable, as they all assume a common center of projection. In this paper, we present a RANSAC-based method that copes with this limitation and handles multi-camera rigs. In addition, we present quantitative results to serve as a design guide for full system deployments based on multi-camera rigs. Our formulation is completely general, in that it handles an arbitrary, heterogeneous collection of cameras in any arbitrary configuration.
-
ItemWhat Are the Ants Doing? Vision-Based Tracking and Reconstruction of Control Programs(Georgia Institute of Technology, 2005-04) Balch, Tucker ; Dellaert, Frank ; Delmotte, Florent ; Khan, Zia ; Egerstedt, Magnus B.In this paper, we study the problem of going from a real-world, multi-agent system to the generation of control programs in an automatic fashion. In particular, a computer vision system is presented, capable of simultaneously tracking multiple agents, such as social insects. Moreover, the data obtained from this system is fed into a mode-reconstruction module that generates low-complexity control programs, i.e. strings of symbolic descriptions of control-interrupt pairs, consistent with the empirical data. The result is a mechanism for going from the real system to an executable implementation that can be used for controlling multiple mobile robots.
-
ItemA Markov Chain Monte Carlo Approach to Closing the Loop in SLAM(Georgia Institute of Technology, 2005-04) Kaess, Michael ; Dellaert, FrankThe problem of simultaneous localization and mapping has received much attention over the last years. Especially large scale environments, where the robot trajectory loops back on itself, are a challenge. In this paper we introduce a new solution to this problem of closing the loop. Our algorithm is EM-based, but differs from previous work. The key is a probability distribution over partitions of feature tracks that is determined in the E-step, based on the current estimate of the motion. This virtual structure is then used in the M-step to obtain a better estimate for the motion. We demonstrate the success of our algorithm in experiments on real laser data.
- «
- 1 (current)
- 2
- 3
- »