Search

Articulated motion analysis often utilizes strong prior knowledge such as a known or trained parts model for humans. Yet, the world contains a variety of articulating objects--mammals, insects, mechanized structures--where the number and configuration of parts for a particular object is unknown in advance. Here, we relax such strong assumptions via an unsupervised, Bayesian nonparametric parts model that infers an unknown number of parts with motions coupled by a body dynamic and parameterized by SE(D), the Lie group of rigid transformations. We derive an inference procedure that utilizes short observation sequences (image, depth, point cloud or mesh) of an object in motion without need for markers or learned body models. Efficient Gibbs decompositions for inference over distributions on SE(D) demonstrate robust part decompositions of moving objects under both 3D and 2D observation models. The inferred representation permits novel analysis, such as object segmentation by relative part motion, and transfers to new observations of the same object type.

Consider a particular finite-time disturbance applied to a system governed by ordinary differential equations and which possesses a stable equilibrium point. The recovery of the system from a disturbance is a function of the system parameter values. It is an important though challenging problem to identify the system parameter values, called critical parameter values, for which the system is just marginally unable to recover from a particular disturbance. Such critical parameter values correspond to cases where the system state, at the instant when the disturbance clears, is on the boundary of the region of attraction of the stable equilibrium point. The paper proposes novel algorithms for numerically computing critical parameter values, both for one and arbitrary dimensional parameter spaces. In the latter case, the algorithm computes the critical parameter values that are nearest to a given point in parameter space. The key idea underpinning the algorithms is that on the boundary of the region of attraction, the trajectory becomes infinitely sensitive to small changes in parameter value. Therefore, critical parameter values are found by varying parameters so as to maximize trajectory sensitivities. The algorithms are demonstrated using a fourth-order power system test case.

The ability of a nonlinear system to recover from a large disturbance to a desired stable equilibrium point depends on system parameter values, which are often uncertain and time varying. A particular disturbance acting for a finite time can be modeled as an implicit map that takes a parameter value to its corresponding post-disturbance initial condition in state space. The system recovers when the post-disturbance initial condition lies inside the region of attraction of the stable equilibrium point. Critical parameter values are defined to be parameter values whose corresponding post-disturbance initial condition lies on the boundary of the region of attraction. Computing such values is important in numerous applications because they represent the boundary between desirable and undesirable system behavior. Many realistic system models involve controller clipping limits and other forms of switching. Furthermore, these hybrid dynamics are closely linked to the ability of a system to recover from disturbances. The paper develops theory which underpins a novel algorithm for numerically computing critical parameter values for nonlinear systems with clipping limits and switching. For an almost generic class of vector fields with event-selected discontinuities, it is shown that the boundary of the region of attraction is equal to a union of the stable manifolds of the equilibria and periodic orbits it contains, and that this decomposition persists and the boundary varies continuously under small changes in parameter.

Soft actuators with auxetic, or negative Poisson's ratio (NPR), behavior offer a way to create soft robots with novel kinematic behavior. This paper presents an original framework for reinforcement of a soft actuator using a generalized NPR element, called a Representative Auxetic Element (RAE), and an experimental validation of the kinematic behavior that it enables. We build a generalized kinematic model that enables the design of RAE-patterned actuators and reveal the distinct auxetic behavior of RAE actuators with comparable model accuracy to the legacy McKibben actuators. A simple, reproducible way of designing and fabricating RAE actuators is described and varied prototypes are shown. This RAE-based design scheme can be used to create actuators with specified kinematics like bending, extension, and radial expansion, which can also vary across the actuator's surface both circumferentially and axially in a tractable, scalable manner.

For a given power system disturbance, it is useful to determine the critical parameter values that cause the resulting trajectory to lie exactly on the boundary (in state space) of the region of attraction of the operating point. These critical parameter values form the boundary, in parameter space, between sets of parameter values for which the system recovers to its original stable operating point, and sets of parameter values for which it does not. The paper presents an algorithm for numerically computing critical parameter values and their associated boundaries in parameter space by exploiting the presence of a controlling unstable equilibrium point (CUEP) on the boundary of the operating point's region of attraction. The key idea is to vary a parameter value in such a way as to maximize the time spent by the trajectory in a ball centred at the CUEP. This will drive parameter values to their critical values. The algorithm is demonstrated on a test case where it is used to find the critical amount of inertia in the network such that the system is marginally able to recover from a particular fault. It is also used to numerically trace a curve of critical parameter values given by varying the moments of inertia for a pair of generators.

© 2018 IEEE. When performing multi-robot tasks, sensory feedback is crucial in reducing uncertainty for correct execution. Yet the utilization of sensors should be planned as an integral part of the task planning, taken into account several factors such as the tolerance of different inferred properties of the scene and interaction with different agents. In this paper we handle this complex problem in a principled, yet efficient way. We use surrogate predictors based on open-loop simulation to estimate and bound the probability of success for specific tasks. We reason about such task-specific uncertainty approximants and their effectiveness. We show how they can be incorporated into a multi-robot planner, and demonstrate results with a team of robots performing assembly tasks.

This paper considers a system of ordinary differential equations subject to a parameter-dependent disturbance. The goal is to find the boundary in parameter space between parameter values for which the system will recover from the disturbance to a desired stable equilibrium point, and parameter values for which it will not recover. If the system state when the disturbance clears, call it the initial condition, depends continuously on parameter value, then it seems plausible that this parameter space boundary would consist of parameter values whose corresponding initial conditions lie on the boundary of the region of attraction (RoA) of the desired stable equilibrium point (SEP). Unfortunately, this is not true in general since, even when the system's vector field varies smoothly with parameter value, the boundary of the RoA of the SEP may not vary even continuously with respect to small parameter variations. This work shows that, for a large class of vector fields which generalize Morse-Smale vector fields, the RoA boundary varies continuously in an appropriate sense with respect to small parameter variations. Furthermore, it has been shown elsewhere that the RoA boundary for these vector fields is equal to the union of the stable manifolds of the equilibria and periodic orbits they contain. A complete argument is provided here that this decomposition into stable manifolds persists under small changes in parameter for the vector fields under consideration. The above results are applied to provide a theoretical basis for a numerical algorithm which computes parameter values which lie on the desired parameter space boundary.

© 2017 IEEE. Point cloud alignment is a common problem in computer vision and robotics, with applications ranging from 3D object recognition to reconstruction. We propose a novel approach to the alignment problem that utilizes Bayesian non-parametrics to describe the point cloud and surface normal densities, and branch and bound (BB) optimization to recover the relative transformation. BB uses a novel, refinable, near-uniform tessellation of rotation space using 4D tetrahedra, leading to more efficient optimization compared to the common axis-angle tessellation. We provide objective function bounds for pruning given the proposed tessellation, and prove that BB converges to the optimum of the cost function along with providing its computational complexity. Finally, we empirically demonstrate the efficiency of the proposed approach as well as its robustness to real-world conditions such as missing data and partial overlap.

The advent of widely available photo collections covering broad geographic areas has spurred significant advances in large-scale urban scene modeling. While much emphasis has been placed on reconstruction and visualization, the utility of such models extends well beyond. Specifically, these models should support a wide variety of reasoning tasks (or queries), and thus enable advanced scene study. Driven by this interest, we analyze 3D representations for their utility to perform queries. Since representations as well as queries are highly heterogeneous, we build on a categorization that serves as a coupling interface between both domains. Equipped with our taxonomy and the notion of uncertainty in the representation, we quantify the utility of representations for solving three archetypal reasoning tasks in terms of accuracy, uncertainty and computational complexity. We provide an empirical analysis of these intertwined realms on challenging real and synthetic urban scenes.

Sensor planning and active sensing, long studied in robotics, adapt sensor parameters to maximize a utility function while constraining resource expenditures. Here we consider information gain as the utility function. While these concepts are often used to reason about 3D sensors, these are usually treated as a predefined, black-box, component. In this paper we show how the same principles can be used as part of the 3D sensor. We describe the relevant generative model for structured-light 3D scanning and show how adaptive pattern selection can maximize information gain in an open-loop-feedback manner. We then demonstrate how different choices of relevant variable sets (corresponding to the subproblems of locatization and mapping) lead to different criteria for pattern selection and can be computed in an online fashion. We show results for both subproblems with several pattern dictionary choices and demonstrate their usefulness for pose estimation and depth acquisition., United States. Office of Naval Research (Grant N00014-09-1-1051), United States. Army Research Office (Grant W911NF-11- 1-0391), United States. Office of Naval Research (Grant N00014- 11-1-0688)

We consider a methodology for integrating multiple sensors along with semantic information to enhance scene representations. We propose a probabilistic generative model for inferring semantically-informed aerial reconstructions from multi-modal data within a consistent mathematical framework. The approach, called Semantically-Aware Aerial Reconstruction (SAAR), not only exploits inferred scene geometry, appearance, and semantic observations to obtain a meaningful categorization of the data, but also extends previously proposed methods by imposing structure on the prior over geometry, appearance, and semantic labels. This leads to more accurate reconstructions and the ability to fill in missing contextual labels via joint sensor and semantic information. We introduce a new multi-modal synthetic dataset in order to provide quantitative performance analysis. Additionally, we apply the model to real-world data and exploit OpenStreetMap as a source of semantic observations. We show quantitative improvements in reconstruction accuracy of large-scale urban scenes from the combination of LiDAR, aerial photography, and semantic data. Furthermore, we demonstrate the model's ability to fill in for missing sensed data, leading to more interpretable reconstructions.

Superpixel segmentation is a key step in many image processing and vision tasks. Our recently-proposed connectivity-constrained probabilistic model [1] yields high-quality super-pixels. Seemingly, however, connectivity constraints preclude parallelized inference. As such, the implementation from [1] is serial. The contributions of this work are as follows. First, we demonstrate that effective parallelization is possible via a fast GPU implementation that scales gracefully with both the number of pixels and number of superpixels. Second, we show that the superpixels are improved by replacing the fixed and restricted spatial covariances from [1] with a flexible Bayesian prior. Quantitative evaluation on public benchmarks shows the proposed method outperforms the state-of-the-art. We make our implementation publicly available.

Structural regularities in man-made environments reflect in the distribution of their surface normals. Describing these surface normal distributions is important in many computer vision applications, such as scene understanding, plane segmentation, and regularization of 3D reconstructions. Based on the small-variance limit of Bayesian nonparametric von-Mises-Fisher (vMF) mixture distributions, we propose two new flexible and efficient k-means-like clustering algorithms for directional data such as surface normals. The first, DP-vMF-means, is a batch clustering algorithm derived from the Dirichlet process (DP) vMF mixture. Recognizing the sequential nature of data collection in many applications, we extend this algorithm to DDP-vMF-means, which infers temporally evolving cluster structure from streaming data. Both algorithms naturally respect the geometry of directional data, which lies on the unit sphere. We demonstrate their performance on synthetic directional data and real 3D surface normals from RGB-D sensors. While our experiments focus on 3D data, both algorithms generalize to high dimensional directional data such as protein backbone configurations and semantic word vectors., United States. Office of Naval Research. Multidisciplinary University Research Initiative (Grant N00014- 11-1-0688), United States. Army Research Office. Multidisciplinary University Research Initiative (Grant W911NF-11-1-0391)

We analyze the complexity of evaluating information rewards for measurement selection in sparse graphical models under the assumption that measurements are drawn from a limited number of nodes subject to a finite budget. Previous analyses [1, 2, 3] exploit the submodular property of conditional mutual information to demonstrate that greedy measurement selection come with near-optimal guarantees As noted in [4] typical formulations assume oracle value models. However, [1, 2, 5] allude to a more significant source of complexity, namely computing the measurement reward. Here, we focus on Gaussian models and show that by exploiting sparsity in the measurement model, the complexity of planning is substantially reduced. We also demonstrate that by utilizing the information form additional significant reductions in complexity may be realized.

The development of hydraulic fracturing technology has dramatically increased the supply and lowered the cost of natural gas in the United States, driving an expansion of natural gas-fired generation capacity in several electrical inter-connections. Gas-fired generators have the capability to ramp quickly and are often utilized by grid operators to balance intermittency caused by wind generation. The time-varying output of these generators results in time-varying natural gas consumption rates that impact the pressure and line-pack of the gas network. As gas system operators assume nearly constant gas consumption when estimating pipeline transfer capacity and for planning operations, such fluctuations are a source of risk to their system. Here, we develop a new method to assess this risk. We consider a model of gas networks with consumption modeled through two components: forecasted consumption and small spatio-temporarily varying consumption due to the gas-fired generators being used to balance wind. While the forecasted consumption is globally balanced over longer time scales, the fluctuating consumption causes pressure fluctuations in the gas system to grow diffusively in time with a diffusion rate sensitive to the steady but spatially-inhomogeneous forecasted distribution of mass flow. To motivate our approach, we analyze the effect of fluctuating gas consumption on a model of the Transco gas pipeline that extends from the Gulf of Mexico to the Northeast of the United States., Comment: 10 pages, 7 figures

We propose an integrated probabilistic model for multi-modal fusion of aerial imagery, LiDAR data, and (optional) GPS measurements. The model allows for analysis and dense reconstruction (in terms of both geometry and appearance) of large 3D scenes. An advantage of the approach is that it explicitly models uncertainty and allows for missing data. As compared with image-based methods, dense reconstructions of complex urban scenes are feasible with fewer observations. Moreover, the proposed model allows one to estimate absolute scale and orientation and reason about other aspects of the scene, e.g., detection of moving objects. As formulated, the model lends itself to massively-parallel computing. We exploit this in an efficient inference scheme that utilizes both general purpose and domain-specific hardware components. We demonstrate results on large-scale reconstruction of urban terrain from LiDAR and aerial photography data.

Objects and structures within man-made environments typically exhibit a high degree of organization in the form of orthogonal and parallel planes. Traditional approaches to scene representation exploit this phenomenon via the somewhat restrictive assumption that every plane is perpendicular to one of the axes of a single coordinate system. Known as the Manhattan-World model, this assumption is widely used in computer vision and robotics. The complexity of many real-world scenes, however, necessitates a more flexible model. We propose a novel probabilistic model that describes the world as a mixture of Manhattan frames: each frame defines a different orthogonal coordinate system. This results in a more expressive model that still exploits the orthogonality constraints. We propose an adaptive Markov-Chain Monte-Carlo sampling algorithm with Metropolis-Hastings split/merge moves that utilizes the geometry of the unit sphere. We demonstrate the versatility of our Mixture-of-Manhattan-Frames model by describing complex scenes using depth images of indoor scenes as well as aerial-LiDAR measurements of an urban center. Additionally, we show that the model lends itself to focal-length calibration of depth cameras and to plane segmentation., United States. Office of Naval Research. Multidisciplinary University Research Initiative (Award N00014-11-1-0688), United States. Defense Advanced Research Projects Agency (Award FA8650-11-1-7154), Technion, Israel Institute of Technology (MIT Postdoctoral Fellowship Program)

We present an integrated probabilistic model for layered object tracking that combines dynamics on implicit shape representations, topological shape constraints, adaptive appearance models, and layered flow. The generative model combines the evolution of appearances and layer shapes with a Gaussian process flow and explicit layer ordering. Efficient MCMC sampling algorithms are developed to enable a particle filtering approach while reasoning about the distribution of object boundaries in video. We demonstrate the utility of the proposed tracking algorithm on a wide variety of video sources while achieving state-of-the-art results on a boundary-accurate tracking dataset.

We develop a generative probabilistic model for temporally consistent super pixels in video sequences. In contrast to supermodel methods, object parts in different frames are tracked by the same temporal super pixel. We explicitly model flow between frames with a bilateral Gaussian process and use this information to propagate super pixels in an online fashion. We consider four novel metrics to quantify performance of a temporal super pixel representation and demonstrate superior performance when compared to supermodel methods.

Sampling from distributions of implicitly defined shapes enables analysis of various energy functionals used for image segmentation. Recent work [1] describes a computationally efficient Metropolis- Hastings method for accomplishing this task. Here, we extend that framework so that samples are accepted at every iteration of the sampler, achieving an order of magnitude speed up in convergence. Additionally, we show how to incorporate topological constraints.

Optimal measurement selection for inference is combinatorially complex and intractable for large scale problems. Under mild technical conditions, it has been proven that greedy heuristics combined with conditional mutual information rewards achieve performance within a factor of the optimal. Here we provide conditions under which cost-penalized mutual information may achieve similar guarantees. Specifically, if the cost of a measurement is proportional to the information it conveys, the bounds proven in [4] and [10] still apply.

We present a new generative image model, integrating techniques arising from two different domains: manifold modeling and Markov random fields. First, we develop a probabilistic model with a mixture of hyperplanes to approximate the manifold of orientable image patches, and demonstrate that it is more effective than the field of experts in expressing local texture patterns. Next, we develop a construction that yields an MRF for coherent image generation, given a configuration of local patch models, and thereby establish a prior distribution over an MRF space. Taking advantage of the model structure, we derive a variational inference algorithm, and apply it to low-level vision. In contrast to previous methods that rely on a single MRF, the method infers an approximate posterior distribution of MRFs, and recovers the underlying images by combining the predictions in a Bayesian fashion. Experiments quantitatively demonstrate superior performance as compared to state-of-the-art methods on image denoising and inpainting.

Markov random fields play a central role in solving a variety of low level vision problems, including denoising, in-painting, segmentation, and motion estimation. Much previous work was based on MRFs with hand-crafted networks, yet the underlying graphical structure is rarely explored. In this paper, we show that if appropriately estimated, the MRF's graphical structure, which captures significant information about appearance and motion, can provide crucial guidance to low level vision tasks. Motivated by this observation, we propose a principled framework to solve low level vision tasks via an exponential family of MRFs with variable structures, which we call Switchable MRFs. The approach explicitly seeks a structure that optimally adapts to the image or video along the pursuit of task-specific goals. Through theoretical analysis and experimental study, we demonstrate that the proposed method addresses a number of drawbacks suffered by previous methods, including failure to capture heavy-tail statistics, computational difficulties, and lack of generality.

We present a method for sampling from the posterior distribution of implicitly defined segmentations conditioned on the observed image. Segmentation is often formulated as an energy minimization or statistical inference problem in which either the optimal or most probable configuration is the goal. Exponentiating the negative energy functional provides a Bayesian interpretation in which the solutions are equivalent. Sampling methods enable evaluation of distribution properties that characterize the solution space via the computation of marginal event probabilities. We develop a Metropolis-Hastings sampling algorithm over level-sets which improves upon previous methods by allowing for topological changes while simultaneously decreasing computational times by orders of magnitude. An M-ary extension to the method is provided.

We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local motion, we primarily aim at inferring a global model of persistent and collective dynamics. With this in mind, we first introduce the concept of geometric flow that describes motion simultaneously over space and time, and derive a vector space representation based on Lie algebra. We then extend it to model complex motion by combining multiple flows in a geometrically consistent manner. Taking advantage of the linear nature of this representation, we formulate a stochastic flow model, and incorporate a Gaussian process to capture the spatial coherence more effectively. This model leads to an efficient and robust algorithm that can integrate both point pairs and frame differences in motion estimation. We conducted experiments on different types of videos. The results clearly demonstrate that the proposed approach is effective in modeling persistent motion.

We present a novel representation for modeling textured regions subject to smooth variations in orientation and scale. Utilizing the steerable pyramid of Simoncelli and Freeman as a basis, we decompose textured regions of natural images into explicit local attributes of contrast, bias, scale, and orientation. Additionally, we impose smoothness on these attributes via Markov random fields. The combination allows for demonstrable improvements in common scene analysis applications including unsupervised segmentation, reflectance and shading estimation, and estimation of the radiometric response function from a single image.

Fusion of 3D laser radar (LIDAR) imagery and aerial optical imagery is an efficient method for constructing 3D virtual reality models. One difficult aspect of creating such models is registering the optical image with the LIDAR point cloud, which is characterized as a camera pose estimation problem. We propose a novel application of mutual information registration methods, which exploits the statistical dependency in urban scenes of optical appearance with measured LIDAR elevation. We utilize the well known downhill simplex optimization to infer camera pose parameters. We discuss three methods for measuring mutual information between LIDAR imagery and optical imagery. Utilization of OpenGL and graphics hardware in the optimization process yields registration times dramatically lower than previous methods. Using an initial registration comparable to GPS/INS accuracy, we demonstrate the utility of our algorithm with a collection of urban images and present 3D models created with the fused imagery.

We present a novel method for modeling dynamic visual phenomena, which consists of two key aspects. First, the integral motion of constituent elements in a dynamic scene is captured by a common underlying geometric transform process. Second, a Lie algebraic representation of the transform process is introduced, which maps the transformation group to a vector space, and thus overcomes the difficulties due to the group structure. Consequently, the statistical learning techniques based on vector spaces can be readily applied. Moreover, we discuss the intrinsic connections between the Lie algebra and the Linear dynamical processes, showing that our model induces spatially varying fields that can be estimated from local motions without continuous tracking. Following this, we further develop a statistical framework to robustly learn the flow models from noisy and partially corrupted observations. The proposed methodology is demonstrated on real world phenomenon, inferring common motion patterns from surveillance videos of crowded scenes and satellite data of weather evolution.

Information measures have long been studied in the context of hypothesis testing leading to variety of bounds on performance based on the information content of a signal or the divergence between distributions. Here we consider the problem of estimation of information content for high-dimensional signals for purposes of classification. Direct estimation of information for high-dimensional signals is generally not tractable therefore we consider an extension to a method first suggested in [1] in which high dimensional signals are mapped to lower dimensional feature spaces yielding lower bounds on information content. We develop an affine-invariant gradient method and examine the utility of the resulting estimates for predicting classification performance empirically.

This paper explores modeling the dependency structure among multiple vector time-series. We focus on a large classes of structures which yield efficient and tractable exact inference. Specifically, we use directed trees and forests to model causal interactions among time-series. These models are incorporated in a dynamic setting in which a latent variable indexes evolving structures. We demonstrate the utility of the method by analyzing the interaction of multiple moving objects.

We present a method for sequential learning of increasingly complex graphical models for discriminating between two hypotheses. We generate forests for each hypothesis, each with no more edges than a spanning tree, which optimize an information-theoretic criteria. The method relies on a straightforward extension of the efficient max-weight spanning tree (MWST) algorithm by incorporating multivalued edge-weights. Each iteration produces nested forests with increasing number of edges; each provably optimal as compared to alternative forests. Empirical results demonstrate superior probability of error as compared to generative approaches.

The performance of three well known face detection algorithms and four alternative types of features are characterized using face data from the Face Recognition Grand Challenge. The three algorithms are a semi-naive Bayesian classifier, a neural network called a SNoW, and a cascade classifier using Haar wavelets. For the first two algorithms, ROC analysis is used to assess the relative value of wavelet features compared to simpler pixel features. No universally best feature is observed, and for imagery acquired under uncontrolled lighting, pixels perform slightly better than wavelets. The cascade classifier is found to be impossible to train in the same fashion as the other algorithms, but it is also found to perform very well using a training configuration supplied along with the algorithm as part of the OpenCV library.

Many estimation problems involve sensors which can be actively controlled to alter the information received and utilized in the underlying inference task. In this paper, we discuss a novel integer programming method which exploits the submodularity of information theoretic estimation criterion to find an efficient solution to constructing an open loop plan for sensor resource management problems involving many independent objects. The integer programming formulation solves a sequence of simplified problems; the solution of each forms an upper bound to the full complexity problem. The updates performed between iterations may be viewed as steps in a constraint generation process, ensuring that the bound is successively tightened. An auxiliary problem also provides a lower bound to the optimal solution, and a solution attaining that bound, enabling early termination with a guaranteed near-optimal solution. Computational experiments demonstrate the benefit that the algorithm can provide in various planning problems.

We consider the problem of jointly forming images and determining anisotropy from wide-angle synthetic aperture radar (SAR) measurements. Conventional SAR image formation techniques assume isotropic scattering, which is not valid with wide-angle apertures. We present a method based on a sparse representation of aspect-dependent scattering with an overcomplete dictionary composed of elements with varying levels of angular persistence. Solved as an inverse problem, the result is a complex-valued, aspect-dependent response for each spatial location in a scene. Our formulation leads to an optimization problem for which we develop a tractable, graph-structured approximate algorithm. We present experimental results on realistic electromagnetic simulations demonstrating the effectiveness of the proposed approach.

We formulate the problem of audio-visual speaker association as a dynamic dependency test. That is, given an audio stream and multiple video streams, we wish to determine their dependency structure as it evolves over time. To this end, we propose the use of a hidden factorization Markov model in which the hidden state encodes a finite number of possible dependency structures. Each dependency structure has an explicit semantic meaning, namely "who is speaking". This model takes advantage of both structural and parametric changes associated with changes in speaker. This is contrasted with standard sliding window based dependence analysis. Using this model we obtain state-of-the-art performance on an audio-visual association task without benefit of training data.

Many estimation problems involve sensors which can be actively controlled to alter the information received and utilized in the underlying inference task. In this paper, we discuss performance guarantees for heuristic algorithms for adaptive sensor control in sequential estimation problems, where the inference criterion is mutual information. We also demonstrate the performance of our tighter online computable performance guarantees through computational simulations. The guarantees may be applied to other estimation criteria including the Cramer-Rao bound.

We present a novel level-set method for evolving open surfaces embedded in three-dimensional volumes. We adapt the method for statistical detection and segmentation of cytoarchitectonic regions of the cortical ribbon (e.g., Brodmann areas). In addition, we incorporate an explicit interface appearance model which is oriented normal to the open surface, allowing one to model characteristics beyond voxel intensities and high gradients. We show that such models are well suited to detecting embedded cortical structures. Appearance models of the interface are used in two ways: firstly, to evolve an open surface in the normal direction for the purpose of detecting the location of the surface, and secondly, to evolve the boundary of the surface in a direction tangential to the surface in order to delineate the extent of a specific Brodmann area within the cortical ribbon. The utility of the method is demonstrated on a challenging ex-vivo structural MR dataset for detection of Brodmann area 17.

Understanding the dependency structure of a set of variables is a key component in various signal processing applications which involve data association. The simple task of detecting whether any dependency exists is particularly difficult when models of the data are unknown or difficult to characterize because of high-dimensional measurements. We review the use of nonparametric tests for characterizing dependency and how to carry out these tests with high-dimensional observations. In addition we present a method to assess the significance of the tests.

Inter-sensor communication often comprises a significant portion of energy expenditures in a sensor network as compared to sensing and computation. We discuss an integrated approach to dynamically routing measurements and models in a sensor network. Specifically, we examine the problem of tracking objects within a region wherein the responsibility for combining measurements and updating a posterior state distribution is assigned to a single sensor at any given time step. The so called leader node may change over time. Sensor nodes communicate for two reasons: firstly, measurements of target state are transmitted from sensors to the current leader node for incorporation into the state estimate model; secondly, the state model is transmitted between sensors when the leader node changes. The trade-off between these two types of communication is of primary importance to dynamic selection of the leader node. We propose an algorithm based on a dynamic programming roll-out formulation of the minimum cost problem. We obtain a cost function which can be efficiently minimized by simplifying the problem to that of an open loop feedback controller which is an upper bound to the optimal cost. We present empirical results which compare methods previously proposed in the literature to the algorithm presented here.

We consider the problem of detecting and localizing a material release utilizing sparse sensor measurements. We formulate the problem as one of abrupt change detection. The problem is challenging because of the sparse sensor deployment and complex system dynamics. We restrict ourselves to propagation models consisting of diffusion plus transport according to a Gaussian puff model. We derive optimal inference algorithms, provided the model parametrization is known precisely, within a hybrid detection-localization hypothesis testing framework with linear growth in the hypothesis space. The primary assumptions are that the mean wind field is deterministically known and that the Gaussian puff model is valid. Under these assumptions, we characterize the change in performance of detection, time-to-detection and localization as a function of the number of sensors. We then examine some performance impacts when the underlying dynamical model deviates from the assumed model

Statistical approaches to modeling dynamics and clustering data are well studied research areas. This paper considers a special class of such problems in which one is presented with multiple data streams and wishes to infer their interaction as it evolves over time. This problem is viewed as one of inference on a class of models in which interaction is described by changing dependency structures, i. e. the presence or absence of edges in a graphical model, but for which the full set of parameters are not available. The application domain of dynamic link analysis as applied to tracked object behavior is explored. An approximate inference method is presented along with empirical results demonstrating its performance.

Importance sampling (IS) and actor-critic are two methods which have been used to reduce the variance of gradient estimates in policy gradient optimization methods. We show how IS can be used with temporal difference methods to estimate a cost function parameter for one policy using the entire history of system interactions incorporating many different policies. The resulting algorithm is then applied to improving gradient estimates in a policy gradient optimization. The empirical results demonstrate a 20-40 /spl times/ reduction in variance over the IS estimator for an example queueing problem, resulting in a similar factor of improvement in convergence for a gradient search.