Results 1  10
of
75
Nonparametric Belief Propagation
 IN CVPR
, 2002
"... In applications of graphical models arising in fields such as computer vision, the hidden variables of interest are most naturally specified by continuous, nonGaussian distributions. However, due to the limitations of existing inf#6F6F3 algorithms, it is of#]k necessary tof#3# coarse, ..."
Abstract

Cited by 208 (25 self)
 Add to MetaCart
In applications of graphical models arising in fields such as computer vision, the hidden variables of interest are most naturally specified by continuous, nonGaussian distributions. However, due to the limitations of existing inf#6F6F3 algorithms, it is of#]k necessary tof#3# coarse, discrete approximations to such models. In this paper, we develop a nonparametric belief propagation (NBP) algorithm, which uses stochastic methods to propagate kernelbased approximations to the true continuous messages. Each NBP message update is based on an efficient sampling procedure which can accomodate an extremely broad class of potentialf#l3]k[[z3 allowing easy adaptation to new application areas. We validate our method using comparisons to continuous BP for Gaussian networks, and an application to the stereo vision problem.
Hierarchical Bayesian Inference in the Visual Cortex
, 2002
"... this paper, we propose a Bayesian theory of hierarchical cortical computation based both on (a) the mathematical and computational ideas of computer vision and pattern the ory and on (b) recent neurophysiological experimental evidence. We ,2 have proposed that Grenander's pattern theory 3 could pot ..."
Abstract

Cited by 173 (0 self)
 Add to MetaCart
this paper, we propose a Bayesian theory of hierarchical cortical computation based both on (a) the mathematical and computational ideas of computer vision and pattern the ory and on (b) recent neurophysiological experimental evidence. We ,2 have proposed that Grenander's pattern theory 3 could potentially model the brain as a generafive model in such a way that feedback serves to disambiguate and 'explain away' the earlier representa tion. The Helmholtz machine 4, 5 was an excellent step towards approximating this proposal, with feedback implementing priors. Its development, however, was rather limited, dealing only with binary images. Moreover, its feedback mechanisms were engaged only during the learning of the feedforward connections but not during perceptual inference, though the Gibbs sampling process for inference can potentially be interpreted as topdown feedback disambiguating low level representations? Rao and Ballard's predictive coding/Kalman filter model 6 did integrate generafive feedback in the perceptual inference process, but it was primarily a linear model and thus severely limited in practical utility. The datadriven Markov Chain Monte Carlo approach of Zhu and colleagues 7, 8 might be the most successful recent application of this proposal in solving real and difficult computer vision problems using generafive models, though its connection to the visual cortex has not been explored. Here, we bring in a powerful and widely applicable paradigm from artificial intelligence and computer vision to propose some new ideas about the algorithms of visual cortical process ing and the nature of representations in the visual cortex. We will review some of our and others' neurophysiological experimental data to lend support to these ideas
Nonparametric Belief Propagation for SelfCalibration in Sensor Networks
 In Proceedings of the Third International Symposium on Information Processing in Sensor Networks
, 2004
"... Automatic selfcalibration of adhoc sensor networks is a critical need for their use in military or civilian applications. In general, selfcalibration involves the combination of absolute location information (e.g. GPS) with relative calibration information (e.g. time delay or received signal stre ..."
Abstract

Cited by 84 (7 self)
 Add to MetaCart
Automatic selfcalibration of adhoc sensor networks is a critical need for their use in military or civilian applications. In general, selfcalibration involves the combination of absolute location information (e.g. GPS) with relative calibration information (e.g. time delay or received signal strength between sensors) over regions of the network. Furthermore, it is generally desirable to distribute the computational burden across the network and minimize the amount of intersensor communication. We demonstrate that the information used for sensor calibration is fundamentally local with regard to the network topology and use this observation to reformulate the problem within a graphical model framework. We then demonstrate the utility of nonparametric belief propagation (NBP), a recent generalization of particle filtering, for both estimating sensor locations and representing location uncertainties. NBP has the advantage that it is easily implemented in a distributed fashion, admits a wide variety of statistical models, and can represent multimodal uncertainty. We illustrate the performance of NBP on several example networks while comparing to a previously published nonlinear least squares method.
Tracking people by learning their appearance
 IEEE Trans. Pattern Anal. Mach. Intell
"... Abstract—An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of people in each frame and estimate their configurations. But, finding people and localizing their limbs is hard beca ..."
Abstract

Cited by 74 (3 self)
 Add to MetaCart
Abstract—An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of people in each frame and estimate their configurations. But, finding people and localizing their limbs is hard because people can move fast and unpredictably, can appear in a variety of poses and clothes, and are often surrounded by limblike clutter. We develop a completely automatic system that works in two stages; it first builds a model of appearance of each person in a video and then it tracks by detecting those models in each frame (“tracking by modelbuilding and detection”). We develop two algorithms that build models; one bottomup approach groups together candidate body parts found throughout a sequence. We also describe a topdown approach that automatically builds peoplemodels by detecting convenient key poses within a sequence. We finally show that building a discriminative model of appearance is quite helpful since it exploits structure in a background (without backgroundsubtraction). We demonstrate the resulting tracker on hundreds of thousands of frames of unscripted indoor and outdoor activity, a featurelength film (“Run Lola Run”), and legacy sports footage (from the 2002 World Series and 1998 Winter Olympics). Experiments suggest that our system 1) can count distinct individuals, 2) can identify and track them, 3) can recover when it loses track, for example, if individuals are occluded or briefly leave the view, 4) can identify body configuration accurately, and 5) is not dependent on particular models of human motion. Index Terms—People tracking, motion capture, surveillance. 1
Loopy belief propagation: Convergence and effects of message errors
 Journal of Machine Learning Research
, 2005
"... Belief propagation (BP) is an increasingly popular method of performing approximate inference on arbitrary graphical models. At times, even further approximations are required, whether due to quantization of the messages or model parameters, from other simplified message or model representations, or ..."
Abstract

Cited by 61 (7 self)
 Add to MetaCart
Belief propagation (BP) is an increasingly popular method of performing approximate inference on arbitrary graphical models. At times, even further approximations are required, whether due to quantization of the messages or model parameters, from other simplified message or model representations, or from stochastic approximation methods. The introduction of such errors into the BP message computations has the potential to affect the solution obtained adversely. We analyze the effect resulting from message approximation under two particular measures of error, and show bounds on the accumulation of errors in the system. This analysis leads to convergence conditions for traditional BP message passing, and both strict bounds and estimates of the resulting error in systems of approximate BP message passing. 1
Measure locally, reason globally: Occlusionsensitive articulated pose estimation
 In CVPR 2006
, 2006
"... Partbased treestructured models have been widely used for 2D articulated human poseestimation. These approaches admit efficient inference algorithms while capturing the important kinematic constraints of the human body as a graphical model. These methods often fail however when multiple body part ..."
Abstract

Cited by 59 (3 self)
 Add to MetaCart
Partbased treestructured models have been widely used for 2D articulated human poseestimation. These approaches admit efficient inference algorithms while capturing the important kinematic constraints of the human body as a graphical model. These methods often fail however when multiple body parts fit the same image region resulting in global pose estimates that poorly explain the overall image evidence. Attempts to solve this problem have focused on the use of strong prior models that are limited to learned activities such as walking. We argue that the problem actually lies with the image observations and not with the prior. In particular, image evidence for each body part is estimated independently of other parts without regard to selfocclusion. To address this we introduce occlusionsensitive local likelihoods that approximate the global image likelihood using perpixel hidden binary variables that encode the occlusion relationships between parts. This occlusion reasoning introduces interactions between nonadjacent body parts creating loops in the underlying graphical model. We deal with this using an extension of an approximate belief propagation algorithm (PAMPAS). The algorithm recovers the realvalued 2D pose of the body in the presence of occlusions, does not require strong priors over body pose and does a quantitatively better job of explaining image evidence than previous methods. 1.
Distributed occlusion reasoning for tracking with nonparametric belief propagation
 In NIPS
, 2004
"... We describe a three–dimensional geometric hand model suitable for visual tracking applications. The kinematic constraints implied by the model’s joints have a probabilistic structure which is well described by a graphical model. Inference in this model is complicated by the hand’s many degrees of fr ..."
Abstract

Cited by 55 (0 self)
 Add to MetaCart
We describe a three–dimensional geometric hand model suitable for visual tracking applications. The kinematic constraints implied by the model’s joints have a probabilistic structure which is well described by a graphical model. Inference in this model is complicated by the hand’s many degrees of freedom, as well as multimodal likelihoods caused by ambiguous image measurements. We use nonparametric belief propagation (NBP) to develop a tracking algorithm which exploits the graph’s structure to control complexity, while avoiding costly discretization. While kinematic constraints naturally have a local structure, self– occlusions created by the imaging process lead to complex interpendencies in color and edge–based likelihood functions. However, we show that local structure may be recovered by introducing binary hidden variables describing the occlusion state of each pixel. We augment the NBP algorithm to infer these occlusion variables in a distributed fashion, and then analytically marginalize over them to produce hand position estimates which properly account for occlusion events. We provide simulations showing that NBP may be used to refine inaccurate model initializations, as well as track hand motion through extended image sequences. 1
Attractive people: Assembling looselimbed models using nonparametric belief propagation
 In NIPS. 2004
"... The detection and pose estimation of people in images and video is made challenging by the variability of human appearance and the high dimensionality of articulated body models. To cope with these problems we exploit rich image likelihood models and represent the 3D human body using a graphical mod ..."
Abstract

Cited by 50 (2 self)
 Add to MetaCart
The detection and pose estimation of people in images and video is made challenging by the variability of human appearance and the high dimensionality of articulated body models. To cope with these problems we exploit rich image likelihood models and represent the 3D human body using a graphical model in which the relationships between the body parts are represented by conditional probability distributions. We formulate the pose estimation problem as one of probabilistic inference over a graphical model where the random variables correspond to the individual limb parameters (position and orientation). Because the limbs are described by 6dimensional vectors encoding pose in 3space, discretization is impractical and the random variables in our model must be continuousvalued. To approximate belief propagation in such a graph we exploit a recently introduced generalization of the particle filter. This framework facilitates the automatic initialization of the bodymodel from low level cues and is robust to occlusion of body parts and scene clutter. 1
Nonparametric belief propagation for selflocalization of sensor networks
 IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
, 2005
"... Automatic selflocalization is a critical need for the effective use of adhoc sensor networks in military or civilian applications. In general, selflocalization involves the combination of absolute location information (e.g. GPS) with relative calibration information (e.g. distance measurements b ..."
Abstract

Cited by 49 (3 self)
 Add to MetaCart
Automatic selflocalization is a critical need for the effective use of adhoc sensor networks in military or civilian applications. In general, selflocalization involves the combination of absolute location information (e.g. GPS) with relative calibration information (e.g. distance measurements between sensors) over regions of the network. Furthermore, it is generally desirable to distribute the computational burden across the network and minimize the amount of intersensor communication. We demonstrate that the information used for sensor localization is fundamentally local with regard to the network topology and use this observation to reformulate the problem within a graphical model framework. We then present and demonstrate the utility of nonparametric belief propagation (NBP), a recent generalization of particle filtering, for both estimating sensor locations and representing location uncertainties. NBP has the advantage that it is easily implemented in a distributed fashion, admits a wide variety of statistical models, and can represent multimodal uncertainty. Using simulations of small to moderatelysized sensor networks, we show that NBP may be made robust to outlier measurement errors by a simple model augmentation, and that judicious message construction can result in better estimates. Furthermore, we provide an analysis of NBP’s communications requirements, showing that typically only a few messages per sensor are required, and that even low bitrate approximations of these messages can have little or no performance impact.
Visual hand tracking using nonparametric belief propagation
 Propagation,” IEEE Workshop on Generative Model Based Vision
, 2004
"... Abstract — This paper develops probabilistic methods for visual tracking of a threedimensional geometric hand model from monocular image sequences. We consider a redundant representation in which each model component is described by its position and orientation in the world coordinate frame. A prio ..."
Abstract

Cited by 48 (1 self)
 Add to MetaCart
Abstract — This paper develops probabilistic methods for visual tracking of a threedimensional geometric hand model from monocular image sequences. We consider a redundant representation in which each model component is described by its position and orientation in the world coordinate frame. A prior model is then defined which enforces the kinematic constraints implied by the model’s joints. We show that this prior has a local structure, and is in fact a pairwise Markov random field. Furthermore, our redundant representation allows color and edgebased likelihood measures, such as the Chamfer distance, to be similarly decomposed in cases where there is no self–occlusion. Given this graphical model of hand kinematics, we may track the hand’s motion using the recently proposed nonparametric belief propagation (NBP) algorithm. Like particle filters, NBP approximates the posterior distribution over hand configurations as a collection of samples. However, NBP uses the graphical structure to greatly reduce the dimensionality of these distributions, providing improved robustness. Several methods are used to improve NBP’s computational efficiency, including a novel KDtree based method for fast Chamfer distance evaluation. We provide simulations showing that NBP may be used to refine inaccurate model initializations, as well as track hand motion through extended image sequences. I.