Stochastic Tracking of 3D Human Figures Using 2D Image Motion

Sidenbladh, Hedvig; Black, Michael J.; Fleet, David J.

doi:10.1007/3-540-45053-x_45

Cited by 491 publications

(447 citation statements)

References 9 publications

Supporting

Mentioning

446

Contrasting

Order By: Relevance

“…While recent advances have been obtained for the tracking of 3d human motion using 2d image cues from monocular image sequences [14,25,30] or multi-view image sequences [4,9,11], these techniques require manual initialization (see [20] for a more complete review). Despite these successes, the complete recovery of 3d body motion is not always necessary and the detection and tracking of 2d human motion is sufficient for numerous applications.…”

Section: Problem Statement and Related Workmentioning

confidence: 99%

“…The focus of a great deal of research has been the detection and tracking of simple models of humans by exploiting knowledge of skin color or static backgrounds [10,15,22]. Progress has also been made on the problem of accurate 3d tracking of high-dimensional articulated body models given a known initial starting pose [9,11,25]. A significant open issue that limits the applicability of these 3d models is the problem of automatic initialization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Detection and Tracking of Human Motion with a View-Based Representation

Fablet

Black

2002

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper proposes a solution for the automatic detection and tracking of human motion in image sequences. Due to the complexity of the human body and its motion, automatic detection of 3D human motion remains an open, and important, problem. Existing approaches for automatic detection and tracking focus on 2D cues and typically exploit object appearance (color distribution, shape) or knowledge of a static background. In contrast, we exploit 2D optical flow information which provides rich descriptive cues, while being independent of object and background appearance. To represent the optical flow patterns of people from arbitrary viewpoints, we develop a novel representation of human motion using low-dimensional spatio-temporal models that are learned using motion capture data of human subjects. In addition to human motion (the foreground) we probabilistically model the motion of generic scenes (the background); these statistical models are defined as Gibbsian fields specified from the first-order derivatives of motion observations. Detection and tracking are posed in a principled Bayesian framework which involves the computation of a posterior probability distribution over the model parameters (i.e., the location and the type of the human motion) given a sequence of optical flow observations. Particle filtering is used to represent and predict this non-Gaussian posterior distribution over time. The model parameters of samples from this distribution are related to the pose parameters of a 3D articulated model (e.g. the approximate joint angles and movement direction). Thus the approach proves suitable for initializing more complex probabilistic models of human motion. As shown by experiments on real image sequences, our method is able to detect and track people under different viewpoints with complex backgrounds.

show abstract

Section: Problem Statement and Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Detection and Tracking of Human Motion with a View-Based Representation

Fablet

Black

2002

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to blob tracking approaches, model based ones [6][7][8][9][10][11] do not track objects on the image plane but, rather, on a hidden model-space. This is commonly facilitated by means of sequential Bayesian filters such as Kalman or particle filters.…”

Section: Introductionmentioning

confidence: 99%

“…Among model-based approaches, particle filtering [12] has been successfully applied to object tracking, both with edge-based [12] and kinematic [7,8] imaging models. With respect to the data association problem, particle filtering offers a significant advantage over other filtering methods because it allows for different, locally-optimal data association solutions for each particle which are implicitly evaluated through each particle's likelihood.…”

Section: Introductionmentioning

confidence: 99%

Propagation of Pixel Hypotheses for Multiple Objects Tracking

Baltzakis

Argyros

2009

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. In this paper we propose a new approach for tracking multiple objects in image sequences. The proposed approach differs from existing ones in important aspects of the representation of the location and the shape of tracked objects and of the uncertainty associated with them. The location and the speed of each object is modeled as a discrete time, linear dynamical system which is tracked using Kalman filtering. Information about the spatial distribution of the pixels of each tracked object is passed on from frame to frame by propagating a set of pixel hypotheses, uniformly sampled from the original object's projection to the target frame using the object's current dynamics, as estimated by the Kalman filter. The density of the propagated pixel hypotheses provides a novel metric that is used to associate image pixels with existing object tracks by taking into account both the shape of each object and the uncertainty associated with its track. The proposed tracking approach has been developed to support face and hand tracking for human-robot interaction. Nevertheless, it is readily applicable to a much broader class of multiple objects tracking problems.

show abstract

“…Previous works either choose complex dynamic models or simple dynamic models to characterize the target dynamics and to propagate particles [4,6,8,9]. The advantages of simple models are that they can be easily obtained and adapted to a specific application.…”

Section: Introductionmentioning

confidence: 99%

Approximating Inference on Complex Motion Models Using Multi-model Particle Filter

Wang

Zhao

Shan

et al. 2004

Advances in Multimedia Information Processing - PCM 2004

View full text Add to dashboard Cite

Abstract. Due to its great ability of conquering clutters, which is especially useful for high-dimensional tracking problems, particle filter becomes popular in the visual tracking community. One remained difficulty of applying the particle filter to high-dimensional tracking problems is how to propagate particles efficiently considering complex motions of the target. In this paper, we propose the idea of approximating the complex motion model using a set of simple motion models to deal with the tracking problems cumbered by complex motions. Then, we provide a practical way to do inference on the set of simple motion models instead of original complex motion model in the particle filter. This new variation of particle filter is termed as Multi-Model Particle Filter (MMPF). We apply our proposed MMPF to the problem of head motion tracking. Note that the defined head motions include both rigid motions and non-rigid motions. Experiments show that, when compared with the standard particle filter, the MMPF works well for this high-dimensional tracking problem with reasonable computational cost. In addition, the MMPF may provide a possible solution to other high-dimensional sequential state estimation problems such as human body pose estimation and sign language estimation and recognition from video.

show abstract

Stochastic Tracking of 3D Human Figures Using 2D Image Motion

Cited by 491 publications

References 9 publications

Automatic Detection and Tracking of Human Motion with a View-Based Representation

Automatic Detection and Tracking of Human Motion with a View-Based Representation

Propagation of Pixel Hypotheses for Multiple Objects Tracking

Approximating Inference on Complex Motion Models Using Multi-model Particle Filter

Contact Info

Product

Resources

About