The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
Computer Vision and Image Understanding
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling
International Journal of Computer Vision
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Parameterized modeling and recognition of activities
Computer Vision and Image Understanding
Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking persons in monocular image sequences
Computer Vision and Image Understanding
A survey of computer vision-based human motion capture
Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Pedestrian Detection from a Moving Vehicle
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Statistical Foreground Modelling for Object Localisation
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
A Probabilistic Background Model for Tracking
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Stochastic Tracking of 3D Human Figures Using 2D Image Motion
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Learning and Recognizing Human Dynamics in Video Sequences
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Learning Parameterized Models of Image Motion
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
3-D model-based tracking of humans in action: a multi-view approach
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Tracking People with Twists and Exponential Maps
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Cardboard People: A Parameterized Model of Articulated Image Motion
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Object Localization by Bayesian Correlation
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A convex penalty method for optical human motion tracking
IWVS '03 First ACM SIGMM international workshop on Video surveillance
Human-centered multimedia: representations and challenges
Proceedings of the 1st ACM international workshop on Human-centered multimedia
Human body pose detection using Bayesian spatio-temporal templates
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Real-time boundary detection for cricket game
Proceedings of the 3rd Australasian conference on Interactive entertainment
Nonlinear manifold learning for dynamic shape and dynamic appearance
Computer Vision and Image Understanding
Optimal Camera Placement for Automated Surveillance Tasks
Journal of Intelligent and Robotic Systems
Object detection using image reconstruction with PCA
Image and Vision Computing
Non-rigid object tracking in complex scenes
Pattern Recognition Letters
View-independent human motion classification using image-based reconstruction
Image and Vision Computing
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Multi-object tracking based on a modular knowledge hierarchy
ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
Pedestrian detection using global-local motion patterns
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Homeomorphic manifold analysis: learning decomposable generative models for human motion analysis
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
Boundary fragment matching and articulated pose under occlusion
AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
Dimension reduction in 3d gesture recognition using meshless parameterization
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Robust decentralized multi-model adaptive template tracking
Pattern Recognition
Hi-index | 0.00 |
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.