A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance of optical flow techniques
International Journal of Computer Vision
Active shape models—their training and application
Computer Vision and Image Understanding
Computer graphics (2nd ed. in C): principles and practice
Computer graphics (2nd ed. in C): principles and practice
Visual learning and recognition of 3-D objects from appearance
International Journal of Computer Vision
Lua—an extensible extension language
Software—Practice & Experience
Surface intersection using affine arithmetic
GI '96 Proceedings of the conference on Graphics interface '96
Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion
International Journal of Computer Vision
An anthropometric face model using variational techniques
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Warping and morphing of graphical objects
Warping and morphing of graphical objects
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optical Flow Constraints on Deformable Models with Applications to Face Tracking
International Journal of Computer Vision
Representations for Rigid Solids: Theory, Methods, and Systems
ACM Computing Surveys (CSUR)
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
Active Contours: The Application of Techniques from Graphics,Vision,Control Theory and Statistics to Visual Tracking of Shapes in Motion
Statistical cue estimation for model-based shape and motion tracking
Statistical cue estimation for model-based shape and motion tracking
Stereo Depth Estimation: A Confidence Interval Approach
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Methods and Applications of Interval Analysis (SIAM Studies in Applied and Numerical Mathematics) (Siam Studies in Applied Mathematics, 2.)
Active and Dynamic Information Fusion for Facial Expression Understanding from Image Sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Outlier rejection in high-dimensional deformable models
Image and Vision Computing
Robust facial feature tracking under varying face pose and facial expression
Pattern Recognition
High Resolution Tracking of Non-Rigid Motion of Densely Sampled 3D Data Using Harmonic Maps
International Journal of Computer Vision
Dynamic Tracking of Facial Expressions Using Adaptive, Overlapping Subspaces
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part I: ICCS 2007
Single view motion tracking by depth and silhouette information
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Automatic 3d facial expression analysis in videos
AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures
Dynamically adaptive tracking of gestures and facial expressions
ICCS'06 Proceedings of the 6th international conference on Computational Science - Volume Part III
A multiple camera methodology for automatic localization and tracking of futsal players
Pattern Recognition Letters
Hi-index | 0.14 |
Deformable models are a useful modeling paradigm in computer vision. A deformable model is a curve, a surface, or a volume, whose shape, position, and orientation are controlled through a set of parameters. They can represent manufactured objects, human faces and skeletons, and even bodies of fluid. With low-level computer vision and image processing techniques, such as optical flow, we extract relevant information from images. Then, we use this information to change the parameters of the model iteratively until we find a good approximation of the object in the images. When we have multiple computer vision algorithms providing distinct sources of information (cues), we have to deal with the difficult problem of combining these, sometimes conflicting contributions in a sensible way. In this paper, we introduce the use of a directed acyclic graph (dag) to describe the position and Jacobian of each point of deformable models. This representation is dynamic, flexible, and allows computational optimizations that would be difficult to do otherwise. We then describe a new method for statistical cue integration method for tracking deformable models that scales well with the dimension of the parameter space. We use affine forms and affine arithmetic to represent and propagate the cues and their regions of confidence. We show that we can apply the Lindeberg theorem to approximate each cue with a Gaussian distribution, and can use a maximum-likelihood estimator to integrate them. Finally, we demonstrate the technique at work in a 3D deformable face tracking system on monocular image sequences with thousands of frames.