Learning and Classification of Complex Dynamics
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Probabilistic Exclusion Principle for Tracking Multiple Objects
International Journal of Computer Vision
Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Video Object Hyper-Links for Streaming Applications
VISUAL '02 Proceedings of the 5th International Conference on Recent Advances in Visual Information Systems
Iris Tracking with Feature Free Contours
AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Computer Vision and Image Understanding - Special issue on eye detection and tracking
Object recognition with uncertain geometry and uncertain part detection
Computer Vision and Image Understanding
Human Pose Estimation Using Partial Configurations and Probabilistic Regions
International Journal of Computer Vision
A decentralized probabilistic approach to articulated body tracking
Computer Vision and Image Understanding
Contour graph based human tracking and action sequence recognition
Pattern Recognition
Face detection and tracking using a Boosted Adaptive Particle Filter
Journal of Visual Communication and Image Representation
Variance reduction techniques in particle-based visual contour tracking
Pattern Recognition
Object recognition with uncertain geometry and uncertain part detection
Computer Vision and Image Understanding
Computer Vision and Image Understanding - Special issue on eye detection and tracking
Contour tracking based on marginalized likelihood ratios
Image and Vision Computing
Switching observation models for contour tracking in clutter
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Exemplar-Based human contour tracking
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
| Hi-index | 0.00 |
A method of localising objects in images is proposed. Possible configurations are evaluated using the contour discriminant, a likelihood ratio which is derived from a probabilistic model of the feature detection process. We treat each step in this process probabilistically, including the occurrence of clutter features, and derive the observation densities for both correct "target" configurations and incorrect "clutter" configurations. The contour discriminant distinguishes target objects from the background even in heavy clutter, making only the most general assumptions about the form that clutter might take. The method generates samples stochastically to avoid the cost of processing an entire image, and promises to be particularly suited to the task of initialising contour trackers based on sampling methods.