Sciweavers

515 search results - page 78 / 103
» Multiple parametric motion model estimation and segmentation
Sort
View

Book
5396views
16 years 8 months ago
Markov Random Field Modeling in Computer Vision
Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms sy...
Stan Z. Li
TIP
2002
134views more  TIP 2002»
14 years 9 months ago
Curvature of n-dimensional space curves in grey-value images
Local curvature represents an important shape parameter of space curves which are well described by differential geometry. We have developed an estimator for local curvature of spa...
Bernd Rieger, Lucas J. van Vliet
CVPR
2009
IEEE
15 years 4 months ago
Learning multi-modal densities on Discriminative Temporal Interaction Manifold for group activity recognition
While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activi...
Ruonan Li, Rama Chellappa, Shaohua Kevin Zhou
HUMO
2007
Springer
15 years 3 months ago
Modeling Human Locomotion with Topologically Constrained Latent Variable Models
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Raquel Urtasun, David J. Fleet, Neil D. Lawrence
ICIP
2006
IEEE
15 years 11 months ago
Non-Rigid Registration for Automatic Fracture Segmentation
Automatic segmentation of anatomical structures is often performed using model-based non-rigid registration methods. These algorithms work well when the images do not contain any ...
Johanna Pettersson, Hans Knutsson, Magnus Borga