Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Tracking
International Journal of Computer Vision
Optical aerial image partitioning using level sets based on modified Chan-Vese model
Pattern Recognition Letters
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
A Statistical Overlap Prior for Variational Image Segmentation
International Journal of Computer Vision
Target detection in SAR images based on a level set approach
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Embedding a region merging prior in level set vector-valued image segmentation
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Variational region-based segmentation using multiple texture statistics
IEEE Transactions on Image Processing
Nonparametric density estimation for human pose tracking
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Trimap segmentation for fast and user-friendly alpha matting
VLSM'05 Proceedings of the Third international conference on Variational, Geometric, and Level Set Methods in Computer Vision
Unsupervised texture segmentation with nonparametric neighborhood statistics
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
A continuous max-flow approach to minimal partitions with label cost prior
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
| Hi-index | 0.00 |
We present a novel non-parametric unsupervised segmentationalgorithm based on Region Competition [21];but implemented within a Level Sets framework [11]. Thekey novelty of the algorithm is that it can solve N 驴 2 classsegmentation problems using just one embedded surface;this is achieved by controlling the merging and splitting behaviourof the level sets according to a Minimum DescriptionLength (MDL) [6, 14] cost function. This is in contrastto N class region-based Level Set segmentation methods todate which operate by evolving multiple coupled embeddedsurfaces in parallel [3, 13, 20]. Furthermore, it operates inan unsupervised manner; it is necessary neither to specifythe value of N nor the class models a-priori.We argue that the Level Sets methodology provides amore convenient framework for the implementation of theRegion Competition algorithm, which is conventionally implementedusing region membership arrays due to the lackof a intrinsic curve representation. Finally, we generalisethe Gaussian region model used in standard Region Competitionto the non-parametric case. The region boundary motionand merge equations become simple expressions containingcross-entropy and entropy terms.