An Information Fusion Framework for Robust Shape Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
This paper presents a novel approach for landmark-basedshape deformation, in which fitting error and shapedifference are formulated into a support vector machine(SVM) regression problem. To well describe nonrigid shapedeformation, this paper measures the shape difference usinga thin-plate spline model. The proposed approach iscapable of preserving the topology of the template shape inthe deformation. This property is achieved by inserting aset of additional points and imposing a set of linear equalityand/or inequality constraints. The underlying optimizationproblem is solved using a quadratic programming algorithm.The proposed method has been tested using practicaldata in the context of shape-based image segmentation.Some relevant practical issues, such as missing detectedlandmarks and selection of the regularization parameter arealso briefly discussed.