This paper presents a robust vision algorithm for tracking the boundary of an object with an arbitrary shape by using monocular image sequences. This method consists of a curve registration based optimization technique and a deformable contour model (”snakes”) for the global and the local motion estimations, respectively. By combining techniques, we overcome, among other problems, inaccurate es...

Deformable geometric models can be used in the concannot be solved with conventional reconstruction algorithms, as text of Bayesian analysis to solve ill-posed tomographic reconstrucshown in Reference [5] , for example. Our ability to obtain an tion problems. The uncertainties associated with a Bayesian analysis excellent reconstruction emphasizes the advantage of using demay be assessed by gen...

The deformable parts model (DPM) [6] serves as a key component in most modern state-of-the-art object detection systems. At a high level, the DPM composes a single object model by learning to detect and assemble parts of an object. Most modern systems employing the DPM employ densely computed Histogram of Oriented Gradients [5] features at training time. Despite the success of HOG features in m...

This report surveys current literature related to statistical shape analysis. There are two paradigms: (1) Models that have no prior knowledge about the shape. They evolve boundary curves in time while maintaining predefined smoothness constraints. (2) Models that have prior knowledge about a fixed shape. They use this knowledge to find object boundaries using the covariance matrix and the aver...

We present a novel technique for the automatic adaptation of a deformable model’s elastic parameters within a Kalman filter framework for shape estimation applications. The novelty of the technique is that the model’s elastic parameters are not constant, but spatio-temporally varying. The variation of the elastic parameters depends on the distance of the model from the data and the rate of chan...

Deformable models provide a promising and vigorously researched model-based approach to computer-assisted medical image analysis. The widely recognized potency of deformable models stems from their ability to segment, match, and track images of anatomic structures by exploiting (bottom-up) constraints derived from the image data together with (top-down) a priori knowledge about the location, si...

E cient and powerful topologically adaptable deformable surfaces can be created by embedding and de ning discrete deformable surface models in terms of an A ne Cell Decomposition (ACD) framework. The ACD framework, combined with a novel and original reparameterization algorithm, creates a simple but elegant mechanism for multiresolution deformable curve, surface, and solid models to \ ow" or \g...