Active Contours

By Andrew Blake, Michael Isard. Springer London, 2000

1,177 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design

View Paper: https://www.semanticscholar.org/paper/a90110adc8b77f2d8116500a4e92a6cb602457c9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

A Probabilistic Exclusion Principle for Tracking Multiple Objects (2000, neutral): “The space of contours which can correspond to a target or set of targets is called the shape space[3], and is parameterised as a low-dimensional vector space X.”
Articulated Body Motion Capture by Stochastic Search (2005, methodology): “It differs from Condensation in using the simplified weighting function (exactly the same as for the full Annealed Particle Filter experiment), and in propagating only the mode of the distribution between frames.”
An Overview of Existing Methods and Recent Advances in Sequential Monte Carlo (2007, methodology): “Since then, there have been several independent variants of similar filtering ideas, including the Condensation filter [17], Monte Carlo filter [1], Sequential imputations [18], and the Particle filter [19].”
Optic nerve head segmentation (2004, methodology): “We calculate the radial gradient γ i (ρ) by bilinear interpolation of the image gradient magnitude at the point's four neighboring pixels [24]; see c radial line model (x,y) i i+1 j j+1 1 ς 2 ς 1.0 1.0 i γ 0 Fig.”
Dynamical statistical shape priors for level set-based tracking (2006, methodology): “Autoregressive models were developed for explicit shape representations among others by Blake et al. [2], [3].”
New Methods in Iris Recognition (2007, background): “…M ) is obtained as the new sequence { R θ } for θ = 0 to θ = N − 1 , which is expressed as follows: As is generally true of active-contour methods [1], [8], there is a tradeoff between how precisely one wants the model to ﬁt all the data (improved by increasing M ) versus how much one wishes to…”
A Snake-Based Approach to Accurate Determination of Both Contact Points and Contact Angles (2006, methodology): “In order to achieve hat, triple control points may be used [21].”
Shape Priors for Level Set Representations (2002, background): “Point-based snake models [8], deformable models/templates [2], active shapes [5], level set representations [3], etc.”
Object tracking: A survey (2006, positive): “Object shape can be modeled in the form of contour subspace where a subspace is generated from a set of possible object contours obtained from different object poses [Blake and Isard 2000].”
Image change detection algorithms: a systematic survey (2005, background): “…scene consists of deformable/articulated objects), a nonglobal transformation may need to be estimated to determine corresponding points between two images, e.g., via optical flow [34], tracking [35], object recognition and pose estimation [36], [37], or structure-from-motion [38], [39] algorithms.”
A Framework for Robust Subspace Learning (2003, methodology): “, 1979), Autoregressive analysis (AR) (Blake and Isard, 1998), and Singular Value Decomposition (SVD) (Golub and Van Loan, 1989), have been widely used for the representation of high dimensional data such as appearance, shape, motion, temporal dynamics, etc.”
Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional (2002, methodology): “where Bn are periodic, quadratic B-spline basis functions (Farin, 1997; Blake and Isard, 1998) and pn = (xn, yn) are the spline control points.”
Dynamic Textures (2003, methodology): “Algorithms of this sort are called “particle filters” [23], and in particular the CONDENSATION filter [6] is the best known instance in the Computer Vision community.”
Computing geodesics and minimal surfaces via graph cuts (2003, background): “Details for parametric active contours can be found in [14].”