Active Contours

Blake, A.; Isard, Michael

doi:10.1007/978-1-4471-1555-7

Cited by 878 publications

(697 citation statements)

References 0 publications

Supporting

Mentioning

673

Contrasting

Unclassified

Order By: Relevance

“…We follow here the approach in [7] to which we refer the interested reader for all of the details. The overall method is based on active contours implemented via level set techniques [10], [15], [14], [2]. In our case, the evolution is driven by the gradient flow derived from an energy functional that is based on the Bhattacharyya distance.…”

Section: Information-theoretic Approach To Segmentationmentioning

confidence: 99%

“…Thus the functions the functions P − (x | Ψ(z)) and P + (x | Ψ(z)) given by (2) and (3) are kernel-based estimates of the probability density functions pdf of the image features observed over the sub-domains Ω − and Ω + . The key idea underpinning the segmentation approach of [7] is that for a properly selected subset of image features, the "overlap" between the informational contents of the object and of the background has to be minimal.…”

Section: A Bhattacharyya Flowmentioning

confidence: 99%

See 1 more Smart Citation

Statistical shape learning for 3D tracking

Sandhu

Lankton

Dambreville

et al. 2009

Proceedings of the 48h IEEE Conference on Decision and Control (CDC) Held Jointly With 2009 28th Chinese Control Conference

View full text Add to dashboard Cite

Abstract-In this note, we consider the use of 3D models for visual tracking in controlled active vision. The models are used for a joint 2D segmentation/3D pose estimation procedure in which we automatically couple the two processes under one energy functional. Further, employing principal component analysis from statistical learning, can train our tracker on a catalog of 3D shapes, giving a priori shape information. The segmentation itself is information-based. The allows us to track in uncertain adversarial environments. Our methodology is demonstrated on some real sequences which illustrate its robustness on challenging scenarios.

show abstract

Section: Information-theoretic Approach To Segmentationmentioning

confidence: 99%

Section: A Bhattacharyya Flowmentioning

confidence: 99%

Statistical shape learning for 3D tracking

Sandhu

Lankton

Dambreville

et al. 2009

Proceedings of the 48h IEEE Conference on Decision and Control (CDC) Held Jointly With 2009 28th Chinese Control Conference

View full text Add to dashboard Cite

show abstract

“…Of course this work relates more generically to active contours, e.g. [4,13,5,16] and references therein. In the next section we introduce our model, and in Section 4 we illustrate our approach to infer its (infinite-dimensional) constitutive elements.…”

Section: Relation To Existing Workmentioning

confidence: 99%

Dynamic Shape and Appearance Modeling Via Moving and Deforming Layers

Jackson

Yezzi

Soatto³

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

-We propose a model of the shape, motion and appearance of a scene, seen through a sequence of images, that captures occlusions, scene deformations, arbitrary viewpoint variations and changes in its radiance. This model is based on a collection of overlapping layers that can move and deform, each supporting an intensity function that can change over time. We discuss the generality and limitations of this model in relation to existing ones such as traditional optical flow or motion segmentation, layers, deformable templates and deformotion. We then illustrate how this model can be used for inference of shape, motion, deformation and appearance of the scene from a collection of images. The layering structure allows for automatic inpainting of partially occluded regions. We illustrate the model on synthetic and real sequences where existing schemes fail, and show how suitable choices of constants in the model yield existing schemes, from optical flow to motion segmentation and inpainting.

show abstract

“…Consequently, an energy term is associated with the contour and is designed to be inversely proportional to both the contour's smoothness and its fit to the image data, in order to segment the desired image features. Deformation of the contour in the image will change its energy; thus, one can imagine an energy surface on top of which the contour moves (in a way that resembles the slithering of a snake, and hence the name) while seeking valleys of low energy [5].…”

Section: Introductionmentioning

confidence: 99%