Generalised cylinders from local aggregation of sections

Soroka, Barry I.; Andersson, Russell L.; Bajcsy, Růžena

doi:10.1016/0031-3203(81)90091-1

Cited by 14 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various approaches have been proposed for surface reconstruction, from tetrahedral reconstruction [9] to generalized cylinders [35]. Such techniques remain locally based or need strong topological information about contour points, which can be ambiguous in some case.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

The ellipsoidal skeleton in medical applications

Banegas

Jaeger

Michelucci

et al. 2001

Proceedings of the Sixth ACM Symposium on Solid Modeling and Applications

View full text Add to dashboard Cite

Rough 3D data images obtained by computed tomography or magnetic resonance imagery are inadequate: this paper proposes a highlevel data structure called ellipsoidal skeleton. It is based on a tree of best partitions of the points set and features data compression, multi-level representation capabilities, surface reconstruction, interactive visualization, relevant parameters extraction, automatic matching and recognition.

show abstract

Section: Previous Workmentioning

confidence: 99%

“…Many techniques have been investigated, that may be divided into two classes: either they rely on external [8,1,35] or internal expression of objects. Former ones are based on the surface definition of the object (B-rep, polygonal ou B-spline representation), and latter ones use area descriptor methods (medial axis, shape decomposition).…”

Section: Previous Workmentioning

confidence: 99%

The ellipsoidal skeleton in medical applications

Banegas

Jaeger

Michelucci

et al. 2001

Proceedings of the Sixth ACM Symposium on Solid Modeling and Applications

View full text Add to dashboard Cite

show abstract

“…Furthermore, the Kalman prediction of the axis curve offers an additional advantage: If the intersection plane is not orthogonal to the cylinder axis, even tubular structures with elliptical cross sections generally do not yield ellipses when intersected by a plane (see e.g. [12] or [11] for a more in-depth discussion). Thus, when employing the detection of elliptical cross sections, it is essential to re-slice the 3D input data locally, orthogonal to the Kalman prediction of the axis curve.…”

Section: Kalman Filter Approachmentioning

confidence: 99%

Segmentation of Tubular Structures in 3D Images Using a Combination of the Hough Transform and a Kalman Filter

Behrens¹,

Rohr

Stiehl³

2001

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, we present a new approach for coarse segmentation of tubular anatomical structures in 3D image data. Our approach can be used to initialise complex deformable models and is based on an extension of the randomized Hough transform (RHT), a robust method for low-dimensional parametric object detection. In combination with a discrete Kalman filter, the object is tracked through 3D space. Our extensions to the RHT feature adaptive selection of the sample size, expectation-dependent weighting of the input data, and a novel 3D parameterisation for straight elliptical cylinders. For initialisation, only little user interaction is necessary. Experimental results obtained for 3D synthetic as well as for 3D medical images demonstrate the robustness of our approach w.r.t. image noise. We present the successful segmentation of tubular anatomical structures such as the aortic arc or the spinal chord.

show abstract

“…The description of objects with cylindrical shapes has been extensively used in the computer vision community [1,32,30,35]. In a first approximation it is often convenient to model a shape as a generalized cylinder.…”

Section: Introductionmentioning

confidence: 99%