Efficient 3D Curve Skeleton Extraction from Large Objects

Szilágyi, László; Szilágyi, Sándor; Iclănzan, David; Szabó, Lehel

doi:10.1007/978-3-642-25085-9_15

Cited by 3 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7 prove, for large 3D objects, this proposed parallel algorithm based on OpenCL framework really reduces the computational load and improves efficiency of potential field method with a speedup factor of 5-10. At the same time, it guarantees the accuracy, not like the method applied in article [7]. In this paper, we propose a parallel algorithm for 3D skeleton extraction using OpenCL and prove its validity and efficiency through simulation experiments.…”

Section: Experiments Resultsmentioning

confidence: 93%

“…In physics, we all know that an electrical charge generates a potential field, and whenever another charged object approaches, there will be a force between them [7]. The force can be identified by the formula: F=kq 1 q 2 /d 2 , where k is a constant, q 1 , q 2 is the charge and d is the distance between them.…”

Section: Fieldmentioning

confidence: 99%

“…For those 3D objects represented by discrete data, the algorithm based on potential field works well, but still, suffers high computational burden. Several improved extraction algorithms based on potential field are presented in [6][7][8], however, there still has large space to improve since this kind of algorithm has its potential parallelism. If the execution time decreases to be acceptable, it will become a better choice than others for skeleton extraction, along with its perfect extraction result.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3D Skeleton Extraction Method using Potential Field on OpenCL

Lu¹,

Wang²

2014

Proceedings of the 3rd International Conference on Computer Science and Service System

View full text Add to dashboard Cite

Abstract-For 3D skeleton extraction, the algorithm based on generalized potential fields, known as the outstandingly flexible and robust method, is suffering from seriously heavy computational burden. In this paper, we put forward a parallel algorithm based on OpenCL heterogeneous parallel framework, which can make full use of the great computing power provided by heterogeneous model of CPU+GPU. This algorithm focuses on computing the potential field of each interior point in parallel, with the goal of cutting down the time of potential field calculation to relieve the whole computational burden of this extraction algorithm. The proposed parallel algorithm was evaluated by using several large 3D object volumes. From the tests, we can find that the whole calculation time can be reduced up to 5 to 10 times, without affecting the extraction's accuracy.

show abstract

Section: Experiments Resultsmentioning

confidence: 93%

Section: Fieldmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D Skeleton Extraction Method using Potential Field on OpenCL

Lu¹,

Wang²

2014

Proceedings of the 3rd International Conference on Computer Science and Service System

View full text Add to dashboard Cite

show abstract

“…This sort of curve skeleton is reportedly produced by potential field methods. The actual skeleton extraction algorithm implemented into the medial line identification procedure is the hierarchical formulation of the potential field based problem, described in [30]. …”

Section: Methodsmentioning

confidence: 99%

Identification of dental root canals and their medial line from micro-CT and cone-beam CT records

Benyó

2012

BioMedical Engineering OnLine

View full text Add to dashboard Cite

BackgroundShape of the dental root canal is highly patient specific. Automated identification methods of the medial line of dental root canals and the reproduction of their 3D shape can be beneficial for planning endodontic interventions as severely curved root canals or multi-rooted teeth may pose treatment challenges. Accurate shape information of the root canals may also be used by manufacturers of endodontic instruments in order to make more efficient clinical tools.MethodNovel image processing procedures dedicated to the automated detection of the medial axis of the root canal from dental micro-CT and cone-beam CT records are developed. For micro-CT, the 3D model of the root canal is built up from several hundred parallel cross sections, using image enhancement, histogram based fuzzy c-means clustering, center point detection in the segmented slice, three dimensional inner surface reconstruction, and potential field driven curve skeleton extraction in three dimensions. Cone-beam CT records are processed with image enhancement filters and fuzzy chain based regional segmentation, followed by the reconstruction of the root canal surface and detecting its skeleton via a mesh contraction algorithm.ResultsThe proposed medial line identification and root canal detection algorithms are validated on clinical data sets. 25 micro-CT and 36 cone-beam-CT records are used in the validation procedure. The overall success rate of the automatic dental root canal identification was about 92% in both procedures. The algorithms proved to be accurate enough for endodontic therapy planning.ConclusionsAccurate medial line identification and shape detection algorithms of dental root canal have been developed. Different procedures are defined for micro-CT and cone-beam CT records. The automated execution of the subsequent processing steps allows easy application of the algorithms in the dental care. The output data of the image processing procedures is suitable for mathematical modeling of the central line. The proposed methods can help automate the preparation and design of several kinds of endodontic interventions.

show abstract

“…Szilágyi et al (2011) presented a method based on generalised potential fields (GFPs), proposing a hierarchical approach for computing the GFP. For each level of the hierarchy the input object dimensions were reduced in size and the skeleton extracted for the lower resolution version.…”

Section: Related Workmentioning

confidence: 99%

Real-time three-dimensional skeletonisation using general-purpose computing on graphics processing units applied to computer vision-based human pose estimation

Bakken¹,

Eliassen²

2015

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

Human pose estimation is the process of approximating the configuration of the body’s underlying skeletal articulation in one or more frames. The curve-skeleton of an object is a line-like representation that preserves topology and geometrical information. Finding the curve-skeleton of a volume corresponding to the person is a good starting point for approximating the underlying skeletal structure. In this paper, a GPU implementation of a fully parallel thinning algorithm based on the critical kernel framework is presented. The algorithm is compared to three other state-of-the-art skeletonisation methods—two CPU and one GPU implementation—using both real and synthetic data. It is demonstrated that all four achieve close to real-time frame rates, however, the proposed algorithm yields superior accuracy and robustness when used in a pose estimation context. The GPU implementation is > 8× faster than a CPU implementation of the same algorithm, and the positions of the 4 extremities are estimated with rms error ∼6 cm and ∼98% of frames correctly labelled for some sequences.

show abstract

Efficient 3D Curve Skeleton Extraction from Large Objects

Cited by 3 publications

References 12 publications

3D Skeleton Extraction Method using Potential Field on OpenCL

3D Skeleton Extraction Method using Potential Field on OpenCL

Identification of dental root canals and their medial line from micro-CT and cone-beam CT records

Real-time three-dimensional skeletonisation using general-purpose computing on graphics processing units applied to computer vision-based human pose estimation

Contact Info

Product

Resources

About