Filtering and segmentation of 3D angiographic data: Advances based on mathematical morphology

Dufour, Alice; Tankyevych, Olena; Naegel, Benoît; Talbot, Hugues; Ronse, Christian; Baruthio, J.; Dokládal, Petr; Passat, Nicolas

doi:10.1016/j.media.2012.08.004

Cited by 60 publications

(35 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a lot of mature filtering algorithm in the processing of airborne point cloud data (Dufour et al, 2013;Vosselman, 2000), and vehicle point cloud filter method is usually do some improvements on the basis of airborne point cloud filter algorithm. But many airborne filtering algorithms do not suitable for the tunnel for its special shape, and the tunnel cross section could be considered as an ellipse which is close to the standard circle after deformation (Walton et al, 2014).…”

Section: Denoising Of Sectional Points and Fitting Of Sectional Linesmentioning

confidence: 99%

Automatic Monitoring of Tunnel Deformation Based on High Density Point Clouds Data

Zhong

Sun

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:An automated method for tunnel deformation monitoring using high density point clouds data is presented. Firstly, the 3D point clouds data are converted to two -dimensional surface by projection on the XOY plane, the projection point set of central axis on XOY plane named Uxoy is calculated by combining the Alpha Shape algorithm with RANSAC ( Random Sampling Consistency ) algorithm, and then the projection point set of central axis on YOZ plane named Uyoz is obtained by highest and lowest points which are extracted by intersecting straight lines that through each point of Uxoy and perpendicular to the two -dimensional surface with the tunnel point clouds, Uxoy and Uyoz together form the 3D center axis finally. Secondly, the buffer of each cross section is calculated by K-Nearest neighbor algorithm, and the initial cross-sectional point set is quickly constructed by projection method. Finally, the cross sections are denoised and the section lines are fitted using the method of iterative ellipse fitting. In order to improve the accuracy of the cross section, a fine adjustment method is proposed to rotate the initial sectional plane around the intercept point in the horizontal and vertical direction within the buffer. The proposed method is used in Shanghai subway tunnel, and the deformation of each section in the direction of 0 to 360 degrees is calculated. The result shows that the cross sections becomes flat circles from regular circles due to the great pressure at the top of the tunnel.

show abstract

Section: Denoising Of Sectional Points and Fitting Of Sectional Linesmentioning

confidence: 99%

Automatic Monitoring of Tunnel Deformation Based on High Density Point Clouds Data

Zhong

Sun

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Morphological trees have been applied to various images. One of the most popular application is biomedical imaging [31][32][33].…”

Section: Related Workmentioning

confidence: 99%

Discriminative Subtree Selection for NBI Endoscopic Image Labeling

Hirakawa

Tamaki

Kurita

et al. 2017

Computer Vision – ACCV 2016 Workshops

View full text Add to dashboard Cite

Abstract. In this paper, we propose a novel method for image labeling of colorectal Narrow Band Imaging (NBI) endoscopic images based on a tree of shapes. Labeling results could be obtained by simply classifying histogram features of all nodes in a tree of shapes, however, satisfactory results are difficult to obtain because histogram features of small nodes are not enough discriminative. To obtain discriminative subtrees, we propose a method that optimally selects discriminative subtrees. We model an objective function that includes the parameters of a classifier and a threshold to select subtrees. Then labeling is done by mapping the classification results of nodes of the subtrees to those corresponding image regions. Experimental results on a dataset of 63 NBI endoscopic images show that the proposed method performs qualitatively and quantitatively much better than existing methods.

show abstract

“…New extensions to those algorithms applied to filamentous structures consider the variation of the structuring elements [14,15], the combination of MM with Hessian matrix analysis [18], and optimally designed algorithms to applications in biology as in [19,20]. Similarly, our paper focuses on the optimization of MM operators for fibrillar structures embedded in large image stacks (3D), considering hybrid architectures for fast processing.…”

Section: Detecting Local-linear Structuresmentioning

confidence: 99%

Structure recognition from high resolution images of ceramic composites

Ushizima

Perciano

Krishnan

et al. 2014

2014 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Fibers provide exceptional strength-to-weight ratio capabilities when woven into ceramic composites, transforming them into materials with exceptional resistance to high temperature, and high strength combined with improved fracture toughness. Microcracks are inevitable when the material is under strain, which can be imaged using synchrotron X-ray computed micro-tomography (µ-CT) for assessment of material mechanical toughness variation. An important part of this analysis is to recognize fibrillar features. This paper presents algorithms for detecting and quantifying composite cracks and fiber breaks from high-resolution image stacks. First, we propose recognition algorithms to identify the different structures of the composite, including matrix cracks and fibers breaks. Second, we introduce our package F3D for fast filtering of large 3D imagery, implemented in OpenCL to take advantage of graphic cards. Results show that our algorithms automatically identify micro-damage and that the GPU-based implementation introduced here takes minutes, being 17x faster than similar tools on a typical image file.

show abstract

Filtering and segmentation of 3D angiographic data: Advances based on mathematical morphology

Cited by 60 publications

References 95 publications

Automatic Monitoring of Tunnel Deformation Based on High Density Point Clouds Data

Automatic Monitoring of Tunnel Deformation Based on High Density Point Clouds Data

Discriminative Subtree Selection for NBI Endoscopic Image Labeling

Structure recognition from high resolution images of ceramic composites

Contact Info

Product

Resources

About