3D Hough transform for sphere recognition on point clouds

Camurri, Marco; Vezzani, Roberto; Cucchiara, Rita

doi:10.1007/s00138-014-0640-3

Cited by 39 publications

(25 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows to carefully segment each organ individually based on specifically adapted algorithms. For example, for automatic segmentation of the eyes and spinal cord the expected shape of the resulting label (number allocated for each voxel specific for the tissue of interest) was taken into account, namely a sphere and a tube respectively 35 – 37 . Segmentation of organs such as head nephros and liver was based on the texture analysis due to high tissue contrast 38 – 40 .…”

Section: Resultsmentioning

confidence: 99%

Quantitative morphometric analysis of adult teleost fish by X-ray computed tomography

Weinhardt¹,

Shkarin²,

Wernet³

et al. 2018

Sci Rep

View full text Add to dashboard Cite

Vertebrate models provide indispensable paradigms to study development and disease. Their analysis requires a quantitative morphometric study of the body, organs and tissues. This is often impeded by pigmentation and sample size. X-ray micro-computed tomography (micro-CT) allows high-resolution volumetric tissue analysis, largely independent of sample size and transparency to visual light. Importantly, micro-CT data are inherently quantitative. We report a complete pipeline of high-throughput 3D data acquisition and image analysis, including tissue preparation and contrast enhancement for micro-CT imaging down to cellular resolution, automated data processing and organ or tissue segmentation that is applicable to comparative 3D morphometrics of small vertebrates. Applied to medaka fish, we first create an annotated anatomical atlas of the entire body, including inner organs as a quantitative morphological description of an adult individual. This atlas serves as a reference model for comparative studies. Using isogenic medaka strains we show that comparative 3D morphometrics of individuals permits identification of quantitative strain-specific traits. Thus, our pipeline enables high resolution morphological analysis as a basis for genotype-phenotype association studies of complex genetic traits in vertebrates.

show abstract

Section: Resultsmentioning

confidence: 99%

Quantitative morphometric analysis of adult teleost fish by X-ray computed tomography

Weinhardt¹,

Shkarin²,

Wernet³

et al. 2018

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Especially sphere targets are used extensively for camera and laser scanner calibration or data registration in which robust sphere detection and estimation are necessary to achieve good results [13][14][15]. Plenty of approaches for sphere segmentation or extraction from point cloud have been proposed, such as the clustering-based method [16,17], sampling-based method [14,18], and Hough transform-based method [19,20], etc. However, most of these methods more or less have limitations, including the robustness to outliers or noise, computation time, requirements for the exposed spherical area and prior information, etc.…”

Section: Algorithms For Sphere Detectionmentioning

confidence: 99%

Monitoring of the Production Process of Graded Concrete Component Using Terrestrial Laser Scanning

et al. 2021

View full text Add to dashboard Cite

Accepting the ecological necessity of a drastic reduction of resource consumption and greenhouse gas emissions in the building industry, the Institute for Lightweight Structures and Conceptual Design (ILEK) at the University of Stuttgart is developing graded concrete components with integrated concrete hollow spheres. These components weigh a fraction of usual conventional components while exhibiting the same performance. Throughout the production process of a component, the positions of the hollow spheres and the level of the fresh concrete have to be monitored with high accuracy and in close to real-time, so that the quality and structural performance of the component can be guaranteed. In this contribution, effective solutions of multiple sphere detection and concrete surface modeling based on the technology of terrestrial laser scanning (TLS) during the casting process are proposed and realized by the Institute of Engineering Geodesy (IIGS). A complete monitoring concept is presented to acquire the point cloud data fast and with high-quality. The data processing method for multiple sphere segmentation based on the efficient combination of region growing and random sample consensus (RANSAC) exhibits great performance on computational efficiency and robustness. The feasibility and reliability of the proposed methods are verified and evaluated by an experiment monitoring the production of an exemplary graded concrete component. Some suggestions to improve the monitoring performance and relevant future work are given as well.

show abstract

“…The experimental results with point clouds show that the randomized method performed better than other variants. Camurri et al [102] implemented both traditional and randomized HTs to detect spheres, but they used every point together with its associated normal to determine the plane in the 3-D space corresponding to one vote in the Hough space. This was in lieu of randomly generating planes to cast votes [103], [104].…”

Section: A Shape Primitivesmentioning

confidence: 99%

Geometric Primitives in LiDAR Point Clouds: A Review

Xia

Chen

Wang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

To the best of our knowledge, the most recent light detection and ranging (lidar)-based surveys have been focused only on specific applications such as reconstruction and segmentation, as well as data processing techniques based on a specific platform, e.g., mobile laser. However, in this article, lidar point clouds are understood from a new and universal perspective, i.e., geometric primitives embedded in versatile objects in the physical world. In lidar point clouds, the basic unit is the point coordinate. Geometric primitives that consist of a group of discrete points may be viewed as one kind of abstraction and representation of lidar data at the entity level. We categorize geometric primitives into two classes: shape primitives, e.g., lines, surfaces, and volumetric shapes, and structure primitives, represented by skeletons and edges. In recent years, many efforts from different communities, such as photogrammetry, computer vision, and computer graphics, have been made to finalize geometric primitive detection, regularization, and in-depth applications. Interpretations of geometric primitives from multiple disciplines try to convey the significance of geometric primitives, the latest processing techniques regarding geometric primitives, and their potential possibilities in the context of lidar point clouds. To this end, primitive-based applications are reviewed with an emphasis on object extraction and reconstruction to clearly show the significances of this article. Next, we survey and compare methods for geometric primitive extraction and then review primitive regularization methods that add real-world constrains to initial primitives. Finally, we summarize the challenges, expected applications, and describe possible future for primitive extraction methods that can achieve globally optimal results efficiently, even with disorganized, uneven, noisy, incomplete, and large-scale lidar point clouds.

show abstract

3D Hough transform for sphere recognition on point clouds

Cited by 39 publications

References 29 publications

Quantitative morphometric analysis of adult teleost fish by X-ray computed tomography

Quantitative morphometric analysis of adult teleost fish by X-ray computed tomography

Monitoring of the Production Process of Graded Concrete Component Using Terrestrial Laser Scanning

Geometric Primitives in LiDAR Point Clouds: A Review

Contact Info

Product

Resources

About