A point cloud decomposition by the 3D level scanning for planes detection

Chmelar, et al.

doi:10.21833/ijaas.2017.011.019

Cited by 4 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and its marking by indexes in the similar way as the classical component labeling. In our last research [9] and [10] the algorithm was mentioned and in this paper we are describing its general form for using with any input 3D data. The pseudo code of describing algorithm gives Fig.…”

Section: Level Connected Component Labelingmentioning

confidence: 99%

“…The two dots show the difference between the level estimation by the data range mean (the orange dot) and the histogram max (ℎ ( )) (the red dot). In our previous research [9] and [10] we used the mean level estimation which provides inaccurate results in comparison with the histogram method for example in situation of Fig. 3.…”

Section: Level Connected Component Labelingmentioning

confidence: 99%

“…An image level gives information about data distribution in a detected level. More information about the level image and its construction is described in our previous work [9] and [10]. Its idea is based on the distance quantization by the parameter .…”

Section: Fig 4 the Level Estimation Stepmentioning

confidence: 99%

“…To introduce our algorithm we used only dimension. For all planes detection is necessary to use left dimension too or use point cloud rotation as we introduce in [9]. When the rotation is used all planes will be detected even without priory information about input point cloud orientation.…”

Section: Fig 4 the Level Estimation Stepmentioning

confidence: 99%

“…In the next papers [9] and [10] we described a method for point cloud plane visualization by using the level image. The level image is a tool for expressing the points' presence in specific point cloud levels via an image.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Advanced plane properties by using level image

Chmelar

Beran

Chmelarova

et al. 2018

2018 28th International Conference Radioelektronika (RADIOELEKTRONIKA)

View full text Add to dashboard Cite

This paper deals with advanced plane properties in analyzed point clouds. Planes are detected by the level connected component labeling, which is our modification of the classical algorithm for 3D data. According selected detection parameters and a scanning dimension the algorithm detects individual levels in an input point cloud. A level is presented by an image expressing the points' presence at a specific level in a space, we call it level image. The pixel size in a level image is equal to the point cloud distance quantization. This connection allows us to use image processing methods to get important properties about the analyzed 3D space, which can be difficult to get by the standard mathematical solution. Image processing methods offers a simple plane segmentation and visualization or area and perimeter estimation including statistical data description. The results show level image advantages.

show abstract

Section: Level Connected Component Labelingmentioning

confidence: 99%

Section: Level Connected Component Labelingmentioning

confidence: 99%

Section: Fig 4 the Level Estimation Stepmentioning

confidence: 99%

Section: Fig 4 the Level Estimation Stepmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Advanced plane properties by using level image

Chmelar

Beran

Chmelarova

et al. 2018

2018 28th International Conference Radioelektronika (RADIOELEKTRONIKA)

View full text Add to dashboard Cite

show abstract

The Fine Plane Range Estimation From Point Cloud

Chmelarova

Chmelar

Rejfek

2019

2019 29th International Conference Radioelektronika (RADIOELEKTRONIKA)

View full text Add to dashboard Cite

This paper deals with the fine plane estimation. For a plane detection the level connected component labeling algorithm is used. The precise plane position is determined by the plane's points histogram in the scanning dimension. Up till now, the final plane's range has been selected manually by a parameter. Plane presence in an input point cloud represents the higher points' concentration in the scanning dimension, higher than average value. The concentration decreases on both sides from a local maximum value. This paper presents the algorithm of the elbows' position estimation for the optimal plane's points range expression. The experimental part shows practical results of several examples and gives recommendations for parameters setting.

show abstract

Advanced Methods for Point Cloud Processing and Simplification

et al. 2020

View full text Add to dashboard Cite

Nowadays, mobile robot exploration needs a rangefinder to obtain a large number of measurement points to achieve a detailed and precise description of a surrounding area and objects, which is called the point cloud. However, a single point cloud scan does not cover the whole area, so multiple point cloud scans must be acquired and compared together to find the right matching between them in a process called registration method. This method requires further processing and places high demands on memory consumption, especially for small embedded devices in mobile robots. This paper describes a novel method to reduce the burden of processing for multiple point cloud scans. We introduce our approach to preprocess an input point cloud in order to detect planar surfaces, simplify space description, fill gaps in point clouds, and get important space features. All of these processes are achieved by applying advanced image processing methods in combination with the quantization of physical space points. The results show the reliability of our approach to detect close parallel walls with suitable parameter settings. More importantly, planar surface detection shows a 99% decrease in necessary descriptive points almost in all cases. This proposed approach is verified on the real indoor point clouds.

show abstract

A point cloud decomposition by the 3D level scanning for planes detection

Cited by 4 publications

References 8 publications

Advanced plane properties by using level image

Advanced plane properties by using level image

The Fine Plane Range Estimation From Point Cloud

Advanced Methods for Point Cloud Processing and Simplification

Contact Info

Product

Resources

About