Sharp feature extraction in point clouds

Cao, Junyi; Silamu, Wushour; Yao, Xiaomin; Li, N.; Liang, Jian; Liang, Xiaohui

doi:10.1049/iet-ipr.2011.0361

Cited by 13 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PCA approach has been widely used in many fields. Cao et al [23] used PCA to estimate the normal directions of the obtained candidate sharp feature points to extract sharp features from point clouds. Humberstone et al [24] used PCA to differentiate between expanded and fault conditions.…”

Section: Principal Component Analysismentioning

confidence: 99%

Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration

Gao¹,

Qiao²

2013

Laser Phys.

View full text Add to dashboard Cite

There exists plenty of welding quality information on a molten pool during high-power fiber laser welding. An approach for monitoring the high-power fiber laser welding status based on the principal component analysis (PCA) of a molten pool configuration is investigated. An infrared-sensitive high-speed camera was used to capture the molten pool images during laser butt-joint welding of Type 304 austenitic stainless steel plates with a high-power (10 kW) continuous wave fiber laser. In order to study the relationship between the molten pool configuration and the welding status, a new method based on PCA is proposed to analyze the welding stability by comparing the situation when the laser beam spot moves along, and when it deviates from the weld seam. Image processing techniques were applied to process the molten pool images and extract five characteristic parameters. Moreover, the PCA method was used to extract a composite indicator which is the linear combination of the five original characteristics to analyze the different status during welding. Experimental results showed that the extracted composite indicator had a close relationship with the actual welding results and it could be used to evaluate the status of the high-power fiber laser welding, providing a theoretical basis for the monitoring of laser welding quality.

show abstract

Section: Principal Component Analysismentioning

confidence: 99%

Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration

Gao¹,

Qiao²

2013

Laser Phys.

View full text Add to dashboard Cite

show abstract

“…In the point cloud processing area, the existing feature detection methods can be classified into two main groups: polygonal-based methods [13,14] and point-based methods [15,16]. The former method generates a set of edges by using the connectivity information and normal associated with the underlying polygonal meshes.…”

Section: B 3d Edge Extractionmentioning

confidence: 99%

Edge extraction by merging 3D point cloud and 2D image data

Wang

Ewert

Schilberg

et al. 2013

2013 10th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT)

View full text Add to dashboard Cite

Edges provide important visual information by corresponding to discontinuities in the physical, photometrical and geometrical properties of scene objects, such as significant variations in the reflectance, illumination, orientation and depth of scene surfaces. The significance has drawn many people to work on the detection and extraction of edge features. The characteristics of 3D point clouds and 2D digital images are thought to be complementary, so the combined interpretation of objects with point clouds and image data is a promising approach to describe an object in computer vision area. However, the prerequisite for different levels of integrated data interpretation is the geometric referencing between the 3D point cloud and 2D image data, and a precondition for geometric referencing lies in the extraction of the corresponding features. Addressing the wide-ranged applications of edge detection in object recognition, image segmentation and pose identification, this paper presents a novel approach to extract 3D edges. The main idea is combining the edge data from a point cloud of an object and its corresponding digital images. Our approach is aimed to make use of the advantages of both edge processing and analysis of point clouds and image processing to represent the edge characteristics in 3D with increased accuracy. On the 2D image processing part, an edge extraction is applied on the image by using the Canny edge detection algorithm after the raw image data pre-processing. An easily-operating pixel data mapping mechanism is proposed in our work for corresponding 2D image pixels with 3D point cloud pixels. By referring to the correspondence map, 2D edge data are merged into 3D point cloud. On the point cloud part, the border extracting operator is performed on the range image. As a preparation work, the raw point cloud data are used to generate a range image. Edge points in the range image, points with range, are converted to 3D point type with the application of the Point Cloud Library (PCL) to define the edges in the 3D point cloud.

show abstract

“…Effective estimation of point-cloud normal vectors is the basis of pointcloud data processing. In addition, many effective point-cloud processing methods also require accurate normal vectors as input, such as feature extraction [13,14], data segmentation [15][16][17][18], and so on. Point-cloud normal-vector estimation has thus been thoroughly studied.…”

Section: Introductionmentioning

confidence: 99%

Normal estimation of point cloud based on sub-neighborhood clustering

Hao¹,

Huang²,

2018

Meas. Sci. Technol.

View full text Add to dashboard Cite

In this paper, we propose a method to estimate normal vectors based on neighborhood clustering segmentation, which improves the accuracy of normal-vector estimation for sharp features. The proposed method adjusts the neighborhood through Gauss mapping and clustering segmentation to solve the problem of inaccurate estimation of the normal vector in the sharp-feature region. First, the normal vectors of the point cloud are initially estimated by principal component analysis (PCA). Next, the neighborhood of points from different patches, which are close to the sharp feature, are mapped to a unit Gauss sphere, and the point cloud on the unit sphere is clustered. All points of the cluster belonging to the target point are divided into sub-neighborhoods. Finally, with this sub-neighborhood as input, the normal vector of the point is accurately calculated by PCA. Experiments show that, even for noise and non-uniform sampling, the method proposed herein outperforms previous methods in terms of quality of results and running time.

show abstract

Sharp feature extraction in point clouds

Cited by 13 publications

References 17 publications

Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration

Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration

Edge extraction by merging 3D point cloud and 2D image data

Normal estimation of point cloud based on sub-neighborhood clustering

Contact Info

Product

Resources

About