Developing a Reassembling Algorithm for Broken Objects

Jia, Caiqin; He, Ligang; Yang, Xia; Han, Xingcheng; Chang, Bobo

doi:10.1109/access.2020.3042261

Cited by 7 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of method is more sensitive to parameters and threshold values, and setting the size of a single neighborhood for different areas of the point cloud is not suitable for identifying features. Compared with the method in Jia et al [14], the recognition rate of the method in this paper is relatively decreased because of the generation of some false feature points caused by the redundancy of feature points when selecting the parameters by the multi-scale neighborhood method. The sensitivity to noise is relatively increased because the proposed method in Jia et al [14] used the multi-scale neighborhood method to calculate the point cloud features.…”

Section: Results Of Comparison With Existing Methodsmentioning

confidence: 93%

“…Compared with the method in Jia et al [14], the recognition rate of the method in this paper is relatively decreased because of the generation of some false feature points caused by the redundancy of feature points when selecting the parameters by the multi-scale neighborhood method. The sensitivity to noise is relatively increased because the proposed method in Jia et al [14] used the multi-scale neighborhood method to calculate the point cloud features. Furthermore, the proposed method not only reduces the parameter setting, but also improves the robustness to noise at a certain degree, which effectively enhances the adaptability of the algorithm.…”

Section: Results Of Comparison With Existing Methodsmentioning

confidence: 93%

“…The noise deviation is set to [0.1, 0.5]. Under the same hardware environment, the methods in Zhang et al [41], Xia and Wang [34], and Jia et al [14] are used together with the method proposed in this paper to calculate the feature point extraction rates, respectively, to conduct an experimental comparative analysis, the results of which are shown in Fig. 9.…”

Section: Results Of Comparison With Existing Methodsmentioning

confidence: 99%

“…Fu and Wu [9] used the geometric relationship between adjacent points to calculate the lineto-intercept ratio, based on which the feature points of the model could be identified. Moreover, multi-scale feature extraction technology improved the accuracy of feature recognition and enhanced the noise resistance of the algorithm [3,14,16,19,29].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Feature Extraction Algorithm Based on Optimal Neighborhood Size

Jia

Pang

Xie

2022

Circuits Syst Signal Process

Self Cite

View full text Add to dashboard Cite

The feature extraction of a point cloud fragment model is the basis of fragment splicing, which provides the technical support for research on the segmentation, splicing, and restoration of fragment surfaces. High-quality feature extraction, however, is a complicated process due to the diversity of the surface information of a fragment model. For this subject, a high-efficient point cloud feature extraction method was proposed to address a new method for extracting feature lines. First, the projection distance feature of the point cloud model was calculated to identify the potential feature points. Furthermore, the local information of the possible feature points was used to construct the adaptive neighborhoods for identifying the feature points based on neighborhoods of the model. The clustering fusion of the feature points was proposed according to the discrimination threshold values of the feature points. Finally, the Laplace operator was utilized to refine and connect the feature points to form smooth feature lines. The experimental results showed that the proposed method was automatic, highly efficient, and with good adaptability that could effectively extract the detailed features and construct the complete feature lines. Moreover, results showed that the provided framework could extract the features of simple structure models and be feasible to a certain extent for fragment models with abundant features.

show abstract

Section: Results Of Comparison With Existing Methodsmentioning

confidence: 93%

Section: Results Of Comparison With Existing Methodsmentioning

confidence: 93%

Section: Results Of Comparison With Existing Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Feature Extraction Algorithm Based on Optimal Neighborhood Size

Jia

Pang

Xie

2022

Circuits Syst Signal Process

Self Cite

View full text Add to dashboard Cite

show abstract

“…For more accurate selection of sample subsets, Jia C.Q. etc (Jia C.Q., 2020) adds three improvements to this method: 1) Setting the best matching degree during the iteration; 2) After ensuring a minimum subset of three, adding only one pair of feature matching point pairs for verification based on the smallest subset, ensuring that only four pairs of feature matching points need to be computed each time; 3) The correct point pairs already computed will not appear in subsequent iterations. The improved method can further reduce the amount of computation and improve the efficiency of the algorithm.…”

Section: Finding Neighbouring Fragmentsmentioning

confidence: 99%

Research Progress in the Splicing and Restoration of Artifact Fragments Based on Point Cloud

Zhao,

Yin,

Yang

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Due to environmental reasons, most of the artifacts are fragmented, and the surface information of the artifacts is also blurred. The traditional method of repairing artifacts mainly relies on archaeologists to manually repair them, using fragment features to compare each fragment one by one, this method will cause secondary damage to the fragments. Based on computer technology, virtual restoration of artifacts fragments can obtain the latest unearthed data of artifacts quickly, preserve digital information of artifacts, achieve permanent preservation, and provide prior knowledge for subsequent artifacts restoration. Point cloud data is widely used in artifacts virtual restoration technology due to its good depth of information. This paper takes ceramics, bronzes, Terra-cotta Warriors, and other individual artifacts fragments as the main research object, and the point cloud data obtained by 3D laser scanner as the main research data. It comprehensively classifies and summarizes the work of computer artifacts splicing in recent years.

show abstract