标题: An anchor-based graph method for detecting and classifying indoor objects from cluttered 3D point clouds
作者: Su, F (Su, Fei); Zhu, HH (Zhu, Haihong); Chen, TY (Chen, Taoyi); Li, L (Li, Lin); Yang, F (Yang, Fan); Peng, HX (Peng, Huixiang); Tang, L (Tang, Lei); Zuo, XK (Zuo, Xinkai); Liang, YF (Liang, Yifan); Ying, S (Ying, Shen)
来源出版物: ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 卷: 172 页: 114-131 DOI: 10.1016/j.isprsjprs.2020.12.007 出版年: FEB 2021
摘要: Most of the existing 3D indoor object classification methods have shown impressive achievements on the assumption that all objects are oriented in the upward direction with respect to the ground. To release this assumption, great effort has been made to handle arbitrarily oriented objects in terrestrial laser scanning (TLS) point clouds. As one of the most promising solutions, anchor-based graphs can be used to classify freely oriented objects. However, this approach suffers from missing anchor detection since valid detection relies heavily on the completeness of an anchor's point clouds and is sensitive to missing data. This paper presents an anchor-based graph method to detect and classify arbitrarily oriented indoor objects. The anchors of each object are extracted by the structurally adjacent relationship among parts instead of the parts' geometric metrics. In the case of adjacency, an anchor can be correctly extracted even with missing parts since the adjacency between an anchor and other parts is retained irrespective of the area extent of the considered parts. The best graph matching is achieved by finding the optimal corresponding node-pairs in a super-graph with fully connecting nodes based on maximum likelihood. The performances of the proposed method are evaluated with three indicators (object precision, object recall and object Fl-score) in seven datasets. The experimental tests demonstrate the effectiveness of dealing with TLS point clouds, RGBD point clouds and Panorama RGBD point clouds, resulting in performance scores of approximately 0.8 for object precision and recall and over 0.9 for chair precision and table recall.
作者关键词: Point cloud; Object classification; Functional part; Graph matching; Super-graph; Graph similarity
地址: [Su, Fei; Zhu, Haihong; Li, Lin; Yang, Fan; Tang, Lei; Zuo, Xinkai; Liang, Yifan; Ying, Shen] Wuhan Univ, Sch Resource & Environm Sci, 129 Luoyu Rd, Wuhan 430079, Peoples R China.
[Chen, Taoyi; Peng, Huixiang] 54th Res Inst CETC, 589 Zhongshan West Rd, Shijiazhuang 050081, Hebei, Peoples R China.
通讯作者地址: Zhu, HH; Li, L (通讯作者)，Wuhan Univ, Sch Resource & Environm Sci, 129 Luoyu Rd, Wuhan 430079, Peoples R China.
电子邮件地址: firstname.lastname@example.org; email@example.com; firstname.lastname@example.org; email@example.com; firstname.lastname@example.org; email@example.com; firstname.lastname@example.org; email@example.com; firstname.lastname@example.org; email@example.com
版权所有 © 威尼人登录网址_新威利斯人官网