https://scholars.lib.ntu.edu.tw/handle/123456789/632095
標題: | 3D-GFE: A Three-Dimensional Geometric-Feature Extractor for Point Cloud Data | 作者: | Chou Y.-C Lin Y.-P Yeh Y.-M YI-CHANG LU |
關鍵字: | Classification; Geometric-Feature Descriptor; Point Cloud; Rotation-Invariant; Segmentation | 公開日期: | 2021 | 起(迄)頁: | 2013-2017 | 來源出版物: | 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings | 摘要: | In this paper, we propose a novel framework that extracts rotation-invariant features relative to the centroid and the reference point in a local point set. Furthermore, we search different scales of nearest neighbors simultaneously to acquire more rotation-invariant information around certain specific point cloud data. We evaluate our architecture with two point cloud tasks, object classification and part segmentation. Experiment results show that our method generates consistent results on randomly rotated data and achieves state-of-the-art performance without any rotational data augmentation. For classification, when training and testing with arbitrary rotations, our model is able to reach averagely 89.0% and 73.5% accuracy on the ModelNet40 and ScanObjectNN datasets, respectively. On the ShapeNet dataset, which is a part segmentation task, our model can achieve 77.7% mIOU. © 2021 APSIPA. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126684896&partnerID=40&md5=6e696dd288109b4446bcc1c4bf115642 https://scholars.lib.ntu.edu.tw/handle/123456789/632095 |
SDG/關鍵字: | Nearest neighbor search; Rotation; Feature descriptors; Feature extractor; Geometric feature; Geometric-feature descriptor; Point cloud data; Point-clouds; Reference points; Rotation invariant; Rotation invariant features; Segmentation; Classification (of information) |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。