SHREC 2021: 3D point cloud change detection for street scenes

• Published in: Computers & graphics Vol. 99; p. 192
• Main Authors: Ku, Tao, Galanakis, Sam, Boom, Bas, Veltkamp, Remco C, Bangera, Darshan, Gangisetty, Shankar, Stagakis, Nikolaos, Arvanitis, Gerasimos, Moustakas, Konstantinos
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Science Ltd 01.10.2021
• Subjects: Algorithms; Change detection; Computer architecture; Datasets; Machine learning; Oversampling; Shape recognition; Three dimensional models
• ISSN: 0097-8493; 1873-7684
• DOI: 10.1016/j.cag.2021.07.004

The rapid development of 3D acquisition devices enables us to collect billions of points in a few hours. However, the analysis of the output data is a challenging task, especially in the field of 3D point cloud change detection. In this Shape Retrieval Challenge (SHREC) track, we provide a street-scene dataset for 3D point cloud change detection. The dataset consists of 866 3D object pairs in year 2016 and 2020 from 78 large-scale street scene 3D point clouds. Our goal is to detect the changes from multi-temporal point clouds in a complex street environment. We compare three methods on this benchmark, with one handcrafted (PoChaDeHH) and the other two learning-based (HGI-CD and SiamGCN). The results show that the handcrafted algorithm has balanced performance over all classes, while learning-based methods achieve overwhelming performance but suffer from the class-imbalanced problem and may fail on minority classes. The randomized oversampling metric applied in SiamGCN can alleviate this problem. Also, different siamese network architecture in HGI-CD and SiamGCN contribute to the designing of a network for the 3D change detection task.