Local-to-global structure prior guided high-precision point cloud registration framework based on FPP. (15th June 2023)

• Record Type: Journal Article
• Authors: Wang, Xingguo; Chen, Xiaoyu; Han, Jing; Zhang, Yi; Zheng, Dongliang
• Is Part Of: Measurement. Volume 214(2023)
• Publication Date: 2023-06-15
• Subjects: Registration -- Fringe projection profilometry -- Point cloud -- Structure prior; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2023.112840
• Languages: English
• ISSNs: 0263-2241

Abstract

Abstract: As one of the popular point cloud reconstruction technologies, fringe projection profilometry (FPP) has great application prospects in point cloud registration from different viewing angles. While the existing point cloud registration algorithm that focuses on FPP is limited to high-speed fringe projection system. Besides, the deep learning methods based on the global feature retrieval mechanism can hardly mine the multi-modal data features of FPP, and are difficult to meet the accuracy requirements of FPP. To address the above issue, we design a local–global structure prior guided high-precision registration framework that focuses on the FPP data characteristics. Specifically, the consistent clustering matching (CCM) module is proposed firstly to obtain the structure priors of cluster correspondences in the overlap regions by analyzing the FPP multi-modal data. Then the local-cluster interaction network (LCINet) guided by the structure priors is introduced for feature extraction and interaction. Finally, the spatial alignment module based on cluster voting(SACV) is proposed to select cluster correspondences with high confidence to calculate the transformation matrix and align point clouds. Experiments show that our method achieves state-of-the-art performance on the dataset collected by FPP, and our framework can also greatly improve the training efficiency and performance of other deep learning models. Highlights: The consistent clustering matching module is proposed to obtain the structure priors of cluster correspondences. The local-cluster interaction network is introduced for feature extraction and interaction. The spatial alignment module is proposed to calculate the reliable transformation matrix.