A Novel Point Cloud Registration Method Based on ROPNet
Open Access
Abstract
Point cloud registration is a crucial preprocessing step for point cloud data analysis and applications. Nowadays, many deep-learning-based methods have been proposed to improve the registration quality. These methods always use the sum of two cross-entropy as a loss function to train the model, which may lead to mismatching in overlapping regions. In this paper, we designed a new loss function based on the cross-entropy and applied it to the ROPNet point cloud registration model. Meanwhile, we improved the ROPNet by adding the channel attention mechanism to make the network focus on both global and local important information, thus improving the registration performance and reducing the point cloud registration error. We tested our method on ModelNet40 dataset, and the experimental results demonstrate the effectiveness of our proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (62101392, 2022420612000585)
- Stability Module trial production Project of the State Grid Hubei Power Research Institute (62101392, 2022420612000585)
This publication has 24 references indexed in Scilit:
- Circle Loss: A Unified Perspective of Pair Similarity Optimization2020
- RPM-Net: Robust Point Matching Using Learned Features2020
- Dice Loss for Data-imbalanced NLP Tasks2020
- Dual Attention Network for Scene Segmentation2019
- Real-Time Point Cloud Alignment for Vehicle Localization in a High Resolution 3D Map2019
- Squeeze-and-Excitation Networks2018
- Focal Loss for Dense Object Detection2017
- A Discriminative Feature Learning Approach for Deep Face Recognition2016
- KinectFusion2011
- Weighted rank aggregation of cluster validation measures: a Monte Carlo cross-entropy approachBioinformatics, 2007