<3D region segmentation using topological persistence>论文笔记
2017-06-21 14:56
316 查看
引用文献:
Beksi W J, Papanikolopoulos N.
3D region segmentation using topological persistence[C]// Ieee/rsj International Conference on Intelligent Robots and Systems. IEEE, 2016:1079-1084.
该文提出了将全局(拓扑)与局部信息(颜色,表面法向量)结合的三维点云数据分割方法,使用了persistent homology理论,该方法属于基于区域生长的分割方法.
另外,作者提到,当点云数据包含噪声(以至于很难探测出对象边缘),基于区域的分割技术比基于边缘的分割技术更好.
该文提出的新的利用了persistent homology的三维区域分割技术是建立在作者另一篇文章的基础上产生的,另一篇是<3D point cloud segmentation using topological persistence>(IEEE International Conference on Robotics and Automation (ICRA), 2016).当前文章的主要贡献是将全局拓扑与局部信息的结合,从而生成了稳定的点云分割方法.该方法是极为智能自动的,并且对初始化种子点没有要求.另外,选择生长的区域的顺序也对结果没有影响.
(算法没有细看,后续补充...)
Beksi W J, Papanikolopoulos N.
3D region segmentation using topological persistence[C]// Ieee/rsj International Conference on Intelligent Robots and Systems. IEEE, 2016:1079-1084.
该文提出了将全局(拓扑)与局部信息(颜色,表面法向量)结合的三维点云数据分割方法,使用了persistent homology理论,该方法属于基于区域生长的分割方法.
另外,作者提到,当点云数据包含噪声(以至于很难探测出对象边缘),基于区域的分割技术比基于边缘的分割技术更好.
该文提出的新的利用了persistent homology的三维区域分割技术是建立在作者另一篇文章的基础上产生的,另一篇是<3D point cloud segmentation using topological persistence>(IEEE International Conference on Robotics and Automation (ICRA), 2016).当前文章的主要贡献是将全局拓扑与局部信息的结合,从而生成了稳定的点云分割方法.该方法是极为智能自动的,并且对初始化种子点没有要求.另外,选择生长的区域的顺序也对结果没有影响.
(算法没有细看,后续补充...)
相关文章推荐
- Towards Topological Correct Segmentation of Macular OCT from Cascaded FCNs 论文笔记
- 【转】论文阅读笔记-Segmentation-Aware Convolutional Networks Using Local Attention Masks
- Semi-supervised Segmentation of Optic Cup in Retinal Fundus Images Using Variational Autoencoder 论文笔记
- 论文阅读笔记:A 3D Coarse-to-Fine Framework for Automatic Pancreas Segmentation
- 图割论文阅读笔记:Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images
- 论文阅读笔记-Segmentation-Aware Convolutional Networks Using Local Attention Masks
- Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks 视频人脸表情识别论文学习笔记
- 【论文笔记】Region-based Convolutional Networks for Accurate Object Detection and Segmentation
- [深度学习论文笔记][ICCV 17]Semi Supervised Semantic Segmentation Using Generative Adversarial Net
- Region-based Convolutional Networks for Accurate Object Detection and Segmentation----R-CNN论文笔记
- 【论文笔记】Beyond frontal faces: improving person recognition using multiple cues
- 全卷积(FCN)论文阅读笔记:Fully Convolutional Networks for Semantic Segmentation
- 论文笔记 《Rich feature hierarchies for accurate object detection and semantic segmentation》
- 论文笔记--STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- 笔记-论文-OverFeat Integrated Recognition, Localization and Detection using Convolutional Networks
- 【论文笔记】3D人脸重建_简略版(时时更新中)
- 论文阅读笔记:Fully Convolutional Networks for Semantic Segmentation
- 深度学习论文笔记--Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- 论文笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- Boilerplate Detection Using Shallow Text Features论文小笔记