一种基于遮罩的稀疏点云滤波算法

doi:10.11896/jsjkx.210600129

计算机科学 ›› 2022, Vol. 49 ›› Issue (5): 25-32.doi: 10.11896/jsjkx.210600129

• 计算机图形学&多媒体^* • 上一篇下一篇

一种基于遮罩的稀疏点云滤波算法

封雷^1,2, 朱登明¹, 李兆歆¹, 王兆其¹

1 中国科学院计算技术研究所北京100190
2 中国科学院大学计算机科学与技术学院北京100049

收稿日期:2021-06-16 修回日期:2021-12-06 出版日期:2022-05-15 发布日期:2022-05-06
通讯作者: 朱登明(mdzhu@ict.ac.cn)
作者简介:(27246540632qq.com)
基金资助:
国家重点研发计划(2020YFB1710400);中国科学院科研仪器设备研制项目(YJKYYQ20190055)

Sparse Point Cloud Filtering Algorithm Based on Mask

FENG Lei^1,2, ZHU Deng-ming¹, LI Zhao-xin¹, WANG Zhao-qi¹

1 Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China
2 School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049,China

Received:2021-06-16 Revised:2021-12-06 Online:2022-05-15 Published:2022-05-06
About author:FENG Lei,born in 1998,postgraduate.His main research interests include 3D reconstruction and so on.
ZHU Deng-ming,born in 1973,Ph.D,associate researcher,master supervisor,is a member of China Computer Federation.His main research interests include virtual reality and human-computer interaction.
Supported by:
National Key R & D Program of China(2020YFB1710400) and Scientific Research Instrument and Equipment Development Project of Chinese Academy of Sciences(YJKYYQ20190055).

摘要/Abstract

摘要： 基于图像的三维重建硬件约束小、成本低、灵活度高,在实际中得到广泛应用,但物体各部分之间存在遮挡,导致由图像生成的三维点云数据稀疏和密度不均等问题,一直是处理的难点和热点。文中提出一种基于遮罩的稀疏点云滤波算法。首先计算点云的包围盒,并在包围盒中根据点云的稀疏度自适应地划分栅格;其次,利用深度优先搜索,递归求出所有由栅格组成的自定义连通域;然后基于量化重要性指标来自适应计算阈值,通过该自适应阈值选择应保留的连通域,将所有保留的连通域集合定义为遮罩,用于描述稀疏点云的全局空间拓扑信息;最后,保留遮罩覆盖区域的点云,剔除遮罩未覆盖区域的点云,从而达到滤除离群点的目的。该方法能很好地处理由于遮挡生成的、空间疏密程度有较大差异的点云数据,可以有效去除原始三维点云数据中的离群点,同时较好地保持点云的细节信息。

关键词: 点云滤波, 立体匹配, 三角网格处理, 三维重建, 遮罩

Abstract: Image-based 3D reconstruction is widely used in practice due to less hardware constraints,lower cost and higher flexibility.Especially for the problems of sparseness and uneven density of the three-dimensional point cloud data generated by the image due to the occlusion between various parts of the object,it has always been a difficulty and hot issue to deal with.In this paper,a mask-based sparse point cloud filtering algorithm is proposed.Firstly,the bounding box of the point cloud is calculated and the grid is adaptively divided according to the sparseness of the point cloud.Secondly,Depth-first search is used to recursively find all customized connected domains composed of grids generated at the first step.Then adaptively calculating the threshold based on the quantized importance index,selecting the connected domains that should be retained based on the adaptive threshold,and defining the set of all retained connected domains as a mask,which is used to describe the global spatial topology information of the sparse point cloud.Finally,points covered by the mask are retained while points of the uncovered area are removed,so as to filter the outliers.This method can handle the point cloud data generated by occlusion and with great differences in spatial density.It can effectively remove outliers in the original three-dimensional point cloud data,while maintaining the detailed information of the point cloud.

Key words: 3D reconstruction, Mask, Point cloud filtering, Stereomatching, Triangular mesh processing

中图分类号:

G312

封雷, 朱登明, 李兆歆, 王兆其. 一种基于遮罩的稀疏点云滤波算法[J]. 计算机科学, 2022, 49(5): 25-32. https://doi.org/10.11896/jsjkx.210600129

FENG Lei, ZHU Deng-ming, LI Zhao-xin, WANG Zhao-qi. Sparse Point Cloud Filtering Algorithm Based on Mask[J]. Computer Science, 2022, 49(5): 25-32. https://doi.org/10.11896/jsjkx.210600129

参考文献

[1]QI C R,SU H,MO K,et al.PointNet:Deep Learning on Point Sets for 3D Classification and Segmentation[C]//CVPR.2017:77-85.
[2]ZHANG D,LU X,QIN H,et al.Pointfilter:Point Cloud Filtering via Encoder-Decoder Modeling[J].IEEE Transactions on Visualization and Computer Graphics,2021:27,2015-2027.
[3]TAUBIN.(1999).A Signal Processing Approach To Fair Surface Design[C]//Computer Graphics(Proceedings of Siggraph’95).1999.
[4]ZHANG Y,LIU X M,SUI Y,et al.Research and improvement of denoising method based on K-neighbors[J].Journal of Computer Applications,2009,29(4):1011-1014.
[5]LIANG X H,LIANG J,GUO C,et al.Research on Noise Re-duction Technology of Scattered Point Clouds Based on Adaptive Optimal Neighborhood[J].China Mechanical Engineering,2010(6):639-643.
[6]LIU Y,XI X,WANG C,et al.An Improved Progressive Encrypted Triangular Mesh Point Cloud Filtering Algorithm[J].Photogrammetry and Remote Sensing,2020,5:106-111.
[7]CHEN J H.Combining principal component analysis and local neighborhood planar point cloud denoising[J].Bulletin of Surveying and Mapping,2020(5):47-50,68.
[8]ZHAN Z Q,HU M Q,MAN Y Y.Multi-scale Regional Growing Point Cloud Filtering Surface Fitting Method[J].Bulletin of Surveying and Mapping,2020,49(6):757-766.
[9]ZHU X X,WANG C,XI X H,et al.Hierachical ThresholdAdaptive for Point Cloud Filter Algorithm of Moving Surface Fitting[J].Acta Geodaetica et Cartographica Sinica,2018,47(2):153-160.
[10]ZHU R,MA S,XU D.Guided Filter Simplification Method for Noisy Point Cloud Data[C]//2020 Chinese Automation Congress (CAC).2020.
[11]HE K M,JIAN S,TANG X.Guided Image Filtering[J].IEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[12]SCHARSTEIN D,SZELISKI R,ZABIH R.A Taxonomy andEvaluation of Dense Two-Frame Stereo Correspondence Algorithms[C]//Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision.2001:131-140.
[13]GEIGER A,ROSER M,URTASUN R.Efficient Large-ScaleStereo Matching[M]//Computer Vision－ACCV 2010.Berlin:Springer,2010.
[14]HAEUSLER R,NAIR R,KONDERMANN D.Ensemble Lear-ning for Confidence Measures in Stereo Vision[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2013:305-312.
[15]HIRSCHMULLER H,SCHARSTEIN D.Evaluation of CostFunctions for Stereo Matching[C]//IEEE Conference on Computer Vision and Pattern Recognition.2007.
[16]HIRSCHMULLER H.Stereo processing by semiglobalma-tching and mutual information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(2):328-341.
[17]ZAGORUYKO S,KOMODAKIS N.Learning to compare image patches via convolutional neural networks[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2015:4353-4361.
[18]LUO W,SCHWING A G,URTASUN R.Efficient Deep Lear-ning for Stereo Matching[C]//IEEE Conference on Computer Vision & Pattern Recognition.2016:5695-5703.
[19]FLYNN J,NEULANDER I,PHILBIN J,et al.DeepStereo:Learning to Predict New Views from the World’s Imagery[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:5515-5524.
[20]EIGEN D,PUHRSCH C,FERGUS R.Depth map predictionfroma single image using a multi-scale deep network[J].NIPS,2014,3:1-9.
[21]MAYER N,ILG E,HAUSSER P,et al.A Large Dataset toTrain Convolutional Networks for Disparity,Optical Flow,and Scene Flow Estimation[J].arXiv:1512.02134,2015.
[22]KENDALL A,MARTIROSYAN H,DASGUPTA S,et al.End-to-End Learning of Geometry and Context for Deep Stereo Regression[C]//IEEE International Conference on Computer Vision (ICCV).2017:66-75.

相关文章 15

[1]	张鹏, 王新晴, 肖毅, 段宝国, 许鸿辉. 基于语义边缘驱动的实时双目深度估计算法 Real-time Binocular Depth Estimation Algorithm Based on Semantic Edge Drive 计算机科学, 2021, 48(9): 216-222. https://doi.org/10.11896/jsjkx.200800203
[2]	曹林, 于威威. 基于图像分割的自适应窗口双目立体匹配算法研究 Adaptive Window Binocular Stereo Matching Algorithm Based on Image Segmentation 计算机科学, 2021, 48(11A): 314-318. https://doi.org/10.11896/jsjkx.201200264
[3]	马俊成, 蒋慕蓉, 房素芹. 基于改进Marching Tetrahedra算法的锥体气象数据三维重建 Three-dimensional Reconstruction of Cone Meteorological Data Based on Improved MarchingTetrahedra Algorithm 计算机科学, 2021, 48(11A): 644-647. https://doi.org/10.11896/jsjkx.210200025
[4]	桑苗苗, 彭进先, 达通航, 张旭峰. 基于PatchMatch的半全局高效双目立体匹配算法 Efficient Semi-global Binocular Stereo Matching Algorithm Based on PatchMatch 计算机科学, 2021, 48(1): 204-208. https://doi.org/10.11896/jsjkx.191000205
[5]	朱玲莹, 桑庆兵, 顾婷婷. 基于视差信息的无参考立体图像质量评价 No-reference Stereo Image Quality Assessment Based on Disparity Information 计算机科学, 2020, 47(9): 150-156. https://doi.org/10.11896/jsjkx.190700213
[6]	曾俊飞,杨海清,吴浩. 面向三维重建的自适应列文伯格-马夸尔特点云配准方法 Adaptive Levenberg-Marquardt Cloud Registration Method for 3D Reconstruction 计算机科学, 2020, 47(3): 137-142. https://doi.org/10.11896/jsjkx.190200261
[7]	苗绘翠, 王吉华, 张全英. 基于单视图三维重建的凹凸制造特征识别 Concave-convex Manufacturing Features Recognition Based on 3D Reconstruction of Single View 计算机科学, 2019, 46(7): 280-285. https://doi.org/10.11896/j.issn.1002-137X.2019.07.043
[8]	王钱庆, 张惊雷. 基于三维形变模型的人脸姿势表情校正 Face Pose and Expression Correction Based on 3D Morphable Model 计算机科学, 2019, 46(6): 263-269. https://doi.org/10.11896/j.issn.1002-137X.2019.06.039
[9]	杜娟, 沈思昀. 基于改进多权值滑动窗口的立体匹配方法的实现及应用 Implementation and Application of Stereo Matching Method Based onImproved Multi-weight Sliding Window 计算机科学, 2019, 46(11A): 241-245.
[10]	李银国, 周中奎, 白羚. 基于双目图像的大尺度智能驾驶场景重建 Large-scale Automatic Driving Scene Reconstruction Based on Binocular Image 计算机科学, 2019, 46(11A): 251-254.
[11]	江泽涛, 王琦, 赵艳. 一种基于自适应支持权重优化的立体匹配算法 Stereo Matching Algorithm Based on Adaptive Support Weight Optimization 计算机科学, 2018, 45(8): 242-246. https://doi.org/10.11896/j.issn.1002-137X.2018.08.043
[12]	周泩朴, 耿国华, 李康, 王飘. 一种基于AKAZE算法的多视图几何三维重建方法 Multi-view Geometric 3D Reconstruction Method Based on AKAZE Algorithm 计算机科学, 2018, 45(11A): 180-184.
[13]	刘金硕,江庄毅,徐亚渤,邓娟,章岚昕. PMVS算法的CPU多线程和GPU两级粒度并行策略 Multithread and GPU Parallel Schema on Patch-based Multi-view Stereo Algorithm 计算机科学, 2017, 44(2): 296-301. https://doi.org/10.11896/j.issn.1002-137X.2017.02.050
[14]	韩磊,徐波,黄向生,张彦峰. 基于GPU的散斑三维重建系统 Speckle Projection Systems Based on GPU 计算机科学, 2015, 42(8): 294-299.
[15]	张彦峰,黄向生,李杭,王梦伟. 基于渐进可靠点生长的散斑图快速立体匹配 Fast Stereo Matching Based on Progressive Reliable Point Growing Matching for Speckle Pattern Images 计算机科学, 2014, 41(Z6): 143-146.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

一种基于遮罩的稀疏点云滤波算法

Sparse Point Cloud Filtering Algorithm Based on Mask

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0