SPARSE POINT CLOUD FILTERING BASED ON COVARIANCE FEATURES

Abstract. This work presents an extended photogrammetric pipeline aimed to improve 3D reconstruction results. Standard photogrammetric pipelines can produce noisy 3D data, especially when images are acquired with various sensors featuring different properties. In this paper, we propose an automatic filtering procedure based on some geometric features computed on the sparse point cloud created within the bundle adjustment phase. Bad 3D tie points and outliers are detected and removed, relying on micro and macro-clusters analyses. Clusters are built according to the prevalent dimensionality class (1D, 2D, 3D) assigned to low-entropy points, and corresponding to the main linear, planar o scatter local behaviour of the point cloud. While the macro-clusters analysis removes smallsized clusters and high-entropy points, in the micro-clusters investigation covariance features are used to verify the inner coherence of each point to the assigned class. Results on heritage scenarios are presented and discussed.

[1]  Markus H. Gross,et al.  Efficient simplification of point-sampled surfaces , 2002, IEEE Visualization, 2002. VIS 2002..

[2]  James R. Lersch,et al.  Context-driven automated target detection in 3D data , 2004, SPIE Defense + Commercial Sensing.

[3]  Qunsheng Peng,et al.  Mean shift denoising of point-sampled surfaces , 2006, The Visual Computer.

[4]  Hermann Gross,et al.  EXTRACTION OF LINES FROM LASER POINT CLOUDS , 2006 .

[5]  Chunxia Xiao,et al.  A dynamic balanced flow for filtering point-sampled geometry , 2006, The Visual Computer.

[6]  C. Mallet,et al.  AIRBORNE LIDAR FEATURE SELECTION FOR URBAN CLASSIFICATION USING RANDOM FORESTS , 2009 .

[7]  Daniel Cohen-Or,et al.  ℓ1-Sparse reconstruction of sharp point set surfaces , 2010, TOGS.

[8]  Uwe Soergel,et al.  Relevance assessment of full-waveform lidar data for urban area classification , 2011 .

[9]  J. Demantké,et al.  DIMENSIONALITY BASED SCALE SELECTION IN 3D LIDAR POINT CLOUDS , 2012 .

[10]  T. Soni Madhulatha,et al.  An Overview on Clustering Methods , 2012, ArXiv.

[11]  W. Zhu,et al.  Feature‐Preserving Surface Reconstruction From Unoriented, Noisy Point Data , 2013, Comput. Graph. Forum.

[12]  Boris Jutzi,et al.  Feature relevance assessment for the semantic interpretation of 3D point cloud data , 2013 .

[13]  Ron Kimmel,et al.  Patch‐Collaborative Spectral Point‐Cloud Denoising , 2013, Comput. Graph. Forum.

[14]  Nicolas David,et al.  Towards 3D lidar point cloud registration improvement using optimal neighborhood knowledge , 2013 .

[15]  Boris Jutzi,et al.  SHAPE DISTRIBUTION FEATURES FOR POINT CLOUD ANALYSIS - A GEOMETRIC HISTOGRAM APPROACH ON MULTIPLE SCALES , 2014 .

[16]  Antonia Teresa Spano,et al.  Fusion of 3D models derived from TLS and image-based techniques for CH enhanced documentation , 2014 .

[17]  Boris Jutzi,et al.  Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features , 2014 .

[18]  Stefan Hinz,et al.  CONTEXTUAL CLASSIFICATION OF POINT CLOUD DATA BY EXPLOITING INDIVIDUAL 3D NEIGBOURHOODS , 2015 .

[19]  Faisal Zaman,et al.  Density-based Denoising of Point Cloud , 2016, ArXiv.

[20]  Jan Dirk Wegner,et al.  Contour Detection in Unstructured 3D Point Clouds , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Boris Jutzi,et al.  GEOMETRIC FEATURES AND THEIR RELEVANCE FOR 3D POINT CLOUD CLASSIFICATION , 2017 .

[22]  Michael Weinmann,et al.  A Classification-Segmentation Framework for the Detection of Individual Trees in Dense MMS Point Cloud Data Acquired in Urban Areas , 2017, Remote. Sens..

[23]  Lei Gao,et al.  Signal Processing: Image Communication , 2022 .

[24]  Fabio Remondino,et al.  QUALITY FEATURES FOR THE INTEGRATION OF TERRESTRIAL AND UAV IMAGES , 2019, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.