トップページ人工知能,実世界DB(目次ページ)
3次元再構成,3次元セグメンテーション(書きかけ)

3次元再構成,3次元セグメンテーション(書きかけ)

Open3D は,3次元データを扱う機能を持った,オープンソースのソフトウエア. Open3D の URL: http://www.open3d.org/ @article{Zhou2018, author = {Qian-Yi Zhou and Jaesik Park and Vladlen Koltun}, title = {{Open3D}: {A} Modern Library for {3D} Data Processing}, journal = {arXiv:1801.09847}, year = {2018}, }

前準備

Open 3D のページにより,Python のバージョンを確認.

Python 3.8 のインストール

Git, cmake Build Tools が必要

Open 3D のインストール

  1. Open 3D のソースコードのダウンロード
    cd c:\pytools
    git clone --recursive https://github.com/intel-isl/Open3D
    cd Open3D
    git submodule update --init --recursive
    

    [image]
  2. ビルド
    cd c:\pytools
    cd Open3D
    rmdir /s /q build
    mkdir build
    cd build
    cmake -G "Visual Studio 16 2019" -A x64 -T host=x64 -DPYTHON_EXECUTABLE="C:\Program Files\Python38\python.exe" ..
    cmake --build . --config RELEASE
    
  3. Python バインディングのインストール,確認
    cmake --build . --config Release 
    cmake --build . --config Release --target pip-package
    py -3.8 -c "import open3d; print(open3d)"
    
    cd c:\pytools
    git clone --recursive https://github.com/intel-isl/Open3D-ML
    cd Open3D-ML
    py -3.8 -m pip install -r requirements.txt
    py -3.8 -m pip install -r requirements-tensorflow.txt
    

    [image]

    https://github.com/intel-isl/Open3D-ML に記載の次のプログラムを実行

    import open3d.ml.tf as ml3d
    
    # construct a dataset by specifying dataset_path
    dataset = ml3d.datasets.SemanticKITTI(dataset_path='/path/to/SemanticKITTI/')
    
    # get the 'all' split that combines training, validation and test set
    all_split = dataset.get_split('all')
    
    # print the attributes of the first datum
    print(all_split.get_attr(0))
    
    # print the shape of the first point cloud
    print(all_split.get_data(0)['point'].shape)
    
    # show the first 100 frames using the visualizer
    vis = ml3d.vis.Visualizer()
    vis.visualize_dataset(dataset, 'all', indices=range(100))
    
    ---------- 以下,メモ
    py -3.8 -m pip install open3
    ScanNet
    
    ScanNet is an RGB-D video dataset containing 2.5 million views in more than 1500 scans, annotated with 3D camera poses, surface reconstructions, and instance-level semantic segmentations.
    
    https://github.com/ScanNet/ScanNet
    
    http://www.scan-net.org
    
    ---
    
    SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite
    
    https://rgbd.cs.princeton.edu/
    
    https://rgbd.cs.princeton.edu/data/SUNRGBD.zip
    
    The dataset contains RGB-D images from NYU depth v2 [1], Berkeley B3DO [2], and SUN3D [3]. Besides this paper, you are required to also cite the following papers if you use this dataset. 
     [1] N. Silberman, D. Hoiem, P. Kohli, R. Fergus. Indoor segmentation and support inference from rgbd images. In ECCV, 2012.
    
    [2] A. Janoch, S. Karayev, Y. Jia, J. T. Barron, M. Fritz, K. Saenko, and T. Darrell. A category-level 3-d object dataset: Putting the kinect to work. In ICCV Workshop on Consumer Depth Cameras for Computer Vision, 2011.
    
    [3] J. Xiao, A. Owens, and A. Torralba. SUN3D: A database of big spaces reconstructed using SfM and object labels. In ICCV, 2013 
    
    S. Song, S. Lichtenberg, and J. Xiao.
    SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite
    Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2015)