rgbd_scribble_benchmark

rgbd_scribble_benchmark copied to clipboard

• TUM RGB-D Scribble-based Segmentation Benchmark

• Description The RGB-D dataset contains the following

  • The number of RGB-D images is 154, each with a corresponding scribble and a ground truth image.
  • Every image has a resolution of 640 \times 480 pixels.
  • The measurement of the depth images is millimeter.
  • The categorization differentiates between 95 classes.
  • All scenes are indoor.

  | LabeledImages | This folder includes all images with the naming convention: [scene][number][image type].png, where scene is either bedroom, kitchen, livingroom or random and image type is either image, depth, scribbles or gt. | | RawData | In this folder the original data in .xcf format can be found. | | UnalignedDepth | One can find here all depth images before they were registered. | | rgbd_palette.gpl | The ground truth and scribble images are converted to indexed mode. The related color palette is saved in this file. | | LabelColorMapping.csv | This file describes which color belongs to which object class. | | displayLabeledImages.py | For visualization this script provides an overview of one image with the associated classes. | | Calibration | This folder contains the scripts, parameters and the images which were used for finding the parameters and for registering the depth images. |

• Example | [[./LabeledImages/kitchen_22_image.png]] | [[./LabeledImages/kitchen_22_gt.png]] | | [[./LabeledImages/kitchen_22_depth.png]] | [[./LabeledImages/kitchen_22_scribbles.png]] |

  For visualizing the point cloud, this matlab script can be used. #+BEGIN_SRC matlab :results file :file pointCloud.png :exports both figure( 1, "visible", "off" ); depth = imread('LabeledImages/kitchen_22_depth.png'); depth = double(depth); img = imread('LabeledImages/kitchen_22_image.png'); surf(depth, img, 'FaceColor', 'texturemap', 'EdgeColor', 'none' ) view(158, 38) print -dpng pointCloud.png; ans = "pointCloud.png"; #+END_SRC #+RESULTS: [[file:pointCloud.png]]

• Citation If you use the dataset, please cite as following

#+BEGIN_SRC @misc{tum-rgbd_scribble_dataset, author = {Caner Hazirbas and Andreas Wiedemann and Robert Maier and Laura Leal-Taixé and Daniel Cremers}, title = {TUM RGB-D Scribble-based Segmentation Benchmark}, howpublished = {\url{https://github.com/tum-vision/rgbd_scribble_benchmark}}, year = {2018} } #+END_SRC