Dexter+Object: A Dataset for Evaluation of Joint Hand+Object Tracking
================================================================================

Dexter+Object is a dataset for evaluating algorithms for joint hand and object tracking.
It consists of 6 sequences with 2 actors, and varying interactions with a simple object.
Fingertip positions and cuboid corners were manually annotated for all sequences.
This dataset accompanies the ECCV 2016 paper, Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input.

--------------------
License
--------------------
If you use this dataset, you are required to cite the following paper.

[1] S. Sridhar, F. Mueller, M. Zollhöfer, D. Casas, A. Oulasvirta, C. Theobalt
Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
European Conference on Computer Vision (ECCV) 2016, Amsterdam, The Netherlands.

--------------------
Downloads
--------------------
Compressed Zip:
http://resources.mpi-inf.mpg.de/handtracker/data/dexter+object.zip

Browse:
http://resources.mpi-inf.mpg.de/handtracker/data/dexter+object

--------------------
Data
--------------------
- RGB: Creative Senz3D color camera
- Depth: Creative Senz3D close range TOF depth camera co-located with the color camera
- Ground Truth: Manually annotated on depth data for 3D fingertip positions, and 3 object (cuboid) corners
- Depth Camera Intrinsics: Can be used to backproject depth image to create a 3D point cloud

--------------------
Evaluation Metric
--------------------
Please see the supplementary document for the definition of the error measure.
We recommend using the same measure to facilitate direct comparison with other methods.

http://handtracker.mpi-inf.mpg.de/projects/RealtimeHO/content/RealtimeHO_ECCV2016_SM.pdf

--------------------
Sequence Details
--------------------
- Grasp1: User grasping a small cuboid.
- Grasp2: User grasping a big cuboid.
- Pinch: User pinching a small cuboid.
- Rigid: User moving rigidly while holding a small cuboid.
- Rotate: User holding and rotating a small cuboid.
- Occlusion: A small cuboid occluding the user's hand.

--------------------
Dataset Structure
--------------------
The root directory (containing this file) consists of 4 sub-directories.
- data: All the data resides here.
  - SEQUENCE_NAME
    - color: Color images in BMP format.
	- depth: Depth map as 16-bit PNG. Background/invalid pixels have a value of 32001.
	- annotations: Contains manually annotated data for fingertip positions and 3 cuboid corners. See README.txt inside the directory for more details.
- preview: Preview videos of all the sequences in the dataset and a montage of results from our tracker.
- scripts: Bash scripts used to make previews and to compute all 8 cuboid corners from the annotated 3 corners.
- calibration: Intrinsic calibration matrix for depth map backprojection.
- hand_dimensions.pdf: Sketches of the hands of both users specifying dimensions in centimeters.

--------------------
Contact
--------------------
For questions about the dataset please contact Srinath Sridhar or Franziska Mueller
{ssridhar, frmueller}@mpi-inf.mpg.de