------Innsbruck Pointing Dataset------

Each participant performed two types of pointing: (1) Natural pointing with index finger, and (2) Tool (board marker) pointing.

10 objects were placed on a table and participants were asked to point at each of them.

The test images for natural pointing and tool pointing can be found in odd and even numbered folders, respectively.

Each folder consists of the following:

	(1) 00001.png (RGB) and 00001d.png (Depth) in are initial images witout any of pointing gesture.

	(2) objLocGroundTruth.mat - Ground truth location of the object. It consists of:
		- objList 	: Names of object
		- obj2DLoc	: Location of the center of the object in image (2D).
		- obj3DLoc	: Location of the center of the object in world (3D)

	(3) Images from 00002,...,00011 are pointing test images for objects in the sequence mentioned in  objLocGroundTruth.at 'objList'.

	(4) xxhandGt.mat (xx - 00002,00003,...) consists of:
		- hand2DLoc	: Location of the center of the hand in image (2D)
		- hand3DLoc	: Location of the center of the hand in world (3D)

	(5) scene_list.txt: List of test scenes in the folder


Ground truth locations of hand and objects in 2D is illustrated in natural_pointing.png and tool_pointing.png

--Reference paper:

Dadhichi Shukla, Özgür Erkent, Justus Piater, Probabilistic detection of pointing directions for human robot interaction. International Conference on Digital Image Computing: Techniques and Applications, 2015.

--BiBTex:

@InProceedings{Shukla-2015-DICTA,
  title = {{Probabilistic detection of pointing directions for human
      robot interaction}},
  author = {Shukla, Dadhichi and Erkent, Ozgur and Piater, Justus},
  booktitle = {{International Conference on Digital Image
      Computing: Techniques and Applications}},
  year = 2015,
  month = 11,
  url = {https://iis.uibk.ac.at/public/papers/Shukla-2015-DICTA.pdf}
}

--Contact:
dadhichi.shukla@uibk.ac.at

		



