[visionlist] RGB-D Person Re-identification Dataset

[Loris Bazzani]

Pattern Analysis and Vision dept. (PAVIS-IIT) is making available a new
dataset for person re-identification using depth information. Download at:
http://www.iit.it/en/datasets/rgbdid.html

The dataset contains four different groups of data (with depth and
RGBimages) collected using the
Kinect. The first group of data has been obtained by recording 79 people
with a frontal view, walking slowly, avoiding occlusions and with stretched
arms ("Collaborative"). This happened in an indoor scenario, where the
people were at least 2 meters away from the camera. The second ("Walking1")
and third ("Walking2") groups of data are composed by frontal recordings of
the same 79 people walking normally while entering the lab where they
normally work. The fourth group ("Backwards") is a back view recording of
the people walking away from the lab. Since all the acquisitions have been
performed in different days, there is no guarantee that visual aspects like
clothing or accessories will be kept constant. Moreover, we asked some
people to dress the same t-shirt in "Walking2". This is useful to highlight
the power of RGB-D re-identification compared with standard
appearance-based methods.

We provide 5 synchronized information for each person: 1) a set of up to 5
RGB images, 2) the foreground masks, 3) the skeletons, 4) the 3d mesh
(ply), 5) the estimated floor. We also provide a MATLAB script to read the
data. Since the data are in standard formats (images, text and ply files)
you can easily implement your own parser using your favourite programming
language.

The main motivation of using depth data is that the standard
appearance-based techniques (such as SDALF) fail when the individuals
change their clothing, therefore they cannot be used for long-term video
surveillance. Depth information is one solution to deal with this problem
because it is more invariant than appearance information over a longer
extent of time. While several datasets for appearance-based
re-identification exist, the current studies still misses a dataset that
provides also depth information. This dataset aims at promoting the RGB-D
re-identification research.

More details and sample images at: http://www.iit.it/en/datasets/rgbdid.html
Paper: B. I. Barbosa, M. Cristani, A. Del Bue, L. Bazzani, and V. Murino.
Re-identification with RGB-D sensors. In 1st International Workshop on
Re-Identification, 2012.

~LB~

-- 
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Loris Bazzani, Ph.D.
IIT - Istituto Italiano di Tecnologia
PAVIS - Pattern Analysis &  Computer Vision dept.
Via Morego, 30, 16163 Genova, Italy.
Website:  www.lorisbazzani.info
Lab page:   www.iit.it/pavis.html
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist/attachments/20121129/f2d7f083/attachment.htm>