Open Call for Benchmark/Test Datasets 
                IEEE OTCBVS Workshop Series 

This is an open call for additional submissions of benchmark datasets for 
testing and evaluating novel and state-of-the-art computer vision algorithms 
beyond the visible spectrum. The current benchmark 
<http://www.cse.ohio-state.edu/otcbvs-bench/> was initially created in 
response to the IEEE Int'l Workshop on "Object Tracking and Classification 
in and Beyond the Visible Spectrum" (launched in 2004, with follow-up meetings
in 2005, 2006, and 2007 in conjunction with the IEEE Conference on Computer 
Vision and Pattern Recognition). The benchmark is used for educational and 
research purposes only, and is available for all researchers in the 
international computer vision communities. Currently the datasets include:

     Dataset 01: OSU Thermal Pedestrian Database
     Dataset 02: IRIS Thermal/Visible Face Database    
     Dataset 03: OSU Color-Thermal Database    
     Dataset 04: Terravic Facial IR Database  
     Dataset 05: Terravic Motion IR Database    
     Dataset 06: Terravic Weapon IR Database

This call solicits your participation to contribute to the benchmark data. All
academic institutions, research laboratories, and companies in the field of 
computer vision, pattern recognition, and robotics are encouraged to respond 
to this call.  The benchmark contain videos and images recorded in and beyond 
the visible spectrum, and fills out the lack of experimental non-visible data 
in the vision community. It also allows a large spectrum of IEEE and SPIE 
vision conference and workshop participants to explore the benefits of the 
non-visible spectrum in real-world applications, contribute to the OTCBVS 
workshop series, and boost this research field significantly. 

This call for benchmark data solicits the submission of quality, original 
non-visible/visible videos and images that deal with object tracking and 
classification within the scope of the OTCBVS workshop series. In addition to 
the submission of imagery, ground truth labeling of the existing datasets 
(without current ground truth) will also be accepted. All submitted materials 
will be reviewed by the OTCBVS steering committee. The evaluation criteria 
will be: (1) Relevance to OTCBVC scope and goals, (2) Comprehensiveness of 
data for topic, and (3) Quality of ground truth (if available). When 
applicable, Institutional Review Board (IRB) procedures must be engaged and 
approved prior to submission of the dataset. Accepted datasets will be made 
available at the OTCBVS benchmark web site:

           <http://www.cse.ohio-state.edu/otcbvs-bench/> 

All contributors to this benchmark will be acknowledged by the users, in the 
OTCBVS workshop series and other associated conferences, and have their 
logo/icon image appear on the OTCBVS website and workshop proceedings. 


GUIDELINES FOR DATASET SUBMISSION:
(1) VIDEO/IMAGE DATA must be in generic format (e.g., pgm, bmp, jpeg, avi, 
mpeg, raw, etc.); No "in-house" data formats will be accepted. Please place 
each sequence in its own subdirectory. 
(2) GROUND TRUTH DATA (if available). 
(3) LOGO/ICON (approx. 100x100 pixels) for dataset. 
(4) TEXT DESCRIPTION FILE including: dataset title (e.g., "XYZ thermal face 
database"), topic-of-interest (e.g., object detection, motion detection, 
etc.), point-of-contact (e.g., name and email), sensor details (e.g., sensor 
core, lens, etc.), data details (e.g., scene/object description, number of 
frames, image size, frames per second, compression, etc.), and requested 
citation acknowledgement (e.g., paper reference, research laboratory). 


To submit your video/image dataset or for comments/questions, please email: 

          otcbvs-bench@cse.ohio-state.edu

Thank you for your participation.