[robotics-worldwide] [software] Dataset released for air-ground matching of images

majdik majdik at ifi.uzh.ch
Mon Nov 4 17:27:19 PST 2013


Matching airborne images to ground level ones is a challenging problem 
since in this case extreme changes in viewpoint and scale can be found 
between the aerial Micro Aerial Vehicle (MAV) images and the 
ground-level images, aside the challenges present in ground visual 
search algorithms used in UGV applications, such as illumination, lens 
distortions, over season variation of the vegetation, and scene changes 
between the query and the database images.

Our dataset consists of image data captured with a small quadroctopter 
flying in the streets of Zurich (up to 15 meters from the ground), along 
a path of 2km, including: (1) aerial MAV Images, (2) ground-level Google 
Street View Images, (3) ground-truth confusion matrix, and (4) GPS data 
(geotags) for every database image.

The dataset is publicly available online at: 

The datasets is the one used in our IROS'13 paper:

A. Majdik, Y. Albers-Schoenberg, D. Scaramuzza MAV Urban Localization 
from Google Street View Data, IROS'13, IEEE/RSJ International Conference 
on Intelligent Robots and Systems, IROS'13, 2013 

The paper and dataset will be presented at IROS'13 on Tuesday, 
17:45-18:00, Paper TuDT9.4, Unmanned Aerial Vehicles IV (TuDT9 Regular 
Session), Room 608.

Dr. András Majdik
Postdoc at Robotics and Perception Group: http://rpg.ifi.uzh.ch, 
University of Zurich, Andreasstrasse 15, AND 2.20, Zurich, Switzerland
Email: majdik at ifi.uzh.ch; Office: +41 44 635 6823; Mobil: +41 78 956 

More information about the robotics-worldwide mailing list