1263 
ORFEO TOOLBOX: A COMPLETE SOLUTION FOR MAPPING FROM HIGH 
RESOLUTION SATELLITE IMAGES 
Emmanuel Christophe, Jordi Inglada and Alain Giros 
CNES DCT/SI/AP Bpi 1219 
18 av E. Belin, 31401 Toulouse Cedex 09 
{emmanuel.christophe, jordi.inglada, alain.giros}@cnes.fr 
http://otb.cnes.fr 
Commission IV/9 
KEY WORDS: OTB, image processing, image registration, change detection, image classification, image segmentation, open source 
software, Pleiades, Orfeo 
ABSTRACT: 
One of the main objectives of the Orfeo Toolbox (OTB) is the definition and the development of tools for the operational exploitation 
of the future sub-metric optic and radar images (rapid mapping, tridimensional aspects, change detection, texture analysis, pattern 
matching, optic and radar complementarities). The purpose of the OTB is to capitalize a methodological know-how in order to adopt 
an incremental development approach aiming to efficiently exploit the results obtained by research studies. OTB is interesting for all 
people working in the remote sensing imagery community. Releasing it under an open source licence, CNES hopes to benefit from 
contributions of many specialists to help grow the practical use of satellite imagery. 
1 INTRODUCTION 
Besides the Pleiades (PHR) and Cosmo-Skymed (CSK) systems 
developments forming ORFEO, a dual French-Italian system for 
Earth Observation, the ORFEO Accompaniment Program was set 
up, to prepare, accompany and promote the use and the exploita 
tion of the images derived from these sensors. 
The creation of a preparatory program is needed because of: 
• the new capabilities and performances of the ORFEO sys 
tems for mapping applications (high resolutions, access ca 
pability, data quality, possibility to acquire simultaneously 
in optic and radar); 
• the implied need of new methodological developments: new 
processing methods, or adaptation of existing ones. 
One of the main objectives of the program is the definition and the 
development of tools for the operational exploitation of the future 
sub-metric optic and radar images (rapid mapping, tridimensional 
aspects, change detection, texture analysis, pattern matching, op 
tic radar complementarities). 
On figure 1, a generic structure for generating maps from satel 
lite data is presented. Several steps are required before the map 
generation itself and several inputs are necessary to obtain valu 
able results. Hence, the pipeline structure is well adapted for this 
problem. 
Section 2 explains the raison d’etre of the ORFEO Toolbox li 
brary and its features are detailled in section 3. As some of the 
features are based on external libraries, we mention them in sec 
tion 4. These external libraries play a key role in the validation 
of the proposed features and the global validation step is illus 
trated in section 5. Finally, the computing aspect which cannot 
be neglected are detailled in section 6. 
2 ORFEO TOOLBOX 
In this context, CNES decided to develop the ORFEO ToolBox 
(OTB) (The ORFEO Toolbox Software Guide, 2008), a set of 
algorithms encapsulated in a software library. The purpose of 
the OTB is to capitalize a methodological know-how in order to 
adopt an incremental development approach aiming to efficiently 
exploit the results obtained in the frame of methodological R&D 
studies. 
Indeed, there is often a gap between published algorithms in con 
ferences or journals and algorithms which are used for real appli 
cations. Algorithms presented at conferences may work well on 
small data set or with some settings which need in-depth knowl 
edge of the theory. On the opposite, functional applications need 
to work on any data set (often huge) without the knowledge of an 
image processing expert. To be able to bridge this gap practical 
implementations of algorithms published in the literature need to 
be available. 
Free availability of such implementations play also an important 
part for the development of reproducible research. It is also very 
valuable for researchers and students to have access to a com 
plete implementation of previously published algorithms. For re 
searchers, this enables them to compare their results with these 
previous algorithms. For PhD students it is often a valuable strat- 
ing point to develop their new methods. 
All the developments are based on FLOSS (Free/Libre Open Source 
Software) or existing CNES developments. 
3 WHAT CAN WE DO WITH OTB? 
When the purpose is to use high resolution satellite images for 
fast mapping, several preprocessing steps are necessary before 
the mapping itself. The goal of OTB is to enable the user to 
process satellite images from different sources (satellite, image 
provider) with different levels of preprocessing (orthorectifica- 
toin, radiometric corrections). OTB proposes the basic function-