monteverdi - remote sensing software from educational to operational context

Post on 11-Jun-2015

2.423 Views

Category:

Technology

1 Downloads

Preview:

Click to see full reader

DESCRIPTION

Presentation of the application Monteverdi at the 30th EARSeL Symposium 2010 - Paris, France

TRANSCRIPT

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox

Monteverdi - Remote sensing software fromeducational to operational context

M.Grizonnet1,J.Inglada2

1CENTRE NATIONAL D’ÉTUDES SPATIALES, TOULOUSE, FRANCE

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Outline

IntroductionEfficiencyReal worldIntegrated process

MonteverdiComponentsGeometric processFiltering process

Orfeo ToolboxA bit of historyWhy doing that?How?

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Everybody with the same problem

Building Remote sensing process

GoalExtract value added and comprehensive informations fromremote sensing imageries

I Large amount of dataI Extraction of informationsI Tools: efficient software, well-design process,experience...

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Real applications on real images

Building real remote sensing process

GoalOperationnal extraction of value added and comprehensiveinformations from remote sensing imageries

InputsI Operational situationsI Complex softwaresI But often incomplete

Multiple tools in the pipeline

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Real processAdvanced and complex process

I complex softwares a - complex interactions I/O difficulties - Proprietary format

Proprietary process

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Real processAdvanced and complex process

I complex softwares a - complex interactions I/O difficulties - Proprietary format

Proprietary process

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Dream processAdvanced and simple process

I One sofware - Lots of process behind a common interface - Open standard

Open Source process

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Hopeness Deception Solution

Dream processAdvanced and simple process

I One sofware - Lots of process behind a common interface - Open standard

Open Source process

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Outline

IntroductionEfficiencyReal worldIntegrated process

MonteverdiComponentsGeometric processFiltering process

Orfeo ToolboxA bit of historyWhy doing that?How?

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Describe your process

PrinciplesI Describe interactively your processI Dynamically define inputs and outputsI Request from CNES’s Strategy and Programs OfficeI Capacity building activities (teaching, simple image manipulation...)

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

GUIAdvanced and simple process

Data and process tree

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

GUIAdvanced and simple process

Data and process tree

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Components available

CurrentlyI Most satellite image formats I/O magic image formatI Geometric corrections: orthorectification, re-projectionI Calibration: Radiometric corrections (Optical, SAR)I Filtering: Feature extraction, Mean-shift segmentation, change detectionI Classification: supervised and unsupervised classification

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Visualization

Advanced and simple process

Visualization

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Visualization

Advanced and simple process

Visualization

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Geometry sectionAdvanced and simple process

Orthorectification

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Geometry sectionAdvanced and simple process

Orthorectification

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Filtering

Mean-shift Segmentation

Interactive segmentation

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Filtering

Mean-shift Segmentation

Interactive segmentation

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Filtering

Feature extraction

Interactive feature extraction

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox Components Geometric process Filtering process

Filtering

Feature extraction

Interactive feature extraction

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

Outline

IntroductionEfficiencyReal worldIntegrated process

MonteverdiComponentsGeometric processFiltering process

Orfeo ToolboxA bit of historyWhy doing that?How?

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

A bit of History

Everything begins (2006)I Started in 2006 by CNES (French Space Agency), funding several full-time

developersI Targeted at high resolution images (Pleiades to be launched in 2010) but with

application to other sensorsI 4 year budget, over 1,000,000ewith extensions in the next years

Moving to user friendly application (2009)I Strong interactions with the user community highlighted that applications for

non-programmers are importantI Application Monteverdi with several applications for non programmers (with GUI)I Several courses (3/5-day courses) given in several French and Belgian

institutions (Cesbio, RMA, ENST,...), in Madagascar...

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

Why doing that?

Is it successful so far?I OTB user community growing steadily (programmers and application users)I Presented at IGARSS in 2009, tutorial in IGARSS in 2010 on Pragmatic Remote

SensingI CNES is planning to extend the budget for several more yearsI Value analysis is very positive (cf. Ohloh): re-using is powerful

Why make a multi-million dollar software and give it forfree?

I CNES is not a software companyI One goal is to encourage research: it is critical for researchers to know what is in

the boxI CNES makes satellites and wants to make sure the images are usedI if more people have the tools to use satellite images, it is good for CNES

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

Why doing that?

Is it successful so far?I OTB user community growing steadily (programmers and application users)I Presented at IGARSS in 2009, tutorial in IGARSS in 2010 on Pragmatic Remote

SensingI CNES is planning to extend the budget for several more yearsI Value analysis is very positive (cf. Ohloh): re-using is powerful

Why make a multi-million dollar software and give it forfree?

I CNES is not a software companyI One goal is to encourage research: it is critical for researchers to know what is in

the boxI CNES makes satellites and wants to make sure the images are usedI if more people have the tools to use satellite images, it is good for CNES

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

How?

How to reach this goal?Using the best work of others: do not reinvent the wheel

Many open-source libraries of good qualityI ITK: software architecture (streaming, multithreading), many image processing

algorithmsI Gdal/Ogr: reading data format (geotiff, raw, png, jpeg, shapefile, . . . )I Ossim: sensor models (Spot, RPC, SAR, . . . ) and map projectionsI 6S: radiometric corrections, TerraSAR X calibration...I and many other: libLAS (lidar data), Edison (Mean Shift clustering), libSiftFast

(SIFT), Boost (graph), libSVM (Support Vector Machines)

⇒ all behind a common interface

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

How?

How to reach this goal?Using the best work of others: do not reinvent the wheel

Many open-source libraries of good qualityI ITK: software architecture (streaming, multithreading), many image processing

algorithmsI Gdal/Ogr: reading data format (geotiff, raw, png, jpeg, shapefile, . . . )I Ossim: sensor models (Spot, RPC, SAR, . . . ) and map projectionsI 6S: radiometric corrections, TerraSAR X calibration...I and many other: libLAS (lidar data), Edison (Mean Shift clustering), libSiftFast

(SIFT), Boost (graph), libSVM (Support Vector Machines)

⇒ all behind a common interface

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

Useful links

I OTB main page:

http://www.orfeo-toolbox.org

I Beta version download:

http://hg.orfeo-toolbox.org

I Wiki (contributors doc.):

http://wiki.orfeo-toolbox.org

I Bugs reporting:

http://bugs.orfeo-toolbox.org

I Blog:

http://blog.orfeo-toolbox.org

EARSeL 2010, Paris

Introduction Monteverdi Orfeo Toolbox When Why How

Thank you for your attention

http://www.orfeo-toolbox.org

top related