Difference between revisions of "GRASS SoC Ideas 2013"

From GRASS-Wiki
Jump to: navigation, search
m (Symbology / Cartography)
(Added "interface to OTB" as a suggestion)
Line 21: Line 21:
  
 
* Based on the work on [[GRASS_GSoC_2012_Image_Segmentation|segmentation]] in GSoC 2012 develop routines for object-based (ore region-based) image classification. This probably entails:
 
* Based on the work on [[GRASS_GSoC_2012_Image_Segmentation|segmentation]] in GSoC 2012 develop routines for object-based (ore region-based) image classification. This probably entails:
** characterizing segments
+
** Characterizing segments. Thsi includes producing statistics such as mean, median, variance of the segmented data within each delineated segment.
** classifying segments based on the characteristics and (possibly) training areas
+
** Classifying segments based on the characteristics and (possibly) training areas
 +
** Interface with other modules in a consistent workflow (i.cluster, r.fuzzy, etc)
  
 
* Implement hierarchical classification tools (e.g. being able to create a large class "forest", with subclasses of different types of forests)
 
* Implement hierarchical classification tools (e.g. being able to create a large class "forest", with subclasses of different types of forests)
 +
 +
* Interface with the [http://www.orfeo-toolbox.org/otb/ Orfeo toolbox (OTB)], which is an open source, [http://www.itk.org ITK]-based, C++ library of (spatial) image processing library. OTB implements a very wide set of interesting features for anybody working with raster data - in particular satellite imagery: radiometric corrections, orthorectification, filtering, feature extraction, image segmentation , classification, change detection, etc.
  
 
{{GSoC}}
 
{{GSoC}}

Revision as of 17:51, 14 February 2013

About

This is the GRASS page for Google Summer of Code 2013. Here we will list project ideas and and other information related to the GRASS GSoC projects.

Ideas

  • Project ideas of your own are also most welcome and often the best.

Symbology / Cartography

  • Allow display of a vector legend in the map display (equivalent to current d.legend implementation for rasters)
HB: note that SoC only accepts coding projects, not graphics design or documentation projects. Adding svg/eps support to a d.* module and ps.map would be quite helpful. See the d.graph help page and ps.map's "eps" and "vpoints" instructions.

Imagery

  • Based on the work on segmentation in GSoC 2012 develop routines for object-based (ore region-based) image classification. This probably entails:
    • Characterizing segments. Thsi includes producing statistics such as mean, median, variance of the segmented data within each delineated segment.
    • Classifying segments based on the characteristics and (possibly) training areas
    • Interface with other modules in a consistent workflow (i.cluster, r.fuzzy, etc)
  • Implement hierarchical classification tools (e.g. being able to create a large class "forest", with subclasses of different types of forests)
  • Interface with the Orfeo toolbox (OTB), which is an open source, ITK-based, C++ library of (spatial) image processing library. OTB implements a very wide set of interesting features for anybody working with raster data - in particular satellite imagery: radiometric corrections, orthorectification, filtering, feature extraction, image segmentation , classification, change detection, etc.