Difference between revisions of "GRASS SoC Ideas 2013"

From GRASS-Wiki
Jump to: navigation, search
(Imagery)
m (Imagery)
Line 22: Line 22:
 
* 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
** classifying segments based on the caracteristics and (possibly) training areas
+
** classifying segments based on the characteristics and (possibly) training areas
  
 
* 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)

Revision as of 13:29, 11 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
    • classifying segments based on the characteristics and (possibly) training areas
  • Implement hierarchical classification tools (e.g. being able to create a large class "forest", with subclasses of different types of forests)