2009

PlanetSasha
Student : ​Massimo Di Stefano
Mentor : Mark Lucas

Aim of the project :

Development of a plug-in for the OssimPlanet application for interface with other Open Source G.I.S software such as GRASS GIS and QGIS, This allows to export the elevation and texture data from GRASS/QGIS to OssimPlanet. The results is to synchronize the GRASS/QGIS maps canvas extent with the OssimPlanet scene.

2011

PyOSSIM - Python bindings for OSSIM
Student : Vipul Raheja
Mentor : ​Massimo Di Stefano

The aim is to expose the OSSIM and OSSIMPlanet API to Python in order to extend their functionalities to other essential GIS and remote sensing analysis tools like GRASS, QuantumGIS and libraries like GDAL etc.

The software package consists of:

• Software libraries,
• Command line tools, and
• GUI applications

OSSIM already has some API exposed using the SWIG interface as wrapper. Hence, The Python bindings for the core library will be used to write a toolbox based on the OSSIM function as an extension to GRASS and QGIS for image analysis while the python bindings for the OSSIMPlanet API will be used to extend the PlanetSasha functionalities inside the respective GRASS and QGIS plug-in.

2012

Complex Image Processing Chain and Under Water Image Processing using PyOSSIM
Student : Mohammed Rashad K.M
Mentor : ​Massimo Di Stefano

The idea is to create complex image processing chain using the OSSIM python bindings PyOSSIM. This includes adding python interface for all the ossim-executables (ossim-igen, ossim-orthoigen, ossim-mosaic, ...). The work will add 'numpy-array' capabilities into pyossim as exchanging formast to include python-gdal and pyOpenCV to solve image processing problems for under water images processing (develop methods for : Bayer Demosaicing, Light detrend, color correction on raw tiff CCD images).

For testing purpose, raw CCD images and relative camera metadata (focal length, distance from the ground, roll, pitch, gain etc..) from the ​Habcam project will be used.

2013

Oceanography Circulatory model for OSSIM using PyOSSIM and PlanetSasha
Student : Mohammed Rashad K.M
Mentor : ​Massimo Di Stefano

The main idea is to develop an intuitive tool to read-process-display online data sources, available in netcdf format. The tool will be able to decode the “get capabilities” of dataservices like Thredds, allow variables selection and execute spatio temporal queries on netcdf resources. All processing will be done in python using pyossim (GSoC-2011/2012) and Necdf4, while PlanetSasha (GSoC 2009) and ​PyGRASS (GSoC-2012) will be used to develop the user interface and imporove the OSSIMPlanet-GRASS comunication. The output generated is sent to OSSIMPlanet for visualization. The GUI will consist of a tool for spatio/temporal query and data selection and a set of controllers to add/remove data from the ossimplanet canvas including the ability to start/stop animation of time series of raster data. As test-bed, the spatio-temporal data from the ocean circulatory model “FVCOM” can be used (data publicy available at : ​USGS Thredds sevice )

willing to mentor : ​Massimo Di Stefano, ​Norman Vine

2014

Photogrammetric image processing: DSM generation tool for OSSIM
Student : Martina Di Rita
Mentors : David Burken; David Hicks

The aim of the project is the development of an OSSIM App for Digital Surface Models (DSMs) generation using high resolution satellite imagery. Such a task is not a trivial one and several complex processing steps are required; the core of this work will be to mix the OSSIM functionalities with the algorithms implemented in the OpenCV library in order to exploit the combined capabilities in a synergistic way.
The idea is to create a complete OSSIM extension for stereo DSM generation able to perform both image orientation and image matching, by integrating OpenCV algorithms that would be used to epipolar images generation and to perform a semi global matching.

2015

OSSIM tool for DSM generation from tri-stereo and SAR imagery
Student : Martina Di Rita
Mentors : David Burken; Oscar Kramer

The aim of the project is the development of an OSSIM App for Digital Surface Models (DSMs) generation using high resolution satellite imagery. Such a task is not a trivial one and several complex processing steps are required; the core of this work will be to mix the OSSIM functionalities with the algorithms implemented in the OpenCV library in order to exploit the combined capabilities in a synergistic way.
The idea is to create a complete OSSIM extension for stereo DSM generation able to perform both image orientation and image matching, by integrating OpenCV algorithms that would be used to epipolar images generation and to perform a semi global matching.