Gerbil is a generic framework for visualization and analysis of multispectral and hyperspectral data that strives to both bring new innovations in analysis capabilities and be of use in a wide range of hyperspectral data applications. In a nutshell, Gerbil lets you…
- explore a multispectral or hyperspectral image before processing it,
- apply common computer vision algorithms adapted to hyperspectral data,
- cluster and label image pixels for your application scenario,
- assess your own algorithms via high-dimensional data visualization,
- use an intuitive interface for teaching multispectral imaging and reflectance analysis,
and most probably a huge amount of other things that we did not think of yet!
Gerbil is free software, which means that you have a lot of freedoms in using the software in your research and beyond. See the Documentation for details on how to install and use the software.
Please see the Comprehensive Feature List.
The following publications describe parts of the Gerbil framework:
- J. Jordan, E. Angelopoulou. “Gerbil - A Novel Software Framework for Visualization and Analysis in the Multispectral Domain”, VMV 2010: Vision, Modeling and Visualization, November 2010, pp. 259-266.
- J. Jordan, E. Angelopoulou. “Edge Detection in Multispectral Images Using the n-dimensional Self-Organizing Map”, IEEE International Conference on Image Processing, September 2011, pp. 3181-3184.
- J. Jordan, E. Angelopoulou. “Supervised Multispectral Image Segmentation with Power Watersheds”, IEEE International Conference on Image Processing, September 2012, pp. 1585-1588.
- J. Jordan, E. Angelopoulou. “Hyperspectral Image Visualization With a 3-D Self-organizing Map”, IEEE 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, June 2013
- J. Jordan, E. Angelopoulou. “Mean-shift Clustering for Interactive Multispectral Image Analysis”, IEEE International Conference on Image Processing, September 2013, pp. 3790-3794