Land Cover Mapping

Land Cover Mapping

The IDRISI software includes a comprehensive suite of image processing tools, making it an excellent choice for land cover mapping applications with remotely-sensed data.

Image processing tools provide for image restoration, enhancement, classification and transformation. IDRISI has the most extensive set of classification tools on the market, including both supervised and unsupervised multi-spectral and hyperspectral classifiers, with special techniques for soft classification analysis. A host of machine learning tools are also provided, including artificial neural network classifiers and classification tree analysis.

A special routine for segmentation classification, which uses segments as landscape objects instead of pixels, provides an alternative to pixel-based classification approaches.

Application areas include:

* Remotely-sensed image analysis
* Inventory and baseline land resource mapping
* Landuse and land change analysis
* Agricultural monitoring
* Natural resource monitoring

Analytical Examples: [click images to enlarge]

Segmentation Analysis with IDRISI Taiga

The SEGMENTATION module creates an image of segments that have spectral similarity across many input bands. The image on the left uses a larger similarity threshold than the one on the right, resulting in more generalized, less homogeneous segments. Using this threshold, the image allows for segments that wholly contain building objects.


Back to Top

Segmentation and Classification Analysis with IDRISI Taiga

The module SEGCLASS classifies the imagery using a majority rule algorithm to assign each segment to the majority class from the reference image. SEGCLASS can improve the accuracy of a pixel-based classification and produce a smoother map-like classification result while preserving the boundaries between the segments.


Back to Top

Neural Network Classification Analysis with IDRISI Taiga

A variety of machine learning classifiers are available within IDRISI. Neural network classifiers include a multi-layer perceptron, self-organizing map, and fuzzy ARTMAP. Each allows complete control over all parameters.


Back to Top

Classification Tree Analysis with IDRISI Taiga

Classification Tree Analysis is a type of machine learning classifier. Procedures are included for training and pruning a classification tree. This module produces both hard and soft classified maps. There is one soft map for each class associated with the degree of membership for that class at a particular leaf in the tree structure.


Back to Top

Linear Spectral Unmixing with IDRISI Taiga

Linear spectral unmixing, or linear mixture modeling, is available in IDRISI and provides a means for sub-pixel evaluation. Three options are provided: the standard unmixing method, a probability guided method, and an exhaustive search method.