By the end of this lab, students should be able to:
- Perform an unsupervised classification in both ArcMap and ERDAS
- Accurately classify images of different spatial and spectral resolutions
- Manually reclassify and recode images to simplify the data
In this lab, I performed unsupervised classification, as well as reclassify and recode these classes. First, using ArcMap, I created a classified image by using the Iso Cluster tool and Maximum Likelihood Classification tool on a raster image. I then examined the new image and properly reclassified the classes and used an appropriate color to represent each class.
In ERDAS Imagine, I used the ISODATA (Iterative Self-Organizing Data Analysis Technique) algorithm to perform an unsupervised classification on a raster image of UWF campus. Once the output image was created and added to ERDAS, I reclassified all 50 classes to proper classes, such as grass, trees, shadows, and buildings and roads. To refine the reclassification step, I used methods such as swipe, flicker, blend, and highlight. I then merged these classes by recoding them into five distinct classes. Using these five classes, I calculated the percentage area of permeable and impermeable surfaces.
The map above represents the land classification of UWF campus.
