GIS 4035 Module 10: Supervised Classification

Supervised classification and spectral distance file of Germantown, Maryland.

The task for module 10 was to utilize ERDAS Imagine to create, analyze, and edit supervised classifications of multispectral images. We began by reviewing the fundamentals of the Signature Editor tool (to create and edit the training samples used for a supervised classification) and creating an AOI (area of interest) layer. We then used the Inquire tool to locate specific points on the image on which we created polygons to capture to areas to be used as the spectral signature of a class. We also reviewed the use of the Seed tool; this tool automatically creates a polygon capturing pixels of a set spectral distance from the initial point based on input parameters. I preferred using the Seed tool to manually inserting polygons as it gives more control over keeping each class distinct. We also spent some time analyzing the histograms and mean plots of spectral signatures. These tools give use a more precise way to ensure our classifications capture unique features and are not spectrally confused.

The assignment required us to use all the tools reviewed in the module to create our own supervised classification of an image of Germantown, Maryland. We were given coordinates of three urban features, two fallow field features, four agriculture features, and one each for grasses, deciduous forests, and mixed forests. We also were to create signatures for water and roads. With this completed, we then needed to recode the number of classes down to eight, consolidating the categories with multiple classes into one each. We also needed to include the spectral distance file in our final map; this image shows us at a glance the pixels in the image that are furthest away from any of our classes. The final layout was completed in ArcMap.

GIS 5990 Module 9: Biscayne Shipwrecks, Analyze Week

Five shipwrecks in Biscayne NP with 300 meter buffers showing benthic zones.

Reclassified layers showing benthic zone and bathymetric data; these layers were used in the weighted overly below.

The output of the Weighted Overlay tool using the reclassified benthic zone and bathymetry layers.

This was the second week of our three-week project focusing on GIS use in analyzing shipwrecks in Biscayne National Park. This module was similar to our previous work in creating predictive models, only this time we processed data relating to the sea floor. As seen above, the variables included in our weighted overlay were benthic zones and bathymetry. Interestingly, the bathymetric data seemed to contradict the actual locations of known shipwrecks; most shipwrecks were not located in the shallowest waters. To account for this, the weighting of the bathymetric data was lowered to 30%; the benthic zone data comprised the majority 70% weighting.

For the most part, this was an enjoyable assignment to complete. I did run into a frustrating difficulty at the end as I attempted to run the Weighted Overlay tool. Many, many attempts either ran into errors or resulted in a raster output that was not classified correctly. Eventually, I checked the properties of my input data, the reclassified benthic zone and bathymetry rasters. I discovered the latter raster was lacking a defined coordinate system; fixing this allowed the tool to run quickly and correctly. The experience reinforced the lesson that I must always check my data to ensure everything is in order.

GIS 4035 Module 9: Unsupervised Classification

Five category unsupervised classification of the UWF campus based on true color imagery.

The ninth module of the course guided us through performing unsupervised classifications of imagery in ArcMap and ERDAS Imagine. An unsupervised classification takes basic guidelines from the user (such as the number of desired categories) and creates categories based on the appearance of each pixel. A perfect classification would, for example, classify all water in a category, all trees in another category, and so on. There has likely never been a perfect classification, however, so the resulting classified image must be edited to better capture the desired categories.

In order to create the above classified image of the UWF campus, the original true color image was run through Imagine's Unsupervised Classification tool to create fifty categories. The resulting image (not shown) looked very similar to the original image. We then reclassified each of the fifty categories into the five classes of trees, grass, buildings/roads, shadows, and mixed (grass/urban). The main source of error was the overlap of bright grass and ground areas to some urban areas; this created the need for the "mixed" class.