Lab 1: M1.1 Fundamentals

The above layout shows the precision of the data collected by comparing the data to the average point (the star) It was found that the data was precise within 4.5 meters of this location (the yellow area). The data was also found to be accurate within 9.3 meters. Precision was determined by comparing the test waypoints to the average location and determining the distance where 68% of the points fell were within the distance. Accuracy was determined using the same method but rather than using an average location it was determined where 68% of the data was within range of a benchmark location known to be the 'correct' location. With this it was determined that the data is more precise than accurate since the data is clustered more around the average than the reference point.

Comments

Module 5 - Unsupervised and Supervised Image Classification

This weeks module focused on classifying images using multispectral signatures. Above you can see the completed classified land cover of Germantown, Maryland. To create this image above signatures were collected that correlated to each required feature. Then bands were chosen (R:4 G:6 B:5) that contained the largest separation amongst features to minimize spectral confusion. In the above image roads and urban areas were often confused leading to a much larger area of roads than actually exist. The inset map contains a classification distance map which displays the distance each cell is (spectrally) from the sample points with brighter pixels being further than darker pixels. This indicates that brighter areas have a higher chance of error.

Lab 3: M 1.3 Assessment

Lab 2: M1.2 Standards

The task for this module was to perform an accuracy assessment on two versions of the same road network in Albuquerque. One was mapped by the city of Albuquerque (yellow) and one by Street Map USA (red). In order to perform the accuracy assessment twenty points per network needed created at matching intersections on each network. Then a reference point was digitized based on satellite imagery to represent the "actual" location for each intersection. XY coordinates were assigned to all sixty of the created points and the values were exported to an excel spreadsheet. From there the RMSE for each of the networks were calculated using the reference points. With this the accuracy assessment was completed resulting in the following: ABQ_Streets Positional Accuracy: Tested 14.84 feet horizontal accuracy at 95% confidence level. StreetMapUSA Positional Accuracy: Tested 158.56 feet horizontal accuracy at 95% confidence level.

GIS Portfolio - Michael Malone

Search This Blog