The focus of our second lab module for GIS5027L Photo Interpretation and Remote Sensing was the USGS Land Use/Land Cover Classification System. We learned in our textbook and lecture material that there are four levels in the classification hierarchy with each level increasing in detail leading to a need for increased spatial and spectral resolution. To be able to successfully assign classification codes to features on our photo we used the skills we learned in module 1 where we learned about visual interpretation of aerial imagery. In this exercise, we were only required to classify up to Level II Classification.
In the first exercise, we created a LULC feature class that consisted of the polygons that we created according to the features we identified in the photograph. The map needed to be 100% covered. I found that as I progressed in the exercise I began to see more and more features that I previously had overlooked especially many that would have been Level III classification. It became borderline frustrating but overall it was a great way to learn new techniques that I otherwise would be unaware of. I would have liked to classify to higher levels but time really began to fly as I believe I put in at least 7-8 by the end this exercise.
In the second portion of the lab we did a ground truthing exercise using Google Maps. I created a feature class that covered the mainland portion of the photograph and then used the create a random point tool to drop sample points on the map. We used Google Maps to determine the accuracy of our classifications by using the aerial imagery as well as the Google Maps Street View (GMSV). In most cases this allowed me to determine if my classification choices were true or false. Overall, this was a great hands on exercise for general land use and land cover that provided me with a solid understanding of the USGS Land Use/Land Cover Classification System.
 |
| LULC map of Pascagoula, MS with random ground truthing sample points. |
No comments:
Post a Comment