GIS 4035 - Module 1 - Visual Interpretation

This map demonstrates, through a grey scale aerial image, how one can classify features on a landscape visually using tone and texture. Tone being the scale of lightness to darkness and texture being a scale of very coarse to very fine. These classifications were done by eye, and may be subjective to the analysts interpretation, as well as the images clarity, scale, and resolution.
This map identifies features in a greyscale aerial photo by 4 means: pattern (Objects/places were chosen that are clearly visible and interpretable as they are part of a larger repeating pattern, but that had they been presented in isolation or at a very large scale, would not be clear as to what they are), shadows (Objects were chosen which could not have been identified had they not been casting a shadow which revealed information about what the object is), association (Objects were chosen that could not be identified without looking at the surrounding environment and making logical connections about what the object might be, given its proximity to other identifiable objects), and shape/size (Objects were chosen which could be identified solely off of their individual appearance and not using any other contextual clues in the image). This process demonstrates these techniques for feature identification on an image. This method is subjective to the analysts interpretation, as well as the images scale, resolution, and in the case of shadows, the declination of the sun.




Comments

Post a Comment

Popular posts from this blog

GIS 4036 - Spatial Enhancement

Image
This lab follows methods of spatial enhancement using various techniques in both ERDAS IMAGE and ArcGIS Pro. The process summary for the different sections can be seen below, as well as some finished map products that were produced using these methods.  Exercise 1: In this exercise, using the glovis.usgs.gov site, I explored the different freely available satellite data from various satellites and how to view the metadata. I did make an account with the website to be able to download data, however I did not receive the confirmation email yet so I am using the data that was provided already in the UWF drive and did not download any data from the website. The image file in the folder was in a .tar.gz format. To convert it into a .tif file, the process involved unzipping the file into a .tar folder, and then once again unzipping that folder into a folder which contains 7 tif files and then supporting documents. It seems this process progressively sheds layers of the original file ...
Read more

GIS 4036 - Unsupervised and Supervised Image Classification

Image
This module focuses on methods of classifying raster images, including supervised and unsupervised classifications. The above map shows an example of supervised image classification completed in ERDAS IMAGE and mapped in ArcGIS Pro. By creating features in an image to feed an algorithm, an image was classified based on several polygons created manually. These images were matched across the entire image to create classes. Spectral bands were then compared through histograms to identify the bands which need to be separated due to overlap in like features. The image was then displayed based on these classes, as well as acres belonging to that class.
Read more

GIS 4035 - Module 2 - LULC Classification and Ground Truthing

Image
In this lab, a study area in Pascagoula, MS is classified up to the 1 st  and 2 nd  classifications under the USGS Standard Land Use / Land Cover Classification System, at a minimum mapping unit of 1:2000 inches, using an aerial photograph. The process involves standardizing best judgement in a way that can be replicable and reliable. Once all land parcels are drawn and classified, 30 random points are placed across the area and ground truthing is performed using Google Maps Street View. The percent accuracy is calculated based on the number of correctly identified points divided by the total number of sample points, multiplies by 100. The ground truth results yielded a 73% accuracy result.  The map below shows the results of the classification and ground truthing.  The following classifications were identified based on their characteristics: 11- Residential: Areas with regular patterns of small homes, green or grassy yards, and following small streets. 12- Comm...
Read more