Quantifying WV2 and UAV eCog Classifications in Arc

I started the morning off by building a classification of a UAV orthophoto in eCognition, the same which I used yesterday for digitizing. This is my primary site for testing methods as I am still looking for a suitable second test site. It spans most of the length of the center of the valley and has multiple small and medium patches of kuku’i, compared to 15-20 commands and many frustrating hours with the WV2 imagery. I was suprised how easy it was to pull out the kuku’i in this image compared to the WV2 imagery. It took 3-4 commands in the process tree to quickly separate the pure stands and even some individuals of kuku’i. It is clearly much more accurate already than the WV2 classification however I still had to quantify everything in ArcMap. I had been calculating some of the areal correlations incorrectly and rebuilt the measurement of the WV2 classification for the test site. I then completed the same analysis for the new UAV image polygons, again finding intersects and unions in order to determine my coefficient of interest. After struggling with projections, referencing errors, data management, and much more all day in the barn, I finally was able to find my values for the two different classification methods. I was correct in seeing that UAV imagery is much more accurate for classification, with areal correlation of more than double that of WV2. It must be remembered that the analysis is based off of digitization of the UAV imagery, however it lines up almost perfectly with the WV2 and there has been little to no vegetation change in the two years since WV2 capture so this should not make a considerable difference. It was excellent to have some success with eCog classification after fighting with the WV2 imagery for the past 4 days of project work! I started working some on my powerpoint and will do more work on this after dinner, and probably also start working on outlining my paper. I am still looking for a second true color mosaic or suitable imagery to build another test site in photoscan, and will likely do this second process tomorrow if I can find something suitable.