Skip to Local Navigation
Skip to Content
California State University, Long Beach
CSULB Geospatial Research and Mapping (GRAM) Field Program
Print this pageAdd this page to your favoritesSelect a font sizeSelect a small fontSelect a medium fontSelect a large font

Daily Blog for Peter Nasuti


Posted on June 28, 2013 by Peter Nasuti

Today we sat around all morning practicing presentations, and gave the presentations at two o’clock at Kualoa Ranch and everything went very well, I really enjoyed sharing my research with others and seeing what others had done in detail. After almost three hours of these presentations, the generous professors took us out to eat at Haleiva Joe’s and we all had a delicious dinner! Following this we all headed back to the barn and I finished up my metadata and put all of my data on the NAS. I had so much fun on this trip and learned so much over the past four weeks. I can’t believe that a month has already passed by and it has been a great time living in the barn with 14 friends. I will always remember this trip and it has been such a great experience for me. I am extremely appreciative of what the professors, TAs, and the NSF have done on this trip to help my further my understanding of the research process and applications of geospatial technologies. I am so glad that I decided to apply for this program months ago and have had one of the best months of my life!

Powerpoint and Paper

Posted on June 28, 2013 by Peter Nasuti

I spent the day revising and finishing my powerpoint and final paper. It was a lot of fun to see everything come together  at the end of this awesome research experience. Presentations are tomorrow and I will practice my delivery in the morning!  It will be excited to see what other have come up with over the course of the research process. Presentations should be roughly 7-9 minutes and I plan to meet this goal but it will be difficult as I have so much to talk about. We had excellent Kualoa Beef burgers for dinner and a great time hanging out around the fire later this night.

Processing/Analysis Day

Posted on June 27, 2013 by Peter Nasuti

I began the day by working once again in Definiens eCognition, trying to improve my WV2 classification. After rebuilding and re-analyzing everything with some minor changes, I was able to increase t0 35% overlap with the digitized kuku’i polygons. Still not as much as I would like, but I can just not seem to break out the kuku’i from certain sections of pasture. Because of this classification, I had to reexport and requantify everything in ArcMap.  Following this, I spent just about the entire day working on writing my final paper for my research topic. This paper follows a standard scientific paper format with abstract, intro, methods, results/discussion, and future directions which might be able to help a student next year if they chose to go in a similar pathway working with OBIA. I completed just about all of the paper today except for finishing the final future directions section, and then chose to begin work on my powerpoint presenting my results. I am trying to follow a similar scientific information pathway like my paper but chose to change some things in order to make it flow better for a public presentation. I plan to complete this powerpoint presentation tomorrow morning, and then start practicing the delivery in the afternoon.

Quantifying WV2 and UAV eCog Classifications in Arc

Posted on June 25, 2013 by Peter Nasuti

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.


Starting to put things together

Posted on June 25, 2013 by Peter Nasuti

I jumped back into work today after the memorable day off yesterday, and was ready to get some real work done on my project. I played around with classifications even more this morning trying to improve their accuracy, as always. I did some tests of my quantification process by using some trial imagery from Greg and Scott’s UAV common product. I did this by bringing everything into ArcMap, digitizing kuku’i stands, extracting kuku’i polygons from the eCognition file (which had over 11,000 unique polygons), georectifying the sample imagery, and more to get everything set up. Once features were digitized they were added as layers and shapefiles, and some geoprocessing calculations were completed. The first was the intersect of the digitized UAV visible regions of kuku’i, the second was the union of the eCog classification zones and the digitized UAV stands. Field geometry was utilized to calculate area for all polygons in all regions, and this was essential to measuring accuracy and quantity of overlap. The sum of the area of intersect was then divided by the sum of the area of union, and this calculates the coefficient of areal correlation for the classification of WV2 imagery. My initial assessment was low @ 31% however I believe this was attributed to improper/quick georeferencing, and an extremely small sample site (from initial X-8 captures). The second test I performed later in the day was of different X-8 imagery that covered a much larger region. Paul shared his already processed mosaic of this longer section, which offered a more stable reference base. This resulted in a quick, rough estimate of 61% overlap which was much better to see.

Tomorrow I will reorganize all my data to prevent future problems, and re-digitize and calculate the coefficient of areal correlation for the longer region. After this I will work with the new mosaic-ed Gatewing NIR imagery and hopefully I will be able to differentiate kuku’i on the landscape. I am also planning to utilize eCognition to perform feature extraction on my UAV imagery test sites, compare this to my digitized regions, and quantity the areal correlation for this object based classification as well. It will be interesting to compare how the software does between the two, however it must be noted that UAV imagery is 3-4 band whereas WV2 is 8 band. There will be much higher spatial resolution, hopefully not too high for the computer to process. I am excited to see the result of this and am really enjoying starting to put different elements together and quantify the product of the object based method. It can be frustrating at times working with software when you are trying to find the correct next step, but it is very satisfying to see things start to line up and make sense. Today was a great day and I am probably going to go to be early so I can go all-out tomorrow fixing problems and finding answers!

Day off!

Posted on June 24, 2013 by Peter Nasuti

This Sunday was spent traversing the island trying to fit in every activity possible with this day off. Kerry, Jessica, Julianna, Greg, Howard and I started off snorkeling at a small beach coming down the east side of the island, spent  time looking over the sea and beaches and mountains at the southeastern point, then went to the blowhole where the waves shoot out of the rocks. We ate lunch at Kona Brewing in downtown Honolulu and then took a driving tour up through the center of the island past pineapple fields with gigantic mountain ranges on either side. Greg, Howard and I went snorkeling at Shark’s Cove or something like that, and saw some amazing sights underwater. There were thousands of beautiful fish, urchins, pencil fish, crabs, and much more. After this we drove back to Honolulu to meet up with the other groups in Waikiki and we went to the beach, ate dinner at the international market and explored around the little shops and downtown.

More Classification Work

Posted on June 24, 2013 by Peter Nasuti

The morning today (Saturday the 22nd) was spent continuing work in eCognition working towards improving my classification of kuku’i for the final project. I kept rebuilding feature extraction parameters working to identify the difficult to find kuku’i in the landscape. This is frustrating because it is clear to anyone looking at the screen as to which is kuku’i and which is other vegetation. However, when utilizing the parameters in eCog, the pixel values are averaged across the polygon of interest, which makes things like certain sections of pasture or high level vegetation blend in with kuku’i. This certainty decreases the overall accuracy of this object based method. There are sufficient variables built into the workflow of the software that I am certain that it is possible to isolate the kuku’i near perfectly, however when you must decide your value for scale parameter, shape, compactness, layer weights, and feature extraction methods, there are an innumerable quantity of combinations which all result in very different products. After working with this software for the past few days, I believe I am getting better at deciding these parameters but feel like it would likely take multiple years to gain a true mastery of this program. This afternoon around 4 we all went around and talked about our project progress and plans. I really enjoy what I am working with and studying however I hope to produce a useful product and must get past all the different small associated problems in order to build a correct classification. I am worried that when I quantify my final accuracy of the WV2 classification that it will not be what I wanted, and am continuing to work towards improving this classification day by day.

Classifications and Project Planning

Posted on June 22, 2013 by Peter Nasuti

Today I stayed back at the barn to work on classifying the WV2 imagery to identify and classify the major, pure stands of kuku’i all within the Ka’a’awa Valley. I learned a ton about eCognition today, primarily within segmentation, statistical extraction, feature extraction, and all sorts of other things within this fun program. Briton helped me out a ton all throughout the morning working constantly towards improving the product that I was creating. I corrected the past 2 days GPS points with the local Oahu base station for maximum accuracy and found that I achieved much better precision with the older trimble units which was surprising. However, all of my accuracy was sufficient for vegetation stand identification.

I mapped all of this in ArcGIS, and cleaned up the attribute tables and renamed pictures for attribute association. These ground truthing points are essential in supervised object based statistical classifications in eCog. The majority of the rest of my day was spent working on eCognition in multiple different classifications and segmentations. This program offers limitless authority to the user to determine their settings which reflect in the final product. I kept record of differing scale parameters, shape and compactness threshold controls, layer weights, and more all working towards building the best segmentation which would come into play later. Because the focus of my classification is kuku’i, the identification of this species is the primary goal which I worked towards. Statistical classification did not give sufficient power for analysis, and Kerry and Jessica helped show me the ropes of the feature extraction classification method which is in my opinion exponentially more effective than a general statistical classification with sample site selections. I was very glad to learn this method and will continue improving my classification tomorrow. Feature extraction is conducted by user control and examination of values per band for the various land cover types, see the attached picture where I planned out and calculated differences between classes to determine band settings for extraction and classification.

While I had been working all day on classifications, I was not one hundred percent on my final topic, and replanned the second half of my project with Dr. Wechsler. My new plan is to compare my kuku’i classification from WV2 in eCognition to digitized polygons of kuku’i regions from UAV imagery that has been mosaic-ed into orthophotos. Within ArcGIS, areas of overlap, intersect, can be compared against total areas of union, and areas can be quantified. From all this, the percent coefficient of areal correlation can be calculated to evaluate classification strategies. Ideally I will be able to also classify UAV mosaics but I will see how far I can get with the current plan tomorrow and next week. Overall a productive day and I will really be on a roll the next day or two when I can improve my WV2 classification and obtain my mosaics of the 2 study sites. Another great day with the CSULB GRAM program in Hawaii!!

From collection to classification

Posted on June 21, 2013 by Peter Nasuti

Today I spent the majority of the day collecting points along the northern ridge, transecting the vegetation about midway up the ridge along the higher road. Since working towards expanding my study outside of the riparian corridor, I decided to continue building my understanding of vegetation dynamics in different regions, and thinking about how it might reflect upon remote sensing imagery. My main goal is to identify kuku’i and possible also octopus tree. By now I have over 150 ground truthing points which will provide the foundation of the supervised classification of segmentation regions in eCognition, and will help in later accuracy assessment.

Tomorrow I am planning on staying back at the barn and beginning to build classifications to test software methods and work more in depth with eCognition. I have been watching supplementary youtube tutorials and reading the reference book in order to gain a better understanding of the software in the short time that I need to meet my goals. Briton spent about an hour working with me this afternoon and set me on the right track for tomorrow with some new methods in the program that he showed me, that I am excited about applying tomorrow.

Scott, Thomas, Michelle and I made dinner tonight and put together some spaghetti with meatballs which we think turned out well. I am looking forward to learning many new methods and applications in eCog tomorrow and seeing what it can show me in trial classifications. Later on, I will be able to overlay other critical data to examine relationships within the spatial distribution of the vegetation types of interest.


Ground Truthing Point Collection

Posted on June 20, 2013 by Peter Nasuti

 Today I got out to the field early to collect vegetation points along the riparian corridor with the new data dictionary which I made last night. I started my point collection a little after nine, and covered roughly 80% of the riparian corridor along both sides. I took samples of species all the way along, especially focusing along Kuku’i groves by the road. I also collected other prevalent species to use as a control. This took awhile as I got 60 points and did not get back to base camp until 2. Somehow I managed to fall into a little bog while I was looking up at the vegetation, and was temporarily trapped on an island of vegetation pods in the middle of a deep mud area. Out in the field I made several observations about vegetation distributions along the linear feature, and saw some interesting things about the way kuku’i comprised sections of the canopy. There are many places where Sygyzium cumuni dominates the top of the canopy, yet the kuku’i plays a significant role in the sides of the canopy coming down most of the way to ground level. I made comprehensive note of each point’s relation to the water features, and failed to notice a dominant pattern connected to the distribution of the kuku’i. I did however note that the hala becomes much more prevalent the farther back you move in the valley, however the stands are generally far too small to be identified with satellite imagery. I brought the data back to the barn and plotted the uncorrected x, y coordinates, and while the points have ample vegetation surrounding to make a field stand classification, the majority of places do not have sufficient resolution to facilitate visual classification.

I talked with Dr. Lee back in the barn this afternoon and discussed potentially expanding my study to include octopus tree in place of kiawe, and to also expand the study area to the valley rather than just the riparian corridor. I am hoping to improve my skills with object based image analysis and understand processes at play in the vegetation of the Ka’a’awa valley throughout the application of my project. However, I feel that I need to specifically organize my goals and methods of study seeing as they have changed from last night, but still need to outline exactly what I am trying to do so I have a foundation to work from. I am not sure precisely what I should do out in the field tomorrow but will likely try to continue improving my understanding of the locations of large, pure stands that will aid in later classifications of both WV2 and UAV imagery. 

About Peter Nasuti

Senior at Appalachian State University in Boone, NC, BS-Geography with a concentration in Geographic Information Systems and a minor in Sustainable Development