Advancements in remote sensing technology continue to aid natural disaster damage assessment. Quick and accurate damage assessment significantly increases the speed of recovery efforts and allows aid to reach those most severely affected. Object-oriented classification techniques require minimal user input to remotely classify large areas and may be utilized to provide timely and accurate damage assessments of affected areas. In this study, I explored the use of object-oriented classification techniques to classify downed timber areas in the Dare County Bombing Range in North Carolina. The spatial resolution of scanned color-infrared aerial photography was degraded from 0.2-meter to 3 other spatial resolutions (1-meter, 5-meter, and 10-meter). Training data developed from the 0.2-meter pixel imagery were used to establish training data for all spatial resolutions. Each set of images was classified using object-oriented classification techniques. Results were compared statistically to each other and to results obtained from a manual delineation and a conventional supervised classification. Before the accuracy assessment began, we anticipated that the classification produced by the 0.2-meter imagery would be the most accurate due to the high level of detail in the imagery. After comparing the results of the classifications, there was no statistically significant difference among the object-oriented classifications, but there was a significant difference between the object-oriented results and the other classifications. Using the training data created on the high-resolution imagery to classify the coarser spatial resolution imagery did not cause classification accuracy loss. The potential damage assessment impact of this technique is that low-resolution imagery can be utilized to quickly classify damaged areas, provided high-resolution imagery is used to create training data. This classification technique demonstrates that damage assessment can be accomplished less expensively, without sacrificing accuracy and speed.
| Identifer | oai:union.ndltd.org:NCSU/oai:NCSU:etd-05042007-150056 |
| Date | 10 August 2007 |
| Creators | Swain, Jeff B |
| Contributors | Heather Cheshire, Stacy Nelson, George Hess |
| Publisher | NCSU |
| Source Sets | North Carolina State University |
| Language | English |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://www.lib.ncsu.edu/theses/available/etd-05042007-150056/ |
| Rights | unrestricted, I hereby certify that, if appropriate, I have obtained and attached hereto a written permission statement from the owner(s) of each third party copyrighted matter to be included in my thesis, dis sertation, or project report, allowing distribution as specified below. I certify that the version I submitted is the same as that approved by my advisory committee. I hereby grant to NC State University or its agents the non-exclusive license to archive and make accessible, under the conditions specified below, my thesis, dissertation, or project report in whole or in part in all forms of media, now or hereafter known. I retain all other ownership rights to the copyright of the thesis, dissertation or project report. I also retain the right to use in future works (such as articles or books) all or part of this thesis, dissertation, or project report. |
Page generated in 0.0022 seconds