Please use this identifier to cite or link to this item:
|Title:||Mapping Coastal Vegetation Using an Expert System and Hyperspectral Imagery||Contributor(s):||Schmidt, K S (author); Skidmore, A K (author); Kloosterman, E H (author); van Oosten, H (author); Kumar, Lalit (author) ; Janssen, J A M (author)||Publication Date:||2004||Handle Link:||https://hdl.handle.net/1959.11/3044||Abstract:||Mapping and monitoring saltmarshes in the Netherlands are important activities of the Ministry of Public Works (Rijkswaterstaat). The Survey Department (Meetkundige Dienst) produces vegetation maps using aerial photographs. However, it is a time-consuming and expensive activity. The accuracy of the conventional vegetation map derived from using aerial photograph interpretation (API) is estimated to be around 43%. In this study, an alternative method is demonstrated that uses an expert system to combine airborne hyperspectral imagery with terrain data derived from radar altimetry. The accuracy of the vegetation map generated by the expert system increased to 66 percent. When hyperspectral imagery alone was used to classify coastal wetlands, an accuracy of 40 percent was achieved - comparable to the accuracy of the API-derived vegetation map. An analysis of the efficiency of the proposed expert system showed that the speed of map production is increased by using the new method. This means that digital image classification using the expert system is an objective and repeatable method superior to the conventional API method.||Publication Type:||Journal Article||Source of Publication:||Photogrammetric Engineering and Remote Sensing, 70(6), p. 703-715||Publisher:||American Society for Photogrammetry and Remote Sensing||Place of Publication:||United States of America||ISSN:||0099-1112||Field of Research (FOR):||090703 Environmental Technologies||Peer Reviewed:||Yes||HERDC Category Description:||C1 Refereed Article in a Scholarly Journal||Other Links:||http://www.asprs.org/publications/pers/2004journal/june/abstracts.html#703||Statistics to Oct 2018:||Visitors: 302
|Appears in Collections:||Journal Article|
Files in This Item:
checked on Jan 12, 2019
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.