GIS Assisted Change Detection Using Remote Sensing
Title:
GIS Assisted Change Detection Using Remote Sensing
Author:
Turker, Mustafa Derenyi, Eugene
Appeared in:
Geocarto international
Paging:
Volume 15 (2000) nr. 1 pages 51-56
Year:
2000-03
Contents:
Two polygon based image analysis schemes are presented for detecting and monitoring such changes in land use and land cover which are confined to certain geographic boundaries, stored in a geographic information system (GIS). Both schemes are based on the assumption that the changes or no change can be, at least partially, anticipated. The monitoring operation is designed to confirm these expectations or detect the deviation. In the first scheme, a standard pixel-by-pixel image classification is performed, one theme at a time, covering the entire area of interest. A polygon-by-polygon assessment of the results follows to separate those polygons which deviate from the apriori expectations by more than a preset threshold level. These polygons are then subjected to further examination. In the second scheme, image classification is bypassed entirely and only image statistics are generated polygon-by-polygon. A comparison of these statistics with those representing the expected conditions identify the polygons with significant deviation. The above approach to monitoring changes overcomes the problems caused by multi-classified and misclassified pixels which often appear in traditional image classification, due to overlapping spectral signatures. It also provides new polygon attributes for an immediate update of the GIS database. The monitoring of the development of tree plantations is used as an example to demonstrate the concept of both schemes.