Share Email Print

Journal of Applied Remote Sensing

Land cover and land use mapping of the iSimangaliso Wetland Park, South Africa: comparison of oblique and orthogonal random forest algorithms
Author(s): Zaakirah Bassa; Urmilla Bob; Zoltan Szantoi; Riyad Ismail
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

In recent years, the popularity of tree-based ensemble methods for land cover classification has increased significantly. Using WorldView-2 image data, we evaluate the potential of the oblique random forest algorithm (oRF) to classify a highly heterogeneous protected area. In contrast to the random forest (RF) algorithm, the oRF algorithm builds multivariate trees by learning the optimal split using a supervised model. The oRF binary algorithm is adapted to a multiclass land cover and land use application using both the “one-against-one” and “one-against-all” combination approaches. Results show that the oRF algorithms are capable of achieving high classification accuracies (<80%). However, there was no statistical difference in classification accuracies obtained by the oRF algorithms and the more popular RF algorithm. For all the algorithms, user accuracies (UAs) and producer accuracies (PAs) <80% were recorded for most of the classes. Both the RF and oRF algorithms poorly classified the indigenous forest class as indicated by the low UAs and PAs. Finally, the results from this study advocate and support the utility of the oRF algorithm for land cover and land use mapping of protected areas using WorldView-2 image data.

Paper Details

Date Published: 11 March 2016
PDF: 22 pages
J. Appl. Rem. Sens. 10(1) 015017 doi: 10.1117/1.JRS.10.015017
Published in: Journal of Applied Remote Sensing Volume 10, Issue 1
Show Author Affiliations
Zaakirah Bassa, Univ. of KwaZulu-Natal (South Africa)
Urmilla Bob, Univ. of KwaZulu-Natal (South Africa)
Zoltan Szantoi, European Commission Joint Research Ctr. (Italy)
Riyad Ismail, Univ. of KwaZulu-Natal (South Africa)

© SPIE. Terms of Use
Back to Top