Journal
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
Volume 73, Issue -, Pages 170-178Publisher
ELSEVIER
DOI: 10.1016/j.jag.2018.06.014
Keywords
Remote sensing; Object-based image analysis; Satellite imagery; Pansharpening; Atmospheric correction; Topographic correction; Landsat; Random forests
Categories
Funding
- New Zealand Development Aid (NZAID)
Ask authors/readers for more resources
The application of Landsat satellite imagery in land cover classification is affected by atmospheric and topographic errors, which have led to the development of different correction methods. In this study, moderate resolution atmospheric transmission (MODTRAN) and dark object subtraction (DOS) atmospheric corrections, and cosine topographic correction were evaluated individually and combined in a heterogeneous landscape in Zambia. These pre-processing methods were tested using a combination of object-based image analysis (OBIA) and Random Forests (RF) non-parametric classifier (hereafter referred to as OBIA-RF). This assessment aimed at understanding the combined effects of different pre-processing methods and the OBIA-RF classification method on the accuracy of Landsat operational land (OLI-8) imagery with different spatial resolutions. Here, we used pansharpened and standard Landsat OLI-8 images with 15 and 30 m spatial resolutions, respectively. The results showed that non pre-processed images reached a classification accuracy of 68% for pansharpened and 66% for standard Landsat OLI-8. Classification accuracy improved to 93% (pansharpened) and 86% (standard) when combined MODTRAN and cosine topographic correction pre-processing were applied. The results highlight the importance of pansharpening, as well as atmospheric and topographic corrections for Landsat OLI-8 imagery, when used as input in OBIA classification with the RF classifier.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available