The impact of object size on the thematic accuracy of landcover maps

Abstract

We recently completed the accuracy assessment of a Landsat-derived landcover polygon layer covering the entire province of Alberta (660,000 km²), Canada, for which we gathered reference information for nearly 5000 randomly selected polygons ranging from two hectares to thousands of hectares in size. This gave us the unique opportunity to quantify, for the first time, how the probability of correctly classifying a landcover object varies with its size. Irrespective of whether they are represented as polygons or as sets of connected pixels with the same label, the classification accuracy of landcover objects decreases as their size decreases, steadily for large and medium sizes, and more dramatically when they are within two orders of magnitude of the pixel size of the input image. We show that this size-dependency is bound to occur whenever the size distribution of landcover objects follows an inverse power law. Our results are consistent with previous studies on related issues, confirm the need to account for size when assessing the accuracy of object-based landcover maps, and cast doubts on the validity of (1) recently proposed object-based accuracy estimators, and (2) landscape pattern analyses where the minimum patch size is close to the pixel size.

Acknowledgements

We are grateful to various colleagues and co-workers from the Foothills Facility for Remote Sensing and GIScience who contributed to the reference data set we used in this work.

Funding

This work has been funded in part through the Alberta Biodiversity Monitoring Institute (ABMI), and through the Natural Science and Engineering Research Council of Canada (NSERC) CRD grant #401966-10, also co-funded by Alberta Pacific Forest industries Inc.