You are here:
USING CLASSIFICATION CONSISTENCY IN INTER-SCENE OVERLAP AREAS TO MODEL SPATIAL VARIATIONS IN LAND-COVER ACCURACY OVER LARGE GEOGRAPHIC REGIONS
Citation:
Gundon, B. AND C Edmonds. USING CLASSIFICATION CONSISTENCY IN INTER-SCENE OVERLAP AREAS TO MODEL SPATIAL VARIATIONS IN LAND-COVER ACCURACY OVER LARGE GEOGRAPHIC REGIONS. Chapter 10, Ross Lunetta & John Lyon (ed.), Remote Sensing and GIS Accuracy Assessment. Taylor & Francis Books, Inc., Boca Raton, FL, (2004).
Impact/Purpose:
The primary objectives of this research are to:
- Provide information on the variability in water supply that can be expected under varying climatic conditions. Early efforts will be focused on assembling regional databases for at least two counties (Mecklenberg County and York County) within SEQL region that can be used for water supply generation and model development.
- Develop tools that will help improve our ability to evaluate, study, and model linkages between different types of environmental systems: hydrologic, geomorphic, ecological, and climatic.
- Explore the use of annual and seasonal measurements of large lake surface temperatures as a new ecological indicator of the overall thermal content of those lakes, and construct an estimator of seasonal large lake heat budgets.
Description:
During the last decade, a number of initiatives have been undertaken to create systematic national and global data sets of processed satellite imagery. An important application of these data is the derivation of large area (i.e. multi-scene) land cover products. Such products, however, can be expected to exhibit internal variations in information quality for two principal reasons. First, they have been assembled from a multi-temporal mix of satellite scenes acquired under differing seasonal and atmospheric conditions. Second, intra-product landscape diversity will lead to spatially varying levels of class commission errors. Detailed modelling of these variations with conventional ground truth is prohibitively expensive and hence an alternative, albeit indirect, accuracy assessment method must be sought, preferably one that provides a measure of classification confidence at the pixel level.
In this paper we propose a method for confidence estimation based on the analysis of classification consistency in regions of overlapping image coverage between Landsat scenes from ad acent orbital i paths and rows. We have developed an overall land cover mapping methodology that exploits consistency evaluation both to improve classification performance during product generation and to conduct post-generation accuracy assessment. This methodology has been implemented within a prototype mapping system, QUAD-LACC (Guindon, 2002), and is being employed to derive synoptic land cover products of the Great Lakes watershed from archival Landsat Multi-spectral scanner (MSS) imagery.
Our methodology involves an independent clustering and classification of each Landsat scene. The interpretation quality of each scene is assessed by comparing its classification of pixels in overlap regions with those of its four nearest neighbouring scenes. Consistency statistics are then used both to identify mislabelled clusters and to assign a measure of classification confidence to each cluster. Finally, the scene-based classifications are 'composited' to generate a final seamless land cover product and an accompanying confidence layer. At the pixel level, this layer quantifies a cumulative confidence that encapsulates the number of independent label estimates available, their level of agreement and the inherent confidence of their parent clusters. It should be noted that others have suggested using overlap regions for accuracy characterization, not in classification but rather landscape metric estimation (e.g. Brown et al., 2000).