You are here:
IMPACTS OF PATCH SIZE AND LANDSCAPE HETEROGENEITY ON THEMATIC IMAGE CLASSIFICATION ACCURACY
Citation:
Smith, J H., J D. Wickham, AND S. V. Stehman. IMPACTS OF PATCH SIZE AND LANDSCAPE HETEROGENEITY ON THEMATIC IMAGE CLASSIFICATION ACCURACY. Presented at Association of American Geographers, New York, NY, February 27-March 3, 2001.
Impact/Purpose:
Our research objectives are to: (a) develop new methods using satellite remote sensor data for the rapid characterization of LC condition and change at regional to national scales; (b) evaluate the utility of the new NASA-EOS MODIS (Moderate Resolution Imaging Spectrometer) leaf area index (LAI) measurements for regional scale application with landscape process models (e.g., biogenic emissions and atmospheric deposition); (c) provide remote sensor derived measurement data to advance the development of the next generation of distributed landscape process-based models to provide a predictive modeling capability for important ecosystem processes (e.g., nutrients, sedimentation, pathogens, etc.); and (d) integrate in situ monitoring measurement networks with UAV and satellite based remote sensor data to provide a continuous environmental monitoring capability.
Description:
Impacts of Patch Size and Landscape Heterogeneity on Thematic Image Classification Accuracy.
Currently, most thematic accuracy assessments of classified remotely sensed images oily account for errors between the various classes employed, at particular pixels of interest, thus ignoring, the landscape context of the pixel. This study analyzed the effects of this context by lncorporating patch size and landscape heterogeneity in the assessment of classification accuracy Land cover and accuracy assessment data were acquired as part of the Multi-Resolution Land Characterization (MUC) project. These data scts were analyzed using ARC/INFO GRID, isolating portions of land cover data, measuring heterogeneity and aggregating identically classified pixels into distinct regions. Logistic regression techniques were then used to test the influence of region size and neighborhood heterogeneity on whether a pixel was correctly classified, or not. The results revealed that both do impact classification accuracy and that these impacts vary among the classes identified. In general, classification accuracy decreased as regions got smaller and as heterogeneity increased, with the largest portions of error introduced when more than two different classes were present in a three by three pixel neighborhood. In order to acquire a complete picture of classification accuracy, neighborhood characteristics such as patch size and heterogeneity should be incorporated into the accuracy assessment process.