Comparing spectral-object-based approaches for extracting and classifying transportation features using high-resolution multi-spectral satellite imagery.

摘要

Recent developments in commercial satellite products have resulted in a broader range of high quality image data, enabling detailed analysis. Transportation features have historically been difficult to accurately identify and structure into coherent networks; prior analyses have demonstrated problems in locating smaller features. One problem is that roadways in urban environments are often partly obscured by proximity to land cover or impervious objects. Ongoing research has focused on object-based methods for classification and different segmentation techniques key to this approach. For this application, software packages such as eCognition have shown encouraging results in assessing spatial and spectral patterns at varied scales in intelligent classification of aerial and satellite imagery.; In this study 2.44m QuickBird and 4m Ikonos multispectral imagery for a 7.5&feet; quad near the Mississippi Gulf Coast are examined. Challenges in analysis include intricate networks of smaller roads in residential zones and regions of tall/dense tree cover. Both spectral and object-based approaches are implemented for pre-classification, and road features are extracted using various techniques, after which the results are compared based on a "Raster Completeness" model developed.