%0 Journal Article
%T Quality Assessment of Pre-Classification Maps Generated from Spaceborne/Airborne Multi-Spectral Images by the Satellite Image Automatic Mapper£¿ and Atmospheric/Topographic Correction£¿-Spectral Classification Software Products: Part£¿2£¿¡ª Experimental Results
%A Andrea Baraldi
%A Michael Humber
%A Luigi Boschetti
%J Remote Sensing
%D 2013
%I MDPI AG
%R 10.3390/rs5105209
%X This paper complies with the Quality Assurance Framework for Earth Observation (QA4EO) international guidelines to provide a metrological/statistically-based quality assessment of the Spectral Classification of surface reflectance signatures (SPECL) secondary product, implemented within the popular Atmospheric/Topographic Correction (ATCOR£¿) commercial software suite, and of the Satellite Image Automatic Mapper£¿ (SIAM£¿) software product, proposed to the remote sensing (RS) community in recent years. The ATCOR£¿-SPECL and SIAM£¿ physical model-based expert systems are considered of potential interest to a wide RS audience: in operating mode, they require neither user-defined parameters nor training data samples to map, in near real-time, a spaceborne/airborne multi-spectral (MS) image into a discrete and finite set of (pre-attentional first-stage) spectral-based semi-concepts (e.g., ¡° vegetation¡±), whose informative content is always equal or inferior to that of target (attentional second-stage) land cover (LC) concepts (e.g., ¡° deciduous forest¡±). For the sake of simplicity, this paper is split into two: Part 1¡ªTheory and Part 2¡ªExperimental results. The Part 1 provides the present Part 2 with an interdisciplinary terminology and a theoretical background. To comply with the principle of statistics and the QA4EO guidelines discussed in the Part 1, the present Part 2 applies an original adaptation of a novel probability sampling protocol for thematic map quality assessment to the ATCOR£¿-SPECL and SIAM£¿ pre-classification maps, generated from three spaceborne/airborne MS test images. Collected metrological/ statistically-based quality indicators (QIs) comprise: (i) an original Categorical Variable Pair Similarity Index (CVPSI), capable of estimating the degree of match between a test pre-classification map¡¯s legend and a reference LC map¡¯s legend that do not coincide and must be harmonized (reconciled); (ii) pixel-based Thematic (symbolic, semantic) QIs (TQIs) and (iii) polygon-based sub-symbolic (non-semantic) Spatial QIs (SQIs), where all TQIs and SQIs are provided with a degree of uncertainty in measurement. Main experimental conclusions of the present Part 2 are the following. (I) Across the three test images, the CVPSI values of the SIAM£¿ pre-classification maps at the intermediate and fine semantic granularities are superior to those of the ATCOR£¿-SPECL single-granule maps. (II) TQIs of both the ATCOR£¿-SPECL and the SIAM£¿ tend to exceed community-agreed reference standards of accuracy. (III) Across the three test images and the SIAM£¿¡¯s three semantic
%K attentive vision
%K confusion matrix
%K degree of uncertainty in measurement
%K harmonization (reconciliation) of ontologies
%K land cover classification
%K multi-spectral image
%K overlapping area matrix
%K pre-attentive vision
%K preliminary classification
%K probability sampling
%K quality indicators of operativeness
%K categorical and spatial accuracy of thematic maps
%U http://www.mdpi.com/2072-4292/5/10/5209