Automatic Spectral Rule-Based Preliminary Mapping of Calibrated Landsat TM and ETM+ Images

Abstract

Abstract-Based on purely spectral-domain prior knowledge taken from the remote sensing (RS) literature, an original spectral (fuzzy) rule-based per-pixel classifier is proposed. Requiring no training and supervision to run, the proposed spectral rule-based system is suitable for the preliminary classification (primal sketch, in the Marr sense) of Landsat-5 Thematic Mapper and Landsat-7 Enhanced Thematic Mapper Plus images calibrated into planetary reflectance (albedo) and at-satellite temperature. The classification system consists of a modular hierarchical top-down processing structure, which is adaptive to image statistics, computationally efficient, and easy to modify, augment, or scale to other sensors' spectral properties, like those of the Advanced Spaceborne Thermal Emission and Reflection Radiometer and of the Satellite Pour l'Observation de la Terre (SPOT-4 and -5). As output, the proposed system detects a set of meaningful and reliable fuzzy spectral layers (strata) consistent (in terms of one-to-one or manyto-one relationships) with land cover classes found in levels I and II of the U.S. Geological Survey classification scheme. Although kernel spectral categories (e.g., strong vegetation) are detected without requiring any reference sample, their symbolic meaning is intermediate between those (low) of clusters and segments and those (high) of land cover classes (e.g., forest). This means that the application domain of the kernel spectral strata is by no means alternative to RS data clustering, image segmentation, and land cover classification. Rather, prior knowledge-based kernel spectral categories are naturally suitable for driving stratified application-specific classification, clustering, or segmentation of RS imagery that could involve training and supervision. The efficacy and robustness of the proposed rule-based system are tested in two operational RS image classification problems.Index Terms-Data clustering, fuzzy rule, fuzzy set (FS), generalization capability, image classification, image color analysis, image segmentation, one-class classifier, prior knowledge, remotely sensed imagery, spectral information, supervised and unsupervised learning from finite data.

GEO-CEOS stage 4 validation of the Satellite Image Automatic Mapper lightweight computer program for ESA Earth observation level 2 product generation – Part 2: Validation

“…(i) The year 2006 SIAM decision tree presented in Baraldi et al (2006). (ii) The static decision tree for Spectral Classification of surface reflectance signatures (SPECL) proposed by Dorigo et al (2009), see Table 4 in the Part 1 of this paper, and implemented by the Atmospheric/Topographic Correction for Satellite Imagery (ATCOR) commercial software product (Richter & Schläpfer, 2012a, 2012b).…”

“…In each of its two independent sets of spectral rules for MS shape and MS intensity modelling SIAM pursues redundancy of spectral terms as a necessary condition to accomplish scalability to changes in the sensor spectral resolution specifications. Possible combinations of these two independent sets of spectral rules make the SIAM decision tree implementations, starting from that proposed in pseudo-code in Baraldi et al (2006), capable of representing the multivariate shape and multivariate intensity information components of a target MS hyperpolyhedron, neither necessarily convex nor connected, as a converging combination of independent functions whose individual terms are input with 1- to N -variate variables, with N equal to the total number of spectral channels. Multivariate data statistics are known to be more informative than a sequence of univariate data statistics.…”

“…Implemented in operating mode in the C/C++ programming language, the SIAM software toolbox is “lightweight” because it runs automatically (without human-machine interaction), in near real time (it is non-iterative and its computational complexity increases linearly with image size) and in tile streaming mode (it requires a fixed runtime memory occupation) (Baraldi, 2015, 2017; Baraldi, Puzzolo, Blonda, Bruzzone, & Tarantino, 2006; Baraldi et al, 2010a, 2010b; Baraldi, Gironda, & Simonetti, 2010c; Baraldi, 2011; Baraldi & Boschetti, 2012a, 2012b; Baraldi et al, 2013; Baraldi, Tiede, Sudmanns, Belgiu, & Lang, 2016, 2017; Baraldi & Humber, 2015). In addition to running on either laptop or desktop computers, the SIAM lightweight computer program is eligible for use in mobile application software or web services.…”

“…The core of the non-iterative SIAM software pipeline is a one-pass prior knowledge-based decision tree (expert system) for MS reflectance space hyperpolyhedralization (quantization, partitioning) into static (non-adaptive-to-data) color names, see Figure 2 and refer to Chapter 2 and Chapter 3 in the Part 1. Presented in the RS literature where enough information was provided for the implementation to be reproduced (Baraldi et al, 2006), the SIAM expert system for MS color naming is followed by a well-posed two-pass superpixel detector in the multi-level color map-domain (Dillencourt, Samet, & Tamminen, 1992; Sonka, Hlavac, & Boyle, 1994) and a per-pixel VQ error assessment for VQ quality assurance, in agreement with the GEO-CEOS QA4EO Val guidelines, refer to Figure 4 in the Part 1 of this paper.

10.1080/23312041.2018.1467254-F0002Figure 2.(same as Figure 5 in the Part 1 of this paper, duplicated for the sake of readability of the present Part 2). Examples of land cover (LC) class-specific families of spectral signatures in top-of-atmosphere reflectance (TOARF) values that include surface reflectance (SURF) values as a special case in clear sky and flat terrain conditions.

…”

“…High-level EO image classification is user- and application-specific, where a thematic map product of Level 3 or superior is provided with a legend consistent with the FAO LCCS Modular Hierarchical Phase (MHP) taxonomy (Di Gregorio & Jansen, 2000); refer to Figure 3 in the Part 1 of this paper. Acronym SIAM stays for Satellite Image Automatic Mapper (SIAM), a lightweight computer program for MS reflectance space hyperpolyhedralization into a static vocabulary of MS color names, superpixel detection and vector quantization (VQ) quality assessment (Baraldi, 2017; Baraldi et al, 2006, 2010a, 2010b, 2010c; Baraldi, 2011; Baraldi & Boschetti, 2012a, 2012b; Baraldi et al, 2013; 2016; Baraldi & Humber, 2015).

10.1080/23312041.2018.1467254-F0004Figure 4.Reference USGS NLCD 2006 map of the CONUS.

…”