Operational Automatic Remote Sensing Image Understanding Systems: Beyond Geographic Object-Based and Object-Oriented Image Analysis (GEOBIA/GEOOIA). Part 1: Introduction

Abstract

According to existing literature and despite their commercial success, state-of-the-art two-stage non-iterative geographic object-based image analysis (GEOBIA) systems and three-stage iterative geographic object-oriented image analysis (GEOOIA) systems, where GEOOIA ⊃ GEOBIA, remain affected by a lack of productivity, general consensus and research. To outperform the degree of automation, accuracy, efficiency, robustness, scalability and timeliness of existing GEOBIA/GEOOIA systems in compliance with the Quality Assurance Framework for Earth Observation (QA4EO) guidelines, this methodological work is split into two parts. The first part of this work provides a multi-disciplinary Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis of the GEOBIA/GEOOIA approaches that augments similar analyses proposed in recent years. In line with constraints stemming from human vision, this SWOT analysis promotes a shift of learning paradigm in the pre-attentive vision first stage of a remote sensing (RS) image understanding system (RS-IUS), from sub-symbolic statistical model-based (inductive) image segmentation to symbolic physical model-based (deductive) image preliminary classification. Hence, a symbolic deductive pre-attentive vision first stage accomplishes image sub-symbolic segmentation and image symbolic pre-classification simultaneously. In the second part of this work a novel hybrid (combined deductive and inductive) RS-IUS architecture featuring a symbolic deductive pre-attentive vision first stage is proposed and discussed in terms of: (a) computational theory (system design); (b) information/knowledge representation; (c) algorithm design; and OPEN ACCESSRemote Sens. 2012, 4 2695 (d) implementation. As proof-of-concept of symbolic physical model-based pre-attentive vision first stage, the spectral knowledge-based, operational, near real-time Satellite Image Automatic Mapper™ (SIAM™) is selected from existing literature. To the best of these authors' knowledge, this is the first time a symbolic syntactic inference system, like SIAM™, is made available to the RS community for operational use in a RS-IUS pre-attentive vision first stage, to accomplish multi-scale image segmentation and multi-granularity image pre-classification simultaneously, automatically and in near real-time.

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

“…(II) Overlap wall-to-wall the test SIAM-WELD annual map time-series with the reference USGS NLCD 2006 map to generate instances of an OAMTRX = FrequencyCount(A × B) (Baraldi et al, 2014). (III) Estimate an mDMI set of OP-Q 2 Is, defined as follows, in agreement with the Part 1, Chapter 1 (Baraldi & Boschetti, 2012a, 2012b; Baraldi & Humber, 2015; Baraldi et al, 2013).

Product effectiveness.

…”

“…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.…”

“…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.

…”

GEO-CEOS stage 4 validation of the Satellite Image Automatic Mapper lightweight computer program for ESA Earth observation level 2 product generation - Part 1: Theory

“…A proposed instantiation of mDMI set of EO OP-Q 2 Is includes: (i) degree of automation, inversely related to human-machine interaction, (ii) effectiveness, e.g., thematic mapping accuracy, (iii) efficiency in computation time and in run-time memory occupation, e.g., inversely related to the number of system’s free-parameters to be user-defined based on heuristics, (iv) robustness (vice versa, sensitivity) to changes in input data, (v) robustness to changes in input parameters to be user-defined, (vi) scalability to changes in user requirements and in sensor specifications, (vii) timeliness from data acquisition to information product generation, (viii) costs in manpower and computer power, (ix) value, e.g., semantic value of output products, economic value of output services, etc. (Baraldi, 2017, 2009; Baraldi & Boschetti, 2012a, 2012b; Baraldi, Boschetti, & Humber, 2014; Baraldi et al, 2010a, 2010b; Baraldi, Gironda, & Simonetti, 2010c; Duke, 2016). According to the Pareto formal analysis of multi-objective optimization problems, optimization of an mDMI set of OP-Q 2 Is is an inherently-ill posed problem in the Hadamard sense (Hadamard, 1902), where many Pareto optimal solutions lying on the Pareto efficient frontier can be considered equally good (Boschetti, Flasse, & Brivio, 2004).…”

“…Since 2012, the same EO data exploitation indicator is expected to decrease, because any increase in productivity of existing EO-IUSs seems unable to match the exponential increase in the rate of collection of EO sensory data (NASA, 2016a). Second, EO-IUSs presented in the RS literature are typically assessed and compared based on the sole thematic mapping accuracy, which means their mDMI set of EO OP-Q 2 Is remains largely unknown to date (Baraldi & Boschetti, 2012a, 2012b). As a consequence, the RS literature is unable to contradict the thesis that no EO-IUS is available in operating mode.…”