Visual pattern recognition models for remote sensing of civil infrastructure

As-built models have been proven useful in many project-related applications, such as progress monitoring and quality control. However, they are not widely produced in most projects because a lot of effort is still necessary to manually convert remote sensing data from photogrammetry or laser scanning to an as-built model. In order to automate the generation of as-built models, the first and fundamental step is to automatically recognize infrastructure-related elements from the remote sensing data. This paper outlines a framework for creating visual pattern recognition models that can automate the recognition of infrastructure-related elements based on their visual features. The framework starts with identifying the visual characteristics of infrastructure element types and numerically representing them using image analysis tools. The derived representations, along with their relative topology, are then used to form element visual pattern recognition (VPR) models. So far, the VPR models of four infrastructure-related elements have been created using the framework. The high recognition performance of these models validates the effectiveness of the framework in recognizing infrastructure-related elements.

Visual Pattern Recognition Models for Remote Sensing of Civil Infrastructure

As-built models have been proven useful in many project-related applications, such as progress monitoring and quality control. However, they are not widely produced in most projects because a lot of effort is still necessary to manually convert remote sensing data from photogrammetry or laser scanning to an as-built model. In order to automate the generation of as-built models, the first and fundamental step is to automatically recognize infrastructure-related elements from the remote sensing data. This paper outlines a framework for creating visual pattern recognition models that can automate the recognition of infrastructure-related elements based on their visual features. The framework starts with identifying the visual characteristics of infrastructure element types and numerically representing them using image analysis tools. The derived representations, along with their relative topology, are then used to form element visual pattern recognition (VPR) models. So far, the VPR models of four infrastructure-related elements have been created using the framework. The high recognition performance of these models validates the effectiveness of the framework in recognizing infrastructure-related elements.

Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing

The aim of this paper is to show that Dempster-Shafer evidence theory may be successfully applied to unsupervised classification in multisource remote sensing. Dempster-Shafer formulation allows for consideration of unions of classes, and to represent both imprecision and uncertainty, through the definition of belief and plausibility functions. These two functions, derived from mass function, are generally chosen in a supervised way. In this paper, the authors describe an unsupervised method, based on the comparison of monosource classification results, to select the classes necessary for Dempster-Shafer evidence combination and to define their mass functions. Data fusion is then performed, discarding invalid clusters (e.g. corresponding to conflicting information) thank to an iterative process. Unsupervised multisource classification algorithm is applied to MAC-Europe'91 multisensor airborne campaign data collected over the Orgeval French site. Classification results using different combinations of sensors (TMS and AirSAR) or wavelengths (L- and C-bands) are compared. Performance of data fusion is evaluated in terms of identification of land cover types. The best results are obtained when all three data sets are used. Furthermore, some other combinations of data are tried, and their ability to discriminate between the different land cover types is quantified

Surface pigments,algal biomass profiles,and potential production of the euphotic layer:Relationships reinvestigated in view of remote-sensing applications

Maps of surface chlorophyllous pigment (Chl a + Pheo a) are currently produced from ocean color sensors. Transforming such maps into maps of primary production can be reliably done only by using light-production models in conjuction with additional information about the column-integrated pigment content and its vertical distribution. As a preliminary effort in this direction. $\ticksim 4,000$ vertical profiles pigment (Chl a + Pheo a) determined only in oceanic Case 1 waters have been statistically analyzed. They were scaled according to dimensionless depths (actual depth divided by the depth of the euphotic layer, $Z_e$) and expressed as dimensionless concentrations (actual concentration divided by the mean concentration within the euphotic layer). The depth $Z_e$ generally unknown, was computed with a previously develop bio-optical model. Highly sifnificant relationships were found allowing $\langle C \rangle_tot$, the pigment content of the euphotic layer, to be inferred from the surface concentration, $\bar C_pd$, observed within the layer of one penetration depth. According to their $\bar C_pd$ values (ranging from $0.01 to > 10 mg m^-3$), we categorized the profiles into seven trophic situations and computed a mean vertical profile for each. Between a quasi-uniform profile in eutrophic waters and a profile with a strong deep maximum in oligotrophic waters, the shape evolves rather regularly. The wellmixed cold waters, essentially in the Antarctic zone, have been separately examined. On average, their profiles are featureless, without deep maxima, whatever their trophic state. Averaged values their profiles are featureless, without deep maxima, whatever their trophic state. Averaged values their profiles are featureless, without deep maxima, whatever their trophic state. Averaged values of $ρ$, the ratio of Chl a tp (Chl a + Pheo a), have also been obtained for each trophic category. The energy stored by photosynthesizing algae, once normalized with respect to the integrated chlorophyll biomass $\langle C \rangle _tot $ is proportional to the available photosythetic energy at the surface via a parameter $ψ∗$ which is the cross-section for photosynthesis per unit of areal chlorophyll. By tanking advantage of the relative stability of $ψ∗.$ we can compute primary production from ocean color data acquired from space. For such a computation, inputs are the irradiance field at the ocean surface, the "surface" pigment from which $\langle C \rangle _tot$ can be derived, the mean $ρ value pertinent to the trophic situation as depicted by the $\bar C_pd or $\langle C \rangle _tot$ values, and the cross-section $ψ∗$. Instead of a contant $ψ∗.$ value, the mean profiles can be used; they allow the climatological field of the $ψ∗.$ parameter to be adjusted through the parallel use of a spectral light-production model.