Search

Domain adaptation in remote sensing aims at the automatic knowledge transfer between a set of multitemporal and multisource images. This process is often impaired by nonlinear effects in the data, e.g., varying illumination conditions, different viewing angles, and geometry-dependent reflection. In this paper, we introduce the Nonlinear Feature Normalization (NFN), a fast and robust way to align the spectral characteristics of multiple hyperspectral data sets. NFN employs labeled training spectra for the different classes in an image to describe the corresponding underlying low-dimensional manifold structure. A linear basis for data representation is defined by arbitrary class reference vectors, and the image is aligned to the new basis in the same space. This results in samples of the same class being pulled closer together and samples of different classes pushed apart. NFN transforms the data in its original domain, preserving physical interpretability. We use the continuous invertibility of NFN to derive the NFN Alignment (NFNalign) transformation, which can be used for domain adaptation, by transforming one data set to the domain of a chosen reference. The evaluation is performed on multiple hyperspectral data sets as well as our new benchmark for multitemporal hyperspectral data. In a first step, we show that the NFN transformation successfully mitigates nonlinear effects by comparing classification of the linear Spectral Angle Mapper on original and transformed data. Finally, we demonstrate successful domain adaptation with NFNalign by applying it to the task of hyperspectral data preprocessing. The evaluation shows that our approach for alignment of multitemporal data produces high-spectral similarity and successfully allows knowledge transfer, e.g., of classifier models and training data. [ABSTRACT FROM AUTHOR]

The rising food demand requires regular agriculture land-cover updates to support food security initiatives. Agricultural areas undergo dynamic changes throughout the year, which manifest varying radar backscatter due to crop phenology. Certain crops can show similar backscatter if their phenology intersects, but vary later when their phenology differs. Hence, classification techniques based on single-date remote sensing images may not offer optimal results for crops with similar phenology. Moreover, methods that stack images within a cropping season as composite bands for classification limit discrimination to one feature space vector, which can suffer from overlapping classes. Nonetheless, phenology can aid classification of crops, because their backscatter varies with time. This paper fills this gap by introducing a crop sequence-based ensemble classification method where expert knowledge and TerraSAR-X multitemporal image-based phenological information are explored. We designed first-order and higher order dynamic conditional random fields (DCRFs) including an ensemble technique. The DCRF models have a duplicated structure of temporally connected CRFs, which encode image-based phenology and expert-based phenology knowledge during classification. On the other hand, our ensemble generates an optimal map based on class posterior probabilities estimated by DCRFs. These techniques improved crop delineation at each epoch, with higher order DCRFs (HDCRFs) giving the best accuracy. The ensemble method was evaluated against the conventional technique of stacking multitemporal images as composite bands for classification using maximum likelihood classifier (MLC) and CRFs. It surpassed MLC and CRFs based on class posterior probabilities estimated by both first-order DCRFs and HDCRFs. [ABSTRACT FROM PUBLISHER]

This paper deals with the assignment of persistent scatterers (PSs) to buildings represented by a 3-D city model. Affiliating PSs to real-world structures is highly relevant for two reasons. First, it facilitates interpretation of PS deformation estimates and can be even used to improve those estimates using advanced deformation models for complete structures. Second, such an assignment enables the compilation of a PS density map for the structures under investigation. This helps to mitigate the problem of opportunistic sampling, which is one of the major drawbacks of PS interferometry (PSI). Specifically, a framework in which the PSs are geometrically aligned with the city model and assigned to the bounding surfaces of the single models is outlined. Cases where such an assignment cannot be established are attributed to generalization of the city model or to locations where the reflection mechanism inducing the PS does not correspond to a real-world structure. From the assignments, a density map is compiled, and the main factors driving the PS density are identified and discussed: surface structure, shadowing, aspect dependency, and quasi-random effects (e.g., temporary changes due to building renovation activities). The test site for this paper is located in the inner city area of Berlin. PS results of two high-resolution spotlight TerraSAR-X data stacks of different pass directions are used. The buildings are represented by a level-of-detail 2 city model and an airborne light detection and ranging data set. [ABSTRACT FROM AUTHOR]

In this paper, we contribute to answer the question: How accurately can we estimate heights of buildings with flat roofs given one high-resolution single-pass interferometric synthetic aperture radar (InSAR) image pair and one aerial orthophoto? What makes this problem challenging are the different sensor geometries and the sound stochastic combination of all available elevation cues. We revisit already existing methods and develop novel approaches to determine building heights. A rigorous stochastic approach based on least squares adjustment with functionally dependent parameters is introduced to combine all height measurements per building to one robust height estimate. Observation accuracies of the stochastic model are either taken from the literature or estimated empirically. A major benefit of adjustment is that it delivers a posterior standard deviation per height, which can be interpreted as a precision indicator and is of high relevance for practical applications. Estimated heights of an urban scene are compared to ground truth acquired with airborne laser scanning, allowing us to assess height accuracies that can be achieved under nearly optimal conditions. We conduct statistical tests that validate our model and show that a weighted combination of optical and synthetic aperture radar (SAR) data with least squares adjustment delivers reliable height estimates with meter accuracy for flat-roofed buildings. Additionally, we empirically estimate a confidence interval of the estimated heights that directly tells the user the security margin to be included, for example, in case of building evacuations for an anticipated flooding event, under the condition that the data and model have the same specifications as in this paper. [ABSTRACT FROM PUBLISHER]

The improved ground resolution of state-of-the-art synthetic aperture radar (SAR) sensors suggests utilizing SAR data for the analysis of urban areas. The appearance of buildings in SAR or interferometric SAR (InSAR) data is characterized by the consequences of the inherent oblique scene illumination, such as layover, occlusion by radar shadow, and multipath signal propagation. Therefore, particularly in dense built-up areas, building reconstruction is often impossible from a single SAR or InSAR measurement alone. But, the reconstruction quality can be significantly improved by a combined analysis of multi-aspect data. In this paper, two approaches are proposed to detect and reconstruct buildings of different size from multi-aspect high-resolution InSAR data sets. Both approaches focus on the recognition of buildings supported by knowledge-based analysis considering the mentioned SAR-specific effects observed in urban areas. Building features are extracted independently for each direction from the magnitude and phase information of the interferometric data. Initial primitives are segmented and afterward projected from slant-range into the world coordinate system. From the fused set of primitives of both flight directions, building hypotheses are generated. The first approach exploits the frequently observed lines of bright double-bounce scattering, which are used for building reconstruction in residential districts. In the case of larger buildings, such as industrial halls, often additional features of roof and façade elements are visible. Therefore, in a second approach, extended buildings are extracted by grouping primitives of different kinds. The two approaches are demonstrated in an urban environment for an InSAR data set, which has spatial resolution of about 30 cm and was taken from two orthogonal flight directions. [ABSTRACT FROM AUTHOR]