Search

Friedrich (Fritz) Ackermann, Professor Emeritus of Photogrammetry and Surveying and Former Director of the Institute for Photogrammetry at the University of Stuttgart. gl Fritz Ackermann was born on the 1st November 1929 in Moosbeuren (Ehingen) on the Danube. When Professor E. Gotthardt was appointed to the Technical University of Munich in 1965, his professorship in Stuttgart was vacant and Fritz Ackermann was able to demand the foundation of a new Institute for Photogrammetry in his appointment negotiations - he took over its direction on the 1st April 1966. The analytical block adjustment also fascinated the young researcher Fritz Ackermann, who was able to write a doctoral thesis at the ITC on "Error-Theoretical Investigations on the Accuracy of Photogrammetric Strip Triangulations" (DGK Series C, Issue No. 87) and defended it at the University of Stuttgart in 1964 - his supervisor was Professor E. Gotthardt. [Extracted from the article]

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]

Abstract: Persistent Scatterer Interferometry (PSI) is a technique to simultaneously estimate surface deformation and 3D structure from stacks of SAR images. It was proposed first about one decade ago to monitor preferably urban areas, where in general the highest numbers of PS are found. At that time no high-resolution satellite SAR data were available. Instead, for example, stacks of ERS imagery were used providing ground range resolution of about 25m. In data of such kind only the strongest PS can be detected, which are usually caused by corner reflectors built by orthogonal building and road planes of considerable size, whereas smaller structures causing weaker ones signal are averaged by clutter or mutually interfere with others in the same resolution cell. Thus, if any, only a few or even just one single PS are found per building. The advent of a new senor generation of systems like TerraSAR-X and COSMO-Skymed in 2007 led to a significant improvement of spatial resolution of about one order of magnitude. This comes along with a dramatic rise of PS density: In some cases tens to hundreds are detected at large buildings, which offers the possibility to monitor even individual urban objects. In addition, especially at building façades the distribution of those PS is often quite regular. A reason for that is the usually rectilinear arrangement of façade structures inducing PS like windows or balconies. Those patterns contain a lot of information about the objects under investigation, which is mostly ignored in current PSI processing schemes. For example, consider a regular structure of windows on a certain façade of a multi-story building. Assuming the same kind of structure generates one single PS at each window, the phase centers of all scatterers caused by windows of each floor share the same height. This means, we may benefit from such kind of redundancy, for instance, to improve the height estimate by averaging over PS having the same elevation. In this work, we first discuss the regular appearance of PS at urban façades for an urban test scene in TerraSAR-X spotlight mode data. Then, we show how PS analysis could benefit by exploitation of the redundancy due to repetitive patterns of man-made objects. Finally, we propose a PS grouping scheme based on a production system and discuss first results achieved for the test area. [Copyright &y& Elsevier]

Abstract: SAR stereo image analysis for 3D information extraction is mostly carried out based on imagery taken under same-side or opposite-side viewing conditions. For urban scenes in practice stereo is up to now usually restricted to the first configuration, because increasing image dissimilarity connected with rising illumination direction differences leads to a lack of suitable features for matching, especially in the case of low or medium resolution data. However, due to two developments SAR stereo from arbitrary viewing conditions becomes an interesting option for urban information extraction. The first one is the availability of airborne sensor systems, which are capable of more flexible data acquisition in comparison to satellite sensors. This flexibility enables multi-aspect analysis of objects in built-up areas for various kinds of purpose, such as building recognition, road network extraction, or traffic monitoring. The second development is the significant improvement of the geometric resolution providing a high level of detail especially of roof features, which can be observed from a wide span of viewpoints. In this paper, high-resolution SAR images of an urban scene are analyzed in order to infer buildings and their height from the different layover effects in views taken from orthogonal aspect angles. High level object matching is proposed that relies on symbolic data, representing suitable features of urban objects. Here, a knowledge-based approach is applied, which is realized by a production system that codes a set of suitable principles of perceptual grouping in its production rules. The images are analyzed separately for the presence of certain object groups and their characteristics frequently appearing on buildings, such as salient rows of point targets, rectangular structures or symmetries. The stereo analysis is then accomplished by means of productions that combine and match these 2D image objects and infer their height by 3D clustering. The approach is tested using real SAR data of an urban scene. [Copyright &y& Elsevier]

Abstract: Modern airborne synthetic aperture radar sensors provide high spatial resolution data. Experimental systems have even achieved decimetre resolution. In such data, many features of urban objects can be identified, which are beyond what has been achieved by radar remote sensing before. An example for the new quality of the appearance of urban man-made objects such as buildings in these data is given and interpreted. The fine level of detail opens the opportunity to reconstruct detailed structures of such objects from SAR data with structural pattern recognition techniques. Artificial intelligence concepts such as production systems provide proper means for this purpose. The feasibility of these methods is demonstrated here. Extended building features such as long thin roof edge lines, groups of salient point scatterers, and symmetric configurations are detected using principles from perceptual grouping and Gestalt psychology. These are good continuation, similarity, proximity and symmetry. [Copyright &y& Elsevier]

Abstract: State-of-the-art airborne SAR sensors provide high-resolution ground mapping data. This offers the opportunity of using this technology for the analysis of built-up areas. However, especially at building locations different SAR specific phenomena like layover, shadow, and multipath-propagation burden the interpretation of the SAR imagery even for experts. In order to consider such effects in the analysis and the geocoding of SAR data, high-resolution information about the 3D structure of the urban scene is required. Three dimensional elevation data from a GIS can be provided in different representations, like DEM (raster data) or city models (vector data). In this paper, the benefit of GIS data for the SAR mission planning and the analysis of acquired SAR data are discussed. For the first task, the SAR acquisition parameters are optimized a priori with respect to the best mapping of a local area or a certain object class. For this optimization, a large number of simulations with systematically varying aspect and viewing angles are carried out. For the second task, the 2D and 3D context information are fused with the acquired SAR imagery to support the interpretation for a change detection task. Additionally, simulated features of man-made objects are offered to the image interpreter for comparison with the data. The feasibility of different kinds of GIS data for these purposes is discussed. [Copyright &y& Elsevier]

Since trees are a vital part of urban green infrastructure, automatic mapping of individual urban trees is becoming increasingly important for city management and planning. Although deep-learning-based object detection networks are the state-of-the-art in computer vision, their adaptation to individual tree detection in urban areas has scarcely been studied. Some existing works have employed 2D object detection networks for this purpose. However, these have used three-dimensional information only in the form of projected feature maps. In contrast, we exploited the full 3D potential of airborne laser scanning (ALS) point clouds by using a 3D neural network for individual tree detection. Specifically, a sparse convolutional network was used for 3D feature extraction, feeding both semantic segmentation and circular object detection outputs, which were combined for further increased accuracy. We demonstrate the capability of our approach on an urban topographic ALS point cloud with 10,864 hand-labeled ground truth trees. Our method achieved an average precision of 83% regarding the common 0.5 intersection over union criterion. 85% percent of the stems were found correctly with a precision of 88%, while tree area was covered by the individual tree detections with an F1 accuracy of 92%. Thereby, we outperformed traditional delineation baselines and recent detection networks. [ABSTRACT FROM AUTHOR]

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]

High food demand has led stakeholders to regularly monitor agricultural production to ensure food security and a balanced ecosystem. Agricultural areas undergo rapid changes throughout a growing season due to phenology. Crop mapping initiatives therefore require efficient and effective information gathering techniques. Remote sensing, specifically radar, offers an effective land-cover mapping platform compared to ground surveying methods. Radar is sensitive to crop physical structure and biomass/vegetation water content, i.e. dielectric property. We adopt and test the potential of the recent Sentinel 1 images for multitemporal crop classification due to its short revisit period and sufficient spatial resolution. The temporal resolution guarantees the highest temporal density of images that captures crop dynamics. However, this presents dimensionality problems in classification algorithms. Therefore, we chose dynamic conditional random fields (DCRFs) and tested their robustness in high-dimensional images constrained to few training data. DCRFs are designed to incorporate spatio-temporal phenological information inherent in images during crop classification. We compare the approach to single epoch classification. Our findings indicate that DCRFs improved crop mapping accuracy in all epochs. Nonetheless, most stakeholders require seasonal crop-type statistics. Hence, we use an ensemble classifier to produce an optimal map from posterior class probabilities estimated from the sequence of images. The ensemble outperforms the conventional approach of merging multitemporal images as composite bands for classification using Maximum Likelihood Classifier (MLC-stack) and mono-temporal conditional random fields. It still retains high accuracy compared to MLC-stack when subjected to high-dimensional images with fewer 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]

Radargrammetry is a useful approach to generate Digital Surface Models (DSMs) and an alternative to InSAR techniques that are subject to temporal or atmospheric decorrelation. Stereo image matching in radargrammetry refers to the process of determining homologous points in two images. The performance of image matching influences the final quality of DSM used for spatial-temporal analysis of landscapes and terrain. In SAR image matching, local matching methods are commonly used but usually produce sparse and inaccurate homologous points adding ambiguity to final products; global or semi-global matching methods are seldom applied even though more accurate and dense homologous points can be yielded. To fill this gap, we propose a hierarchical semi-global matching (SGM) pipeline to reconstruct DSMs in forested and mountainous regions using stereo TerraSAR-X images. In addition, three penalty functions were implemented in the pipeline and evaluated for effectiveness. To make accuracy and efficiency comparisons between our SGM dense matching method and the local matching method, the normalized cross-correlation (NCC) local matching method was also applied to generate DSMs using the same test data. The accuracy of radargrammetric DSMs was validated against an airborne photogrammetric reference DSM and compared with the accuracy of NASA's 30 m SRTM DEM. The results show the SGM pipeline produces DSMs with height accuracy and computing efficiency that exceeds the SRTM DEM and NCC-derived DSMs. The penalty function adopting the Canny edge detector yields a higher vertical precision than the other two evaluated penalty functions. SGM is a powerful and efficient tool to produce high-quality DSMs using stereo Spaceborne SAR images. [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]

Abstract: In this work we address the task of the contextual classification of an airborne LiDAR point cloud. For that purpose, we integrate a Random Forest classifier into a Conditional Random Field (CRF) framework. It is a flexible approach for obtaining a reliable classification result even in complex urban scenes. In this way, we benefit from the consideration of context on the one hand and from the opportunity to use a large amount of features on the other hand. Considering the interactions in our experiments increases the overall accuracy by 2%, though a larger improvement becomes apparent in the completeness and correctness of some of the seven classes discerned in our experiments. We compare the Random Forest approach to linear models for the computation of unary and pairwise potentials of the CRF, and investigate the relevance of different features for the LiDAR points as well as for the interaction of neighbouring points. In a second step, building objects are detected based on the classified point cloud. For that purpose, the CRF probabilities for the classes are plugged into a Markov Random Field as unary potentials, in which the pairwise potentials are based on a Potts model. The 2D binary building object masks are extracted and evaluated by the benchmark ISPRS Test Project on Urban Classification and 3D Building Reconstruction. The evaluation shows that the main buildings (larger than 50m2) can be detected very reliably with a correctness larger than 96% and a completeness of 100%. [Copyright &y& Elsevier]

In recent years, Synthetic Aperture Radar (SAR) data is being used intensely for scientific applications and many SAR missions have been accomplished. On the contrary of optical systems operating based on passive sensing principle, SAR technology is capable of providing data independent of weather conditions and time of acquisition under favour of active sensing ability and long wavelength. The most important problem of SAR data was decided upon the resolution. However, this problem is overcome with orbitting of TerraSAR-X (TSX) which is considered to be a revolution. TSX can provide high resolution data (up to 1m) covering large areas thanks to three different imaging modes. Today, many scientific studies are performed employing TSX data. ISPRS SAR Interferometry Working Group is also conducting a project that performs quality assessment of digital elevation models generated from TSX data. Within the scope of this project, several test sites are being studied from Turkey, Spain, Germany and Italy. In this research, many high resolution DEMs are generated using 3m azimuth resolution TSX StripMap (SM) mode images for Barcelona (Spain) and the most suitable one is chosen and quality assessment is performed on it in the context of the aforementioned project. For the study, quality assessment is performed taking into consideration accuracy and visuality components in Barcelona test site that has been partitioned in two sub-areas as a large area with steep and mountainous topography and an urban area. In the application, a photogrammetric reference model that has 10 cm horizontal and 10 cm - 1 m vertical accuracy was used for the verification. The results show that TSX DEM is compatible with all aspects of the topography with the accuracy between ±8-10m. As another application in the study, Barcelona city model available in Google Earth, which is known to be generated by very accurate LIDAR data, and PSI results of TSX are compared. As a result, it is observed that PSI products and reference data are quite compatible and RMSZ of elevations are around 2,5m. [ABSTRACT FROM AUTHOR]

Abstract: The GESTALT system is a stratified architecture designed for challenging computer vision tasks. As example application building recognition from high-resolution SAR-data of three urban scenes of different types is presented. This contribution focuses on the 3rd and 4th layers of the system: the grouping and decision layers. The 3rd layer contains an assessment driven perceptual grouping process with any-time capability and flexible control. Object grouping is based on the principles of Gestalt psychology such as similarity, continuity, and symmetry. A dynamic programming optimization is used in the final decision layer to assemble closed polygons delineating building outlines. Further post-processing includes polygon editing and consistency enforcement. [Copyright &y& Elsevier]

Geographic Object-Based Image Analysis (GEOBIA) techniques have become increasingly popular in remote sensing. GEOBIA has been claimed to represent a paradigm shift in remote sensing interpretation. Still, GEOBIA--similar to other emerging paradigms--lacks formal expressions and objective modelling structures and in particular semantic classification methods using ontologies. This study has put forward an object-based semantic classification method for high resolution satellite imagery using an ontology that aims to fully exploit the advantages of ontology to GEOBIA. A three-step workflow has been introduced: ontology modelling, initial classification based on a data-driven machine learning method, and semantic classification based on knowledge-driven semantic rules. The classification part is based on data-driven machine learning, segmentation, feature selection, sample collection and an initial classification. Then, image objects are re-classified based on the ontological model whereby the semantic relations are expressed in the formal languages OWL and SWRL. The results show that the method with ontology--as compared to the decision tree classification without using the ontology--yielded minor statistical improvements in terms of accuracy for this particular image. However, this framework enhances existing GEOBIA methodologies: ontologies express and organize the whole structure of GEOBIA and allow establishing relations, particularly spatially explicit relations between objects as well as multi-scale/hierarchical relations. [ABSTRACT FROM AUTHOR]

Abstract: Reliable extraction of corresponding straight lines in overlapping images can be used for different purposes such as 3D object extraction, image registration, automated triangulation, etc. In this study, a new approach for the matching of straight line features from stereo aerial images is presented. Initial correspondences between stereo images are generated using a pair-wise stereo matching approach, which involves a total of seven relational constraints. The final straight line correspondences between the stereo images are established in a line-to-line matching stage. The optimal settings for the parameters guiding the matching phase are determined after analysing the probability density functions (PDFs). The proposed approach is tested on 30 image patches of two different urban areas, and as a result, very successful and promising stereo line matching performances are achieved. Besides, the comparison of the results of the proposed approach with the results of one of the state-of-the-art stereo matching approaches proves the superiority and potential of the proposed approach. [Copyright &y& Elsevier]

Lidar waveforms are 1-D signals representing a train of echoes caused by reflections at different targets. Modeling these echoes with the appropriate parametric function is useful to retrieve information about the physical characteristics of the targets. This paper presents a new probabilistic model based upon a marked point process which reconstructs the echoes from recorded discrete waveforms as a sequence of parametric curves. Such an approach allows to fit each mode of a waveform with the most suitable function and to deal with both, symmetric and asymmetric, echoes. The model takes into account a data term, which measures the coherence between the models and the waveforms, and a regularization term, which introduces prior knowledge on the reconstructed signal. The exploration of the associated configuration space is performed by a reversible jump Markov chain Monte Carlo (RJMCMC) sampler coupled with simulated annealing. Experiments with different kinds of lidar signals, especially from urban scenes, show the high potential of the proposed approach. To further demonstrate the advantages of the suggested method, actual laser scans are classified and the results are reported. [ABSTRACT FROM AUTHOR]

Abstract: The Wadden Sea is a unique habitat formed by the strong influence of tidal currents. Twice a day the area is flooded and falls dry afterwards. Due to the force of tidal streams, strong morphologic changes occur frequently. In order to monitor these changes, high precision digital terrain models (DTMs) are required. Lidar proved to be an adequate technique to deliver highly accurate 3D mass points of the surface and dense spacing. However, water often remains within tidal channels and depressions even at low tide, and near infrared lidar is not able to penetrate the water leading to a point cloud which contains surface and water points. Thus, the standard processing workflow for DTM generation from lidar is not suited for the Wadden Sea. In this article, a new workflow is proposed for DTM generation from lidar data in the Wadden Sea. Two major building blocks of this workflow, namely classification of the water points and structure line detection, are presented in detail. For both tasks suitable algorithms were developed tailored to meet special requirements of mudflat. Lidar measurements from water surfaces are detected by a supervised fuzzy classification using the features height, intensity, and 2D point density. Structure lines are derived through a piecewise reconstruction of the surface from the lidar data with a hyperbolic tangent function. The obtained results show that both methods considerably improve the accuracy of DTMs from lidar data. [Copyright &y& Elsevier]

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]

Remote sensing (RS) image segmentation is an essential step in geographic object-based image analysis (GEOBIA) to ultimately derive “meaningful objects”. While many segmentation methods exist, most of them are not efficient for large data sets. Thus, the goal of this research is to develop an efficient parallel multi-scale segmentation method for RS imagery by combining graph theory and the fractal net evolution approach (FNEA). Specifically, a minimum spanning tree (MST) algorithm in graph theory is proposed to be combined with a minimum heterogeneity rule (MHR) algorithm that is used in FNEA. The MST algorithm is used for the initial segmentation while the MHR algorithm is used for object merging. An efficient implementation of the segmentation strategy is presented using data partition and the “reverse searching-forward processing” chain based on message passing interface (MPI) parallel technology. Segmentation results of the proposed method using images from multiple sensors (airborne, SPECIM AISA EAGLE II, WorldView-2, RADARSAT-2) and different selected landscapes (residential/industrial, residential/agriculture) covering four test sites indicated its efficiency in accuracy and speed. We conclude that the proposed method is applicable and efficient for the segmentation of a variety of RS imagery (airborne optical, satellite optical, SAR, high-spectral), while the accuracy is comparable with that of the FNEA method. [ABSTRACT FROM AUTHOR]

Abstract: Full-waveform lidar data are increasingly being available. Morphological features can be retrieved from the echoes composing the waveforms, and are now extensively used for a large variety of land-cover mapping issues. However, the genuine contribution of these features with respect to those computed from standard discrete return lidar systems has been barely theoretically investigated. This paper therefore aims to study the potential of full-waveform data through the automatic classification of urban areas in building, ground, and vegetation points. Two waveform processing methods, namely a non-linear least squares method and a marked point process approach, are used to fit the echoes both with symmetric and asymmetric modeling functions. The performance of the extracted full-waveform features for the classification problem are then compared to a large variety of multiple-pulse features thanks to three feature selection methods. A support vector machines classifier is finally used to label the point cloud according to various scenarios based on the rank of the features. This allows to find the best classification strategy as well as the minimal feature subsets allowing to achieve the highest classification accuracy possible for each of the three feature selection methods. The results show that the echo amplitude as well as two features computed from the radiometric calibration of full-waveform data, namely the cross-section and the backscatter coefficient, significantly contribute to the high classification accuracies reported in this paper (around 95%). Conversely, features extracted from the non Gaussian modelling of the echoes are not relevant for the discrimination of vegetation, ground, and buildings in urban areas. [Copyright &y& Elsevier]