Browsing by Author "Sörgel, Uwe (Prof. Dr.-Ing.)"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Forming a hybrid intelligence system by combining Active Learning and paid crowdsourcing for semantic 3D point cloud segmentation
    (2023) Kölle, Michael; Sörgel, Uwe (Prof. Dr.-Ing.)
    While in recent years tremendous advancements have been achieved in the development of supervised Machine Learning (ML) systems such as Convolutional Neural Networks (CNNs), still the most decisive factor for their performance is the quality of labeled training data from which the system is supposed to learn. This is why we advocate focusing more on methods to obtain such data, which we expect to be more sustainable than establishing ever new classifiers in the rapidly evolving ML field. In the geospatial domain, however, the generation process of training data for ML systems is still rather neglected in research, with typically experts ending up being occupied with such tedious labeling tasks. In our design of a system for the semantic interpretation of Airborne Laser Scanning (ALS) point clouds, we break with this convention and completely lift labeling obligations from experts. At the same time, human annotation is restricted to only those samples that actually justify manual inspection. This is accomplished by means of a hybrid intelligence system in which the machine, represented by an ML model, is actively and iteratively working together with the human component through Active Learning (AL), which acts as pointer to exactly such most decisive samples. Instead of having an expert label these samples, we propose to outsource this task to a large group of non-specialists, the crowd. But since it is rather unlikely that enough volunteers would participate in such crowdsourcing campaigns due to the tedious nature of labeling, we argue attracting workers by monetary incentives, i.e., we employ paid crowdsourcing. Relying on respective platforms, typically we have access to a vast pool of prospective workers, guaranteeing completion of jobs promptly. Thus, crowdworkers become human processing units that behave similarly to the electronic processing units of this hybrid intelligence system performing the tasks of the machine part. With respect to the latter, we do not only evaluate whether an AL-based pipeline works for the semantic segmentation of ALS point clouds, but also shed light on the question of why it works. As crucial components of our pipeline, we test and enhance different AL sampling strategies in conjunction with both a conventional feature-driven classifier as well as a data-driven CNN classification module. In this regard, we aim to select AL points in such a manner that samples are not only informative for the machine, but also feasible to be interpreted by non-experts. These theoretical formulations are verified by various experiments in which we replace the frequently assumed but highly unrealistic error-free oracle with simulated imperfect oracles we are always confronted with when working with humans. Furthermore, we find that the need for labeled data, which is already reduced through AL to a small fraction (typically ≪1 % of Passive Learning training points), can be even further minimized when we reuse information from a given source domain for the semantic enrichment of a specific target domain, i.e., we utilize AL as means for Domain Adaptation. As for the human component of our hybrid intelligence system, the special challenge we face is monetarily motivated workers with a wide variety of educational and cultural backgrounds as well as most different mindsets regarding the quality they are willing to deliver. Consequently, we are confronted with a great quality inhomogeneity in results received. Thus, when designing respective campaigns, special attention to quality control is required to be able to automatically reject submissions of low quality and to refine accepted contributions in the sense of the Wisdom of the Crowds principle. We further explore ways to support the crowd in labeling by experimenting with different data modalities (discretized point cloud vs. continuous textured 3D mesh surface), and also aim to shift the motivation from a purely extrinsic nature (i.e., payment) to a more intrinsic one, which we intend to trigger through gamification. Eventually, by casting these different concepts into the so-called CATEGORISE framework, we constitute the aspired hybrid intelligence system and employ it for the semantic enrichment of ALS point clouds of different characteristics, enabled through learning from the (paid) crowd.
  • Thumbnail Image
    ItemOpen Access
    Nonlinear feature normalization for hyperspectral feature transfer
    (2019) Groß, Wolfgang; Sörgel, Uwe (Prof. Dr.-Ing.)
    Hyperspectral remote sensing is an important topic for deriving high-level information about the earth's surface. Applications include land cover mapping, precision farming, and the detection of environmental pollution. This is made possible by recording and evaluating narrow-band features that are characteristic of individual materials. External effects, however, lead to nonlinearities in the data and complicate data analysis. These effects include changes in illumination, hard and partial shadows, as well as transmission / multiple reflections by objects in the scene, and anisotropic effects for 3D objects. Correcting these effects is required for robust data analysis. In particular, when comparing multiple data sets a unified representation is required. Physically motivated models for correcting atmospheric in uences are generally used for the pre-processing of hyperspectral data. However, these models do not consider local variations, such as shadows and object geometry. Therefore, this thesis deals with data-driven approaches in the field of Manifold Alignment (MA) and Feature Transfer (FT) to transfer several data sets to a common system. Previous research on these topics has focused primarily on learning the underlying geometry of high-dimensional data and aligning multiple datasets by determining the minimum discrepancy while preserving the individual data structure. Usually, a common domain with very high dimensionality is chosen to facilitate the alignment. The transformation into another domain, however, prevents physical interpretability. Also, inversion of one data set from the common domain to the domain of a target data set is diffcult due to the pre-image problem.The contributions of this thesis can be divided into two categories. The Nonlinear Feature Normalization (NFN) is a data-driven approach to mitigate nonlinear effects in hyperspectral data. NFN is a supervised method and requires training samples for each class in the scene. A new basis for data representation is defined, consisting of one spectral reference signature per class. The training data are then used to individually shift all samples towards the new basis. This significantly reduces the effects of nonlinearities, as shown by comparing classification results before and after the NFN transformation. The NFN is then used to derive the Nonlinear Feature Normalization for Data Alignment (NFNalign). NFNalign transforms multiple data sets to the same basis in the common domain and then applies an inverse transformation to transfer data sets from the common domain to a domain of another data set. Since the dimensionality of the data is not changed during the transformation, it is possible to perform the inversion analytically. The functionality of NFNalign is demonstrated by transforming hyperspectral radiance data to reflection data. Thereby, the pre-processing step of the atmospheric correction can be replaced, shadows and other nonlinearities are corrected, and characteristic features of the spectral signatures are transferred. The quality of the alignment is demonstrated by applying an SVM model trained on a reference data set to the aligned data set. Additional alignment is assessed by applying a classification model trained on a reference data set to a test data set after it has been transformed to the domain of the reference with NFNalign. Further experiments investigate the robustness with regard to noise and errors in the training data as well as the alignment of data with different dimensions. Also, a comparison with common reference methods is performed. Overall, NFN and NFNalign provide a complete framework for hyperspectral data alignment and FT.
  • Thumbnail Image
    ItemOpen Access
    On the analysis and patterns of persistent scatterer interferometry results for satellite-based deformation monitoring
    (2023) Schneider, Philipp J.; Sörgel, Uwe (Prof. Dr.-Ing.)
    The remote sensing method Persistent Scatterer Interferometry (PSI) has developed in the last two decades into a tool for monitoring deformations of the earths surface. Hereby it can be applied to large areas and scenes like earth quakes, landslides or sinkholes but the increasing availability of high resolution Synthetic Aperture Radar (SAR) data also enables a monitoring of small scenes like individual buildings. PSI is recognized and appreciated in the remote sensing community and its benefit has been proven in countless applications. The PSI principle is based on the evaluation of time series of coherent SAR satellite images and considers the relative phase change over time for individual pixels. As a result of this interferometric evaluation, time series are obtained, which capture line-of-sight (LOS) movement of a scatterer over time with millimetre accuracy. The PSI method is especially suited for urban areas, because of the high density of good radar back scatterers in these locations. For high-resolution SAR data, such as those acquired by the TerraSAR-X mission, millions of such so-called Persistent Scatterer (PS) points and their deformation time series can be obtained. The presentation, evaluation, and interpretation of such data is still a challenge. The here presented research contributes to the question of how the joint analysis of many PS points and their time series can be used to infer the underlying causes of the deformation. The investigation of such a field of time series helps in the understanding of temporal and spatial patterns in movements. A distinction is made between the analysis of large-scale areas and the consideration of points on individual buildings. For wide-area deformations, such as those caused by underground constructions, mining activities or by undermining groundwater flow, adapted methods from meteorology, interpolation and decomposition procedures of different observation geometries are presented and discussed. For the monitoring of individual structures, such as single buildings, methods were developed that combine SAR data and geo-data from other sources, such as Airborne Laser Scanning (ALS) data and crowd sourced building circumferences. It can be shown that by grouping PS points that have correlated motion patterns, a building can be segmented into its statically independently moving elements. To achieve such a clustering in a robust way, so it can be applied to different data sources, a non-linear dimension reduction based on a hybrid distance metric is introduced. The results from such a clustering can then be integrated into detailed 3D models, such as those available for Building Information Modeling (BIM) based construction processes, and thus offer the possibility of a continuous and efficient structural monitoring of a building. Often PSI results have to be communicated to experts from non-SAR affine fields such as civil- and geo- engineering for interpretation, which can be challenging without specialized software. For this purpose, exemplary web portals are presented here, that allow PSI results to be displayed interactively. Such platforms are addressing the specific complexity of PSI data, so that informed decisions can be made. The utility of an ensemble evaluation of many PSI time series can be demonstrated, as it proves beneficial in wide-area processes. Motion patterns become identifiable and their spatial propagation can undergo analysis. When considering PS points on single buildings, a grouping of points based on their deformation patterns leads to redundant measurement and segments a structure into its independently moving parts. This segmentation can then be integrated into existing 3D building models and industry standards, signifying an important advancement towards automated and city-wide risk assessment of buildings. Web-based analysis platforms, specifically tailored for the SAR data, serve as a decision support system (DSS) and aid in sharing the findings with non-SAR experts.
  • Thumbnail Image
    ItemOpen Access