Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research & development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.

Abstract. In this paper, we investigate the potential of detecting and classifying vehicle crossings (events) on bridges with ground-based interferometric radar (GBR) data and machine learning (ML) approaches. The GBR data and image data recorded by a unmanned aerial vehicle, used as ground truth, have been measured during field campaigns at three bridges in Germany non-invasively. Since traffic load of the bridges has taken place during the measurement, we have been able to monitor the bridge dynamics in terms of a vertical displacement. We introduce a methodological approach with three steps including preprocessing of the GBR data, feature extraction and well-chosen ML models. The impact of the preprocessing approaches as well as of the selected features on the classification results is evaluated. In case of the distinction between event and no event, adaptive boosting with low-pass filtering achieves the best classification results. Regarding the distinction between different class types of vehicles, random forest performs best utilising low-pass filtered GBR data. Our results reveal the potential of the GBR data combined with the respective methodological approach to detect and to classify events under real-world conditions. In conclusion, the preliminary results of this paper provide a basis for further improvements such as advanced preprocessing of the GBR data to extracted additional features which then can be used as input for the ML models.

Segmenting newspaper pages into articles that semantically belong together is a necessary prerequisite for article-based information retrieval on print media collections like e.g. archives and libraries. It is challenging due to vastly differing layouts of papers, various content types and different languages, but commercially very relevant for e.g. media monitoring. We present a semantic segmentation approach based on the visual appearance of each page. We apply a fully convolutional neural network (FCN) that we train in an end-to-end fashion to transform the input image into a segmentation mask in one pass. We show experimentally that the FCN performs very well: it outperforms a deep learning-based commercial solution by a large margin in terms of segmentation quality while in addition being computationally two orders of magnitude more efficient.

Abstract. This study focuses on detecting vehicle crossings (events) with ground-based interferometric radar (GBR) time series data recorded at bridges in the course of critical infrastructure monitoring. To address the challenging event detection and time series classification task, we rely on a deep learning (DL) architecture. The GBR-displacement data originates from real-world measurements at two German bridges under normal traffic conditions. As preprocessing, we only apply a low-pass filter. We develop and evaluate a one-dimensional convolutional neural network (CNN) to achieve a solely data-driven event detection. As a baseline machine learning approach, we use a Random Forest (RF) with a selected feature-based input. Both models’ performance is evaluated on two datasets by focusing on identifying events and pure bridge oscillations. Generally, the event classification results are promising, and the CNN outperforms the RF with an overall accuracy of 94.7% on the test subset. By relying on an entirely unknown second dataset, we focus on the models’ performances regarding the distinction between events and decays. On this dataset, the CNN meets this challenge successfully, while the feature-based RF classifies the majority of non-event decays as events. To sum up, the presented results reveal the potential of a data-driven DL approach concerning the detection of bridge crossing events in GBR-based displacement time series data. Based on such an event detection, a prospective assessment of bridge conditions seems feasible as an extension to previous structural health monitoring approaches.

Large scale geotechnical earthworks projects, specifically those related to earth dams, dikes, and levees, often require construction of deep vertical seepage barriers. With increasing frequency, the demands of contract compliance, resource scheduling, quality control, and budget management require structured and efficient management of large data sets. Unless properly recognized, the data management requirements can contribute to the complexity, duration and budget of the project. This paper discusses an application of Geographic Information Systems (GIS) technology to capture information from multiple data streams and provide geotechnical feedback, quality control, and project control feedback. This technology was used to provide information to the U.S. Army Corps of Engineers (USACE) as part of the high-profile rehabilitation of the 232-kilometer long Herbert Hoover Dike (HHD) around Lake Okeechobee in South Florida. The implication of this technology to other earthwork projects is demonstrated. RÉSUMÉ: Grands projets de travaux de terrassement, en particulier ceux liés à des barrages de terre, les digues et levées, nécessitent souvent la construction d'un parafoille. De plus en plus, les exigences de respect du contrat, la planification des ressources, contrôle de la qualité et la gestion budgétaire, nécessitent un système de gestion des données structuré et efficace. Sauf si cela est correctement reconnu, les exigences de gestion de données peuvent contribuer à la complexité, la durée et le budget du projet. Cet article examine une application de systèmes d'information géographique (SIG) pour capturer les informations de plusieurs sources de données et fournir une boucle de rétroaction des données géotechniques, contrôle de la qualité, et les informations de contrôle du projet. Cette technologie a été utilisée pour fournir de l'information à l'US Army Corps of Engineers (USACE) pour la réhabilitation à haute visibilité de la Digue Herbert Hoover (HHD), long de 232 kilomètres, autour du lac Okeechobee en Floride du Sud. L'implication de cette technologie à d'autres projets de terrassement est démontrée.