Christian Laubichler

Real-time estimation of actual object depth is an essential module for various autonomous system tasks such as 3D reconstruction, scene understanding and condition assessment. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks has yielded approaches that succeed in achieving realistic depth synthesis out of a simple RGB modality. Most of these models are based on paired RGB-depth data and/or the availability of video sequences and stereo images. However, the lack of RGB-depth pairs, video sequences, or stereo images makes depth estimation a challenging task that needs to be explored in more detail. This study builds on recent advances in the field of generative neural networks in order to establish fully unsupervised single-shot depth estimation. Two generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance, a novel perceptual reconstruction term, and hand-crafted image filters. We comprehensively evaluate the models using a custom-generated industrial surface depth data set as well as the Texas 3D Face Recognition Database, the CelebAMask-HQ database of human portraits and the SURREAL dataset that records body depth. For each evaluation dataset, the proposed method shows a significant increase in depth accuracy compared to state-of-the-art single-image transfer methods.

Radon is a noble gas that occurs naturally as a decay product of uranium. Aside from smoking, radon is considered to be one of the major causes of lung cancer. Indoor environments, where radon can accumulate and potentially reach high concentrations, are of a particular concern. A mixed effects additive model along with a data-driven cross validation model selection method is applied to model the mean indoor radon concentration of dwellings in Austria. For this model a prediction approach is introduced, which enables the mapping of indoor radon potential to identify radon areas in Austria. The data used for modeling was collected in monitoring campaigns for private dwellings in Austria from 2013 to 2019. The proposed method allows policy makers to identify regions with high indoor radon concentrations and enables them to meet regulatory requirements or prioritize radon protection measures. The currently published Austrian radon map and the delineation of radon areas in Austria is based on this proposed method.

Real-time estimation of actual object depth is an essential module for various autonomous system tasks such as 3D reconstruction, scene understanding and condition assessment. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks has yielded approaches that succeed in achieving realistic depth synthesis out of a simple RGB modality. Most of these models are based on paired RGB-depth data and/or the availability of video sequences and stereo images. The lack of sequences, stereo data and RGB-depth pairs makes depth estimation a fully unsupervised single-image transfer problem that has barely been explored so far. This study builds on recent advances in the field of generative neural networks in order to establish fully unsupervised single-shot depth estimation. Two generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance, a novel perceptual reconstruction term and hand-crafted image filters. We comprehensively evaluate the models using industrial surface depth data as well as the Texas 3D Face Recognition Database, the CelebAMask-HQ database of human portraits and the SURREAL dataset that records body depth. For each evaluation dataset the proposed method shows a significant increase in depth accuracy compared to state-of-the-art single-image transfer methods.

Condition monitoring of components in internal combustion engines is an essential tool for increasing engine durability and avoiding critical engine operation. If lubrication at the crankshaft main bearings is insufficient, metal-to-metal contacts become likely and thus wear can occur. Bearing temperature measurements with thermocouples serve as a reliable, fast responding, individual bearing-oriented method that is comparatively simple to apply. In combination with a corresponding reference model, such measurements could serve to monitor the bearing condition. Based on experimental data from an MAN D2676 LF51 heavy-duty diesel engine, the derivation of a data-driven model for the crankshaft main bearing temperatures under steady-state engine operation is discussed. A total of 313 temperature measurements per bearing are available for this task. Readily accessible engine operating data that represent the corresponding engine operating points serve as model inputs. Different machine learning methods are thoroughly tested in terms of their prediction error with the help of a repeated nested cross-validation. The methods include different linear regression approaches (i.e., with and without lasso regularization), gradient boosting regression and support vector regression. As the results show, support vector regression is best suited for the problem. In the final evaluation on unseen test data, this method yields a prediction error of less than 0.4 °C (root mean squared error). Considering the temperature range from approximately 76 °C to 112 °C, the results demonstrate that it is possible to reliably predict the bearing temperatures with the chosen approach. Therefore, the combination of a data-driven bearing temperature model and thermocouple-based temperature measurements forms a powerful tool for monitoring the condition of sliding bearings in internal combustion engines.