We present an infrastructure and model inspection planning approach for known structures in unknown environments. The utilized voxel-based model representations increase the input model flexibility and allow to includ...
详细信息
ISBN:
(数字)9798331510954
ISBN:
(纸本)9798331510961
We present an infrastructure and model inspection planning approach for known structures in unknown environments. The utilized voxel-based model representations increase the input model flexibility and allow to include environment maps of the surroundings in the planning problem. By simultaneously optimizing both coverage and path length using a GTSP representation, we are able to outperform other state-of-the-art inspection planning routines in both runtime and path length while achieving equivalent coverage.
The simulation of Synthetic Aperture Radar (SAR) images plays an important role for many applications such as Automatic Target Recognition, damage detection or for the in-detail analysis of signatures found in real SA...
The simulation of Synthetic Aperture Radar (SAR) images plays an important role for many applications such as Automatic Target Recognition, damage detection or for the in-detail analysis of signatures found in real SAR images. The need for creating synthetic SAR images has increased with the advent of Convolutional Neural Networks (CNNs), since, in contrast to the Electro-Optical domain, only a few very specialized data sets of SAR images exist that could be used for training CNNs. Today, several academic and commercial SAR simulators exist. For all of these, the foundation for the simulation is a 3D model of the scene or object to be simulated. Such 3D models exist in large quantities and can be obtained for virtually any object imaginable. However, these models were not specifically designed for SAR simulation and thus the question arises whether they are suitable for the task. In this paper, several aspects of 3D models are highlighted that should be considered when assessing them for SAR simulation.
We present a new simple graph-Theoretic formulation of the exploratory blockmodeling problem on undirected and unweighted one-mode networks. Our formulation takes as input the network G and the maximum number t of blo...
详细信息
Dimension reduction is a commonplace tool to visualize multi-dimensional data and reparametrize the features to have uniform, metric scales. With a concept of training a Machine Learning method with scarce training da...
Dimension reduction is a commonplace tool to visualize multi-dimensional data and reparametrize the features to have uniform, metric scales. With a concept of training a Machine Learning method with scarce training data in mind, we wish to investigate to what extent several well-known dimension reducers are suitable to separate very challenging remote sensing data, in particular, in shadow regions. The Potsdam data includes not only plenty of these regions, but also several seldom classes, such as vehicles or clutter. Hence, optical and elevation data as well as some additional features will be used as input for dimension reduction algorithms.
Industrial production processes are complex systems that require continuous monitoring to ensure efficiency, product quality, and safety. Anomaly detection is a crucial component of these monitoring systems, with mach...
Industrial production processes are complex systems that require continuous monitoring to ensure efficiency, product quality, and safety. Anomaly detection is a crucial component of these monitoring systems, with machine learning (ML) methods offering significant advantages over traditional statistical techniques. Clustering-based unsupervised anomaly detection algorithms, such as Self-Organizing Maps (SOMS), are particularly valuable in process monitoring, as they can detect anomalies and identify process phases without requiring labeled training data. However, unsupervised learning methods can be sensitive to the inherent properties of the training data, particularly in cases of strong correlation between features or unbalanced datasets. This paper presents a hybrid unsupervised learning strategy (HULS) for monitoring complex industrial production processes. The proposed method combines existing techniques to address the challenges posed by correlated and unbalanced data. Experimental results from a synthetic dataset demonstrate the effectiveness of the developed hybrid approach.
During the last decade, Convolutional Neural Networks (CNNs) have revolutionized many areas of electro-optical (EO) image processing, regularly surpassing traditional methods. This success is strongly connected with t...
详细信息
The effectiveness of free-space laser communications is limited due to wavefront deformations caused by atmospheric optical turbulence. To determine these deformations, we propose a wavefront sensor that utilizes the ...
详细信息
Long-term Boundary Layer Scintillometer (BLS) turbulence measurements were performed over the Baltic Sea and statistics are presented. The BLS was also used as a transmissometer and its performance was compared to a c...
详细信息
Healthcare-associated infections (HAIs) are a serious problem. Many studies showed that high-touch environmental surfaces can take part in the transmission of HAIs. Helping to reduce these transmissions an UVC-LED emi...
详细信息
Maximizing the quality and quantity of production output requires the optimization of every single process involved in the production - separately on its own and in combination with other involved processes and assets...
详细信息
Maximizing the quality and quantity of production output requires the optimization of every single process involved in the production - separately on its own and in combination with other involved processes and assets along the line. Worker assistance systems further optimize otherwise automated production systems by minimizing uncertainties of incorporated manual labor. This paper, subsequent to an elaborate use case and requirements analysis, develops a concept to advance these worker assistance systems from more or less isolated applications, that operate independently from other production and resource management platforms, towards an integrated solution using Industry 4.0-compliant Digital Twins of assistance jobs, products, workers and workstations, that document manually executed processes, their parameters, performances and configurations in an interoperable manner. Consequently, worker assistance systems will be established with little effort as a user- and process-specific enterprise resource planning frontend on the shop floor.
暂无评论