A5082657954- Optical measurement and interference techniques
- Surface Roughness and Optical Measurements
- Industrial Vision Systems and Defect Detection
- Advanced Measurement and Metrology Techniques
- Image and Signal Denoising Methods
- CCD and CMOS Imaging Sensors
- Advanced Vision and Imaging
- Color Science and Applications
- Advanced Image Fusion Techniques
- Medical Image Segmentation Techniques
- Civil and Structural Engineering Research
- Energy Load and Power Forecasting
- Smart Grid Security and Resilience
- Water Quality Monitoring Technologies
- Spectroscopy and Chemometric Analyses
- Image Processing Techniques and Applications
- Intravenous Infusion Technology and Safety
- Hydrological Forecasting Using AI
- Smart Grid Energy Management
- Digital Image Processing Techniques
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation
2023-2024
Karlsruhe Institute of Technology
2013-2018
Pforzheim University of Applied Sciences
2013
Deflectometry as a technique to assess reflective surfaces has now existed for some 40 years. Its different aspects and variations have been studied in multiple theses research articles; reviews are available certain subtopics. Still field of active development with many unsolved problems, deflectometry encompasses large variety application domains, hardware setup types, processing workflows purposes, spans range from qualitative defect inspection vehicles precision measurements microscopic...
Image processing has gained its popularity over the recent years in areas, such as computer vision, artificial intelligence and automation. Deflectometry image technique is developed to inspect defects on reflecting surfaces. FPGA offers flexibility by employing reconfigurability, furthermore, provides parallelization pipelining improve latency execution time. The performance gain of deflectometry algorithm terms times can be achieved using an architecture based FPGA, proposed this paper....
In our previous works, we have presented methods for optimizing wavelet filter banks, which can be used classification of image objects. The banks were designed to biorthogonal, enables a multiscale analysis on given data. Moreover, the filters optimized with respect shape, helps inherit property This optimization is only possible help so called object curve typical objects each class. contrast works where manually, systematic and automatic design method introduced in this paper. new...
Despite its age the inspection of specular surfaces is still a topic ongoing research. While sensory approaches to inspect such based on deflectometry are increasingly used in practice, evaluation techniques using acquired signals (images and reconstruction results) often not sufficient. This work addresses challenge detecting defects with different characteristics by robust multiscale detection classification. In order process obtained efficiently all relevant scales, method for generating...
The accurate and reliable short-term forecasting of urban water demand plays a crucial role in enabling drinking utilities to operate sustainably secure supplies the future. Here, we apply state-of-the-art DeepAR models predict ten district metered areas (DMAs) distribution system northeastern Italy. are based on long memory networks can directly provide probabilistic results. For this contribution, leverage past flow data, current future weather engineered date features as input data one...
Abstract. In this paper we propose new models of two complementary optical sensors to obtain 2.5-D measurements opaque surfaces: a deflectometric and plenoptic sensor. The sensor uses active triangulation works best on specular surfaces, while the passive textured, diffusely reflecting surfaces. We describe measurement uncertainties for specularly surfaces under consideration typical disturbances like ambient light or vibration. predicted both can be used optimized varying surface properties...
Zusammenfassung Für die Inspektion von spiegelnden Oberflächen ist Deflektometrie eine der bekanntesten Methoden. Eine automatische Defektdetektion, Klassifikation und Bewertung Daten deflektometrischen Messungen gibt es allerdings noch nicht. In diesem Artikel werden neue Methoden basierend auf Wavelet-Analyse vorgestellt, in Lage sind, Fehler unterschiedlichen Skalen zu erkennen. Um Erkennungsrate erhöhen, Filterbänke Hinsicht Eigenschaften gegebener Defektklassen sowie an dominante...
Deflectometry as a technical approach to assessing reflective surfaces has now existed for almost 40 years. Different aspects and variations of the method have been studied in multiple theses research articles, reviews are also becoming available certain subtopics. Still field active development with many unsolved problems, deflectometry encompasses large variety application domains, hardware setup types, processing workflows designed different purposes, spans range from qualitative defect...
Zusammenfassung Die Wahrnehmung lackierter Oberflächen wird sehr stark durch deren Oberflächenrauheiten und -welligkeiten beeinflusst. Betrachtet man die Welligkeiten, dann ist für den visuellen Eindruck nicht nur Ausprägung, sondern auch der Verlauf entscheidend. Lokale Änderungen im können dazu führen, dass solche als „unschön“ wahrgenommen werden. Einschätzung Welligkeit heute in Industrie mit Hilfe verschiedener Messinstrumente durchgeführt. Diese ignorieren dabei meist zweidimensionalen...
The use of image processing is being accelerated over the past years in areas, including artificial intelligence, medical field, remote sensing and microscopic imaging. For 3D reconstruction objects, deflectometry used to collect topographic information surfaces. Due computationally intensive nature algorithm, execution time one challenges faced by deflectometry. In this paper, an extended FPGA based architecture proposed execute improve performance algorithm. whole process consists several...