Dr.-Ing.

Gruna, Robin

Filters

5
Reset filters

Settings
Now showing 1 - 9 of 9
No Thumbnail Available
Publication

Mixture of Experts of Neural Networks and Kalman Filters for Optical Belt Sorting

2022 , Thumm, Jakob , Reith-Braun, Marcel , Pfaff, Florian , Hanebeck, Uwe D. , Flitter, Merle , Maier, Georg , Gruna, Robin , Längle, Thomas , Bauer, Albert , Kruggel-Emden, Harald

In optical sorting of bulk material, the composition of particles may frequently change. State-of-the-art sorting approaches rely on tuning physical models of the particle motion. The aim of this work is to increase the prediction accuracy in complex, fast-changing sorting scenarios with data-driven approaches. We propose two neural network (NN) experts for accurate prediction of a priori known particle types. To handle the large variety of particle types that can occur in real-world sorting scenarios, we introduce a simple but effective mixture of experts approach that combines NNs with hand-crafted motion models. Our new method not only improves the prediction accuracy for bulk material consisting of many particle classes, but also proves to be very adaptive and robust to new particle types.

View
No Thumbnail Available
Publication

Motion-based visual inspection of optically indiscernible defects on the example of hazelnuts

2021 , Maier, Georg , Shevchyk, Anja , Flitter, Merle , Gruna, Robin , Längle, Thomas , Hanebeck, Uwe D. , Beyerer, Jürgen

Automatic quality control has long been an integral part of the processing of food and agricultural products. Visual inspection offers solutions for many issues in this context and can be employed in the form of sensor-based sorting to automatically remove foreign and low quality entities from a product stream. However, these methods are limited to defects that can be made visible by the employed sensor, which usually restricts the system to defects appearing on the surface. An alternative non-visual solution lies in impact-acoustic methods, which do not suffer from this constraint. However, these are strongly limited in terms of material throughput and consequently not suitable for large scale industrial application. In this paper, we present a novel approach that performs inspection based on optically acquired motion data. A high-speed camera captures image sequences of test objects during a transportation process on a chute with a specific structured surface. The trajectory data is then used to classify test objects based on their motion behavior. The approach is evaluated experimentally on the example of distinguishing defect-free hazelnuts from ones that suffer from insect damage. Results show that by merely utilizing the motion data, a recognition rate of up to for undamaged hazelnuts can be achieved. A major advantage of our approach is that it can be integrated in sensor-based sorting systems and is suitable for high throughput applications.

View
No Thumbnail Available
Publication

Numerical modelling of an optical belt sorter using a DEM-CFD approach coupled with particle tracking and comparison with experiments

2018 , Pieper, C. , Pfaff, F. , Maier, Georg , Kruggel-Emden, H. , Wirtz, S. , Noack, B. , Gruna, Robin , Scherer, V. , Hanebeck, U.D. , Längle, Thomas , Beyerer, Jürgen

State-of-the-art optical sorting systems suffer from delays between the particle detection and separation stage, during which the material movement is not accounted for. Commonly line scan cameras, using simple assumptions to predict the future particle movement, are employed. In this study, a novel prediction approach is presented, where an area scan camera records the particle movement over multiple time steps and a tracking algorithm is used to reconstruct the corresponding paths to determine the time and position at which the material reaches the separation stage. In order to assess the benefit of such a model at different operating parameters, an automated optical belt sorter is numerically modelled and coupled with the tracking procedure. The Discrete Element Method (DEM) is used to describe the particle-particle as well as particle-wall interactions, while the air nozzles required for deflecting undesired material fractions are described with Computational Fluid Dynamics (CFD). The accuracy of the employed numerical approach is ensured by comparing the separation results of a predefined sorting task with experimental investigations. The quality of the aforementioned prediction models is compared when utilizing different belt lengths, nozzle activation durations, particle types, sampling frequencies and detection windows. Results show that the numerical model of the optical belt sorter is able to accurately describe the sorting system and is suitable for detailed investigation of various operational parameters. The proposed tracking prediction model was found to be superior to the common line scan camera method in all investigated scenarios. Its advantage is especially profound when difficult sorting conditions, e.g. short conveyor belt lengths or uncooperative moving bulk solids, apply.

View
No Thumbnail Available
Publication

Experimental Evaluation of a Novel Sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking

2021 , Maier, Georg , Pfaff, Florian , Pieper, Christoph , Gruna, Robin , Noack, Benjamin , Kruggel-Emden, Harald , Längle, Thomas , Hanebeck, Uwe D. , Wirtz, Siegmar , Scherer, Viktor , Beyerer, Jürgen

Sensor-based sorting is a machine vision application that has found industrial application in various fields. An accept-or-reject task is executed by separating a material stream into two fractions. Current systems use line-scanning sensors, which is convenient as the material is perceived during transportation. However, line-scanning sensors yield a single observation of each object and no information about their movement. Due to a delay between localization and separation, assumptions regarding the location and point in time for separation need to be made based on the prior localization. Hence, it is necessary to ensure that all objects are transported at uniform velocities. This is often a complex and costly solution. In this paper, we propose a new method for reliably separating particles at non-uniform velocities. The problem is transferred from a mechanical to an algorithmic level. Our novel advanced image processing approach includes equipping the sorter with an area-scan camera in combination with a real-time multiobject tracking system, which enables predictions of the location of individual objects for separation. For the experimental validation of our approach, we present a modular sorting system, which allows comparing sorting results using a line-scan and area-scan camera. Results show that our approach performs reliable separation and hence increases sorting efficiency.

View
No Thumbnail Available
Publication

From Visual Spectrum to Millimeter Wave: A Broad Spectrum of Solutions for Food Inspection

2020 , Becker, Florian , Schwabig, Christopher , Krause, Julius , Leuchs, Sven , Krebs, Christian , Gruna, Robin , Kuter, Andries , Längle, Thomas , Nußler, Dirk , Beyerer, Jürgen

The consequences of food adulteration can be far reaching. In the past, inexpensive adulterants were used to inflate different products, leading to severe health issues. Contamination of food has many causes and can be physical(plant stems in tea), chemical (melamine in infant formula), or biological (bacterial contamination). Employing suitable sensor systems along the production process is a requirement for food safety. In this article, different approaches to food inspection are illustrated, and exemplary scenarios outline the potential of different sensor systems along the spectrum.

View
No Thumbnail Available
Publication

Numerical investigation of optical sorting using the discrete element method

2017 , Pieper, C. , Kruggel-Emden, H. , Wirtz, S. , Scherer, V. , Pfaff, F. , Noack, B. , Hanebeck, U.D. , Maier, Georg , Gruna, Robin , Längle, Thomas , Beyerer, Jürgen

Automated optical sorting systems are important devices in the growing field of bulk solids handling. The initial sorter calibration and the precise optical sorting of many materials is still very time consuming and difficult. A numerical model of an automated optical belt sorter is presented in this study. The sorter and particle interaction is described with the Discrete Element Method (DEM) while the separation phase is considered in a post processing step. Different operating parameters and their influence on sorting quality are investigated. In addition, two models for detecting and predicting the particle movement between the detection point and the separation step are presented and compared, namely a conventional line scan camera model and a new approach combining an area scan camera model with particle tracking.

View
No Thumbnail Available
Publication

SmartSpectrometer - Embedded Optical Spectroscopy for Applications in Agriculture and Industry

2021 , Krause, Julius , Grüger, Heinrich , Gebauer, Lucie , Zheng, Xiaorong , Knobbe, Jens , Pügner, Tino , Kicherer, Anna , Gruna, Robin , Längle, Thomas , Beyerer, Jürgen

The ongoing digitization of industry and agriculture can benefit significantly from optical spectroscopy. In many cases, optical spectroscopy enables the estimation of properties such as substance concentrations and compositions. Spectral data can be acquired and evaluated in real time, and the results can be integrated directly into process and automation units, saving resources and costs. Multivariate data analysis is needed to integrate optical spectrometers as sensors. Therefore, a spectrometer with integrated artificial intelligence (AI) called SmartSpectrometer and its interface is presented. The advantages of the SmartSpectrometer are exemplified by its integration into a harvesting vehicle, where quality is determined by predicting sugar and acid in grapes in the field.

View
No Thumbnail Available
Patent

Verfahren und Vorrichtung zur Bestimmung zumindest einer mechanischen Eigenschaft zumindest eines Objektes

2019 , Gruna, Robin , Hanebeck, Uwe , Längle, Thomas , Maier, Georg , Noack, Benjamin , Pfaff, Florian

Die Erfindung betrifft ein Verfahren und eine Vorrichtung zum Bestimmen zumindest einer mechanischen Eigenschaft zumindest eines Objektes, wobei das zumindest eine Objekt zumindest einer Wechselwirkung unterworfen wird, die einen Bewegungszustand des zumindest einen Objektes beeinflusst,wobei die zumindest eine Wechselwirkung so gewählt ist, dass der durch die Wechselwirkung bewirkte Bewegungszustand eine Funktion der zumindest einen mechanischen Eigenschaft ist,wobei das zumindest eine Objekt mit zumindest einer Kamera beobachtet wird,wobei aus von der zumindest einen Kamera aufgenommenen Bildern der Bewegungszustand bestimmt wirdund wobei aus dem so bestimmten Bewegungszustand die zumindest eine mechanische Eigenschaft des zumindest einen Objektes bestimmt wird.

View
No Thumbnail Available
Publication

Feature selection with a budget

2016 , Richter, M. , Maier, Georg , Gruna, Robin , Längle, Thomas , Beyerer, Jürgen

Feature selection is an important step in all practical applications of pattern recognition. As such, it is not surprising that during the past decades it has received a lot of attention from the research community. The topic is well understood and many methods have been put to the test. Most methods, however, overlook an aspect critical to real-time applications: limited computation time. The set of selected features must not only be suitable to solve the task, but must also ensure that the task can be solved within the available time. With this in mind, we propose a method for feature selection with a budget. We approach the problem by stating feature selection as a multi-objective optimization problem. This problem is solved using the well known NSGA-II algorithm. We evaluate our approach using one synthetic and two real-world datasets. We explore the properties of the genetic algorithm and investigate the classification performance of the resulting selections. Our results show that the selected feature sets are highly suitable, especially when considering real-time systems.

View