Dr.-Ing.

Gruna, Robin

Filters

4 1
Reset filters

Settings
Now showing 1 - 5 of 5
  • Publication
    Real-time multitarget tracking for sensor-based sorting: A new implementation of the auction algorithm for graphics processing units
    ( 2019)
    Maier, Georg
    ;
    Pfaff, F.
    ;
    Wagner, M.
    ;
    Pieper, C.
    ;
    Gruna, Robin
    ;
    Noack, B.
    ;
    Kruggel-Emden, H.
    ;
    Längle, Thomas
    ;
    Hanebeck, U.D.
    ;
    Scherer, V.
    ;
    Beyerer, Jürgen
    Utilizing parallel algorithms is an established way of increasing performance in systems that are bound to real-time restrictions. Sensor-based sorting is a machine vision application for which firm real-time requirements need to be respected in order to reliably remove potentially harmful entities from a material feed. Recently, employing a predictive tracking approach using multitarget tracking in order to decrease the error in the physical separation in optical sorting has been proposed. For implementations that use hard associations between measurements and tracks, a linear assignment problem has to be solved for each frame recorded by a camera. The auction algorithm can be utilized for this purpose, which also has the advantage of being well suited for parallel architectures. In this paper, an improved implementation of this algorithm for a graphics processing unit (GPU) is presented. The resulting algorithm is implemented in both an OpenCL and a CUDA based environment. By using an optimized data structure, the presented algorithm outperforms recently proposed implementations in terms of speed while retaining the quality of output of the algorithm. Furthermore, memory requirements are significantly decreased, which is important for embedded systems. Experimental results are provided for two different GPUs and six datasets. It is shown that the proposed approach is of particular interest for applications dealing with comparatively large problem sizes.
  • Publication
    Application of area-scan sensors in sensor-based sorting
    ( 2018)
    Maier, Georg
    ;
    Pfaff, F.
    ;
    Pieper, C.
    ;
    Gruna, Robin
    ;
    Noack, B.
    ;
    Kruggel-Emden, H.
    ;
    Längle, Thomas
    ;
    Hanebeck, U.D.
    ;
    Wirtz, S.
    ;
    Scherer, V.
    ;
    Beyerer, Jürgen
    In the field of machine vision, sensor-based sorting is an important real-time application that enables the separation of a material feed into different classes. While state-of-the-art systems utilize scanning sensors such as line-scan cameras, advances in sensor technology have made application of area scanning sensors feasible. Provided a sufficiently high frame rate, objects can be observed at multiple points in time. By applying multiobject tracking, information about the objects contained in the material stream can be fused over time. Based on this information, our approach further allows predicting the position of each object for future points in time. While conventional systems typically apply a global, rather simple motion model, our approach includes an individual motion model for each object, which in turn allows estimating the point in time as well as the position when reaching the separation stage. In this contribution, we present results from our collaborative research project and summarize the present advances by discussing the potential of the application of area-scan sensors for sensor-based sorting. Among others, we introduce our simulation-driven approach and present results for physical separation efficiency for simulation-generated data, demonstrate the potential of using motion-based features for material classification and discuss real-time related challenges.
  • Publication
    Motion-based material characterization in sensor-based sorting
    ( 2018)
    Maier, Georg
    ;
    Pfaff, F.
    ;
    Becker, F.
    ;
    Pieper, C.
    ;
    Gruna, Robin
    ;
    Noack, B.
    ;
    Kruggel-Emden, H.
    ;
    Längle, Thomas
    ;
    Hanebeck, U.D.
    ;
    Wirtz, S.
    ;
    Scherer, V.
    ;
    Beyerer, Jürgen
    Für die Sortierung von kohäsiven, granularen Materialien entspricht die sensorgestützte Sortierung dem Stand der Technik. Die Auswahl geeigneter Systemkomponenten, wie etwa Sensorik, Beleuchtung, oder die Realisierung der Datenauswertung, orientiert sich bei der Entwicklung entsprechender Systeme an der konkreten Sortieraufgabe, die es zu lösen gilt. Eine Gemeinsamkeit findet sich im Einsatz scannender Sensoren. Jüngst wurde jedoch der Einsatz von Flächenkameras vorgeschlagen. Durch die Beobachtung von Objekten zu mehreren Zeitpunkten besteht die Möglichkeit, deren Bewegungspfade zu verfolgen. Dies erlaubt eine präzise Schätzung der Position und des Zeitpunkts, zu welchem ein Objekt die Trennstufe des Systems erreicht und hilft somit dabei, den Fehler in der physikalischen Separation zu verringern. In dieser Veröffentlichung wird vorgeschlagen, diese Bewegungsinformation ebenfalls zur Charakterisierung von Materialien zu verwenden. Durch die Ableitung geeigneter Merkmale zeigen wir exemplarisch für eine Klassifikationsaufgabe, dass hierdurch gute Ergebnisse erzielt werden können. Der vorgestellte Ansatz trägt damit zur Verringerung des Erkennungsfehlers in Sortiersystemen bei.
  • Publication
    Improving material characterization in sensor-based sorting by utilizing motion information
    ( 2017)
    Maier, Georg
    ;
    Pfaff, F.
    ;
    Becker, F.
    ;
    Pieper, C.
    ;
    Gruna, Robin
    ;
    Noack, B.
    ;
    Kruggel-Emden, H.
    ;
    Längle, Thomas
    ;
    Hanebeck, U.D.
    ;
    Wirtz, S.
    ;
    Scherer, V.
    ;
    Beyerer, Jürgen
    Sensor-based sorting provides state-of-the-art solutions for sorting of cohesive, granular materials. Systems are tailored to a task at hand, for instance by means of sensors and implementation of data analysis. Conventional systems utilize scanning sensors which do not allow for extraction of motion related information of objects contained in a material feed. Recently, usage of area-scan cameras to overcome this disadvantage has been proposed. Multitarget tracking can then be used in order to accurately estimate the point in time and position at which any object will reach the separation stage. In this paper, utilizing motion information of objects which can be retrieved from multitarget tracking for the purpose of classification is proposed. Results show that corresponding features can significantly increase classification performance and eventually decrease the detection error of a sorting system.
  • Publication
    Real-time motion prediction using the chromatic offset of line scan cameras
    ( 2017)
    Pfaff, F.
    ;
    Maier, Georg
    ;
    Aristov, M.
    ;
    Noack, B.
    ;
    Gruna, Robin
    ;
    Hanebeck, U.
    ;
    Längle, Thomas
    ;
    Beyerer, Jürgen
    ;
    Pieper, C.
    ;
    Kruggel-Emden, H.
    ;
    Wirtz, S.
    ;
    Scherer, V.
    Auf dem heutigen Stand der Technik der optischen Schüttgutsortierung werden Zeilenkameras mit einfachen Annahmen über die Teilchenbewegung kombiniert, um eine Ausschleusung bestimmter Teilchen zu ermöglichen. Kürzlich haben wir einen experimentellen optischen Bandsortierer mit einer Flächenkamera ausgestattet und gezeigt, dass durch das Verfolgen der Teilchen des Schüttguts die Güte der Vorhersagen und somit auch der Ausschleusung verbessert werden kann. In dieser Arbeit nutzen wir den Farbversatz zwischen den Farbkanälen einer Farbzeilenkamera, um in Echtzeit Informationen über die Bewegung der Teilchen abzuleiten. Dieser Ansatz erlaubt es, die Vorhersagen heutiger optischer Bandsortierer zu verbessern, ohne dass deren Hardware dafür angepasst werden muss.