Refine
Document Type
- Conference Proceeding (11)
- Article (2)
- Part of a Book (1)
- Report (1)
Has Fulltext
- no (15)
Is part of the Bibliography
- no (15)
Das CameraFramework wurde entwickelt, um mittels Socket-Kommunikation [1] als Middleware zwischen verschiedenen Kamerainstanzen mit eigenen Kameratreibern und Clienten zu fungieren. Über diesen Kommunikationsweg ist es möglich Clienten nicht nur lokal, sondern auch über das Netzwerk mit Kameradaten zu versorgen. Um neue Kameras mit dem Framework nutzen zu können, muss die Implementierung gewissen Regeln folgen, was durch ein vorgegebenes Basis-Interface (abstrakte Basis-Klasse in C++ [2]) fast vollständig sichergestellt ist. Neue Kameras werden zur Laufzeit über dynamische Bibliotheken geladen. Parameter für Kameras sind über ein XML-File [3] einzustellen. Funktionen zur Übergabe von neuen Kameradaten sind implementiert und müssen durch den Entwickler der einzelnen Kamerainterfaces aufgerufen werden.
Die Zuordnung von Kameradaten zum passenden Nutzer übernimmt das Framework. Jeder Clienterhält seinen eigenen konfigurierbaren Ringbuffer [4] um unabhängig von anderen Nutzern und Kameras zu sein. Die Aufgaben des Frameworks sind auf verschiedene Module, wie in Abbildung 1 dargestellt, aufgeteilt.
Practical application of object detection systems, in research or industry, favors highly optimized black box solutions. We show how such a highly optimized system can be further augmented in terms of its reliability with only a minimal increase of computation times, i.e. preserving realtime boundaries. Our solution leaves the initial (HOG-based) detector unchanged and introduces novel concepts of non-linear metrics and fusion of ROIs. In this context we also introduce a novel way of combining feature vectors for mean-shift grouping. We evaluate our approach on a standarized image database with a HOG detector, which is representative for practical applications. Our results show that the amount of false-positive detections can be reduced by a factor of 4 with a negligable complexity increase. Although introduced and applied to a HOG-based system, our approach can easily be adapted for different detectors.
Technical Report
(2016)
This internal report discusses the theoretical and practical aspects of the cluster management framework SimpleHydra, which was developed in order to allow researchers the quick setup of classical small to mid-scale computation clusters while being as lightweight and platform independent as possible. We motivate crucial design choices with a theoretical analysis in the aspect of time and space complexity, furthermore we give a comprehensive introduction regarding the frameworks usage (which includes examples and detailed description of fundamental concepts as well as data structures). In addition to that we illustrate application scenarios with complete source code examples. Furthermore we hope that this document proves valuable not only as a development report but also as a practical manual for SimpleHydra.
We present a novel approach of distributing matrix multiplications among GPU-equipped nodes in a cluster system. In this context we discuss the induced challenges and possible solutions. Additionally we state an algorithm which outperforms optimized GPU BLAS libraries for small matrices. Furthermore we provide a novel theoretical model for distributing algorithms within homogeneous computation systems with multiple hierarchies. In the context of this model we develop an algorithm which can find the optimal distribution parameters for each involved subalgorithm. We provide a detailed analysis of the algorithms space and time complexities and justify its use with a structured evaluation within a small GPU-equipped Beowulf cluster.
Object detection systems which operate on large data streams require an efficient scaling with available computation power. We analyze how the use of tile-images can increase the efficiency (i.e. execution speed) of distributed HOG-based object detectors. Furthermore we discuss the challenges of using our developed algorithms in practical large scale scenarios. We show with a structured evaluation that our approach can provide a speed-up of 30-180 % for existing architectures. Due to the its generic formulation it can be applied to a wide range of HOG-based (or similar) algorithms. In this context we also study the effects of applying our method to an existing detector and discuss a scalable strategy for distributing the computation among nodes in a cluster system.
We present a novel approach of distributing small-to mid-scale neural networks onto modern parallel architectures. In this context we discuss the induced challenges and possible solutions. We provide a detailed theoretical analysis with respect to space and time complexities and reinforce our computation model with evaluations which show a performance gain over state of the art approaches.
In this paper, we describe an efficient method for a fast people re-identification based on models of human clothes. An initial model is estimated during people detection and tracking, which will be refined during the re-identification. This stepwise extraction, combination and comparing of features speeds up the whole re-identification. For the refining, several saliency maps are used to extract individual features. These individual features are located separately for any human body part. The body parts are located with an optimized GPU-based HOG detector. Furthermore, we introduce a meanshift-based fusion concept which utilizes multiple detectors in order to increase the detection reliability.
Ziel des Verbundprojektes APFel (Projektlaufzeit: 01.01.2010 ‐ 31.03.2014)war eine zeitlich vorwärts‐ und rückwärtsgerichtete Lokalisation von Personen innerhalb eines Kameranetzwerkes aus sich nicht überlappenden Kameras in Hyperechtzeit zu ermöglichen. Einsatzbereiche dieses Szenarios sind kritische Infrastrukturen wie Flughäfen und Flugplätze. Zunächst fokussierte das Projekt APFel auf die Lokalisation einer einzelnen Zielperson. Weiterführend wurden die entwickelten Verfahren auf die Analyse von Gruppen erweitert, um Personen als Teil einer Gruppe lokalisieren zu können.
In the context of existing approaches to cluster computing we present a newly developed modular framework `SimpleHydra' for rapid deployment and management of Beowulf clusters. Instead of focusing only the pure computation tasks on homogeneous clusters (i.e. clusters with identically set up nodes), this framework aims to ease the configuration of heterogeneous clusters and to provide a low-level / high-level object-oriented API for low-latency distributed computing. Our framework does not make any restrictions regarding the hardware and minimizes the use of external libraries to the case of special modules. In addition to that our framework enables the user to develop highly dynamic cluster topologies. We describe the framework's general structure as well as time critical elements, give application examples in the `Big-Data' context during a research project and briefly discuss additional features. Furthermore we give a thorough theoretical time/space complexity analysis of our implemented methods and general approaches.