004 Informatik
Refine
Document Type
- Conference Proceeding (6)
- Article (1)
- Report (1)
Has Fulltext
- no (8)
Is part of the Bibliography
- no (8) (remove)
Institute
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.
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 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 a method to model human clothes for a later recognition by the use of RGB- and SWIR-cameras. A basic model is estimated during people detection and tracking. This model will be refined if the recognition is triggered. For the refining, several saliency maps are used to extract individual features. These individual features are located separately for any human body parts. The body parts are estimated by the use of a silhouette extraction combined with a skeleton estimation. In this way, the model describes the human clothes in a compact manner which allows the use of a simple and fast comparison method for people recognition. Such models can be used in security and service applications.
The neuronal basis of movement preparation, during which movement parameters such as movement direction are assigned values, is fairly well understood (Georgopoulos, 2000). Motor and premotor cortex as well as portions of the parietal cortex represent movement parameters through the activity of neuronal populations (Bastian et al., 2003; Cisek & Kalaska, 2005).
The parameter representation is of dynamic nature, updated in the course of movement. It adapts to boundary conditions of the motion plan or to environmental changes. Schwartz (2004) was able to decode motor cortical activity in the motor cortex and utilized this knowledge to drive a virtual or robotic end-effector. Thus he proved that the motor cortex is involved in the generation of movement planning. At this level of abstraction we assume that the movement of an end-effector, as well as human walking movement, is represented appropriately by its direction and satisfies other constraints, such as obstacle avoidance or movement coordination.
A neuronal dynamic of movement generates goal-directed movements and satisfies other constraints, such as obstacle avoidance. Movement is generated by choosing low-dimensional, behaviorally relevant state variables. Behavioral goals are represented as attractors of dynamical systems over such behavioral variables (Schöner et al., 1995). The robots trajectory emerges as a solution of these dynamical systems, in which the behavioral variables are stabilized at attractors corresponding to behavioral goals. Constraints are included in a similar manner as repellers. Recently we applied this approach to generate reaching movements for manipulators under obstacle avoidance and orientation con- straints (Iossifidis & Schöner, 2009; Reimann et al., 2010a,b).
We aim to develop an approach to robotic action based on dynamical systems 1
that is quantitatively modeled on human behavior. By varying the intrinsic parameters obtained for different individuals we will be able to implement different personal styles of movement. In this contribution we implement the neuronal dynamics of movement on a humanoid robotic system which generates goal-directed walking movements while avoiding obstacles.
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.