Jan Wieghardt

Wireless local positioning

Local positioning will be one of the most exciting features of the next generation of wireless systems. Completely new concepts and features for wireless data transmission and transponder systems will emerge. Self-organizing sensor networks, ubiquitous computing, location sensitive billing, context dependent information services, tracking and guiding are only some of the numerous possible application areas. This article introduces different concepts of several existing and emerging systems and applications.

Augmented reality navigation systems

The augmented reality (AR) research community has been developing a manifold of ideas and concepts to improve the depiction of virtual objects in a real scene. In contrast, current AR applications require the use of unwieldy equipment which discourages their use. In order to essentially ease the perception of digital information and to naturally interact with the pervasive computing landscape, the required AR equipment has to be seamlessly integrated into the user’s natural environment. Considering this basic principle, this paper proposes the car as an AR apparatus and presents an innovative visualization paradigm for navigation systems that is anticipated to enhance user interaction.

A New Visualization Concept for Navigation Systems

At present, various types of car navigation systems are progressively entering the market. Simultaneously, mobile outdoor navigation systems for pe- destrians and electronic tourist guides are already available on handheld com- puters. Although, the depiction of the geographical information on these appli- ances has increasingly improved during the past years, users are still handicapped having to interpret an abstract metaphor on the navigation display and translate it to their real world. This paper introduces an innovative visual paradigm for (mobile) navigation systems, embodied within an application framework that contributes to the ease of perception of navigation information by its users through mixed reality.

Towards Imitation Learning of Grasping Movements by an Autonomous Robot

Imitation learning holds the promise of robots which need not be programmed but instead can learn by observing a teacher. We present recent efforts being made at our laboratory towards endowing a robot with the capability of learning to imitate human hand gestures. In particular, we are interested in grasping movements. The aim is a robot that learns, e.g., to pick up a cup at its handle by imitating a human teacher grasping it like this. Our main emphasis is on the computer vision techniques for finding and tracking the human teachers grasping fingertips. We present first experiments and discuss limitations of the approach and planned extensions.

Self-Organization in Trafric Networks by Digital Pheromones

Nature often provides excellent patterns for the solution of technical problems and challenges: The principle of swarm intelligence e.g., is imitated by a manifold of optimization algorithms, where organisms mark their local environment in order to indirectly communicate with their conspecifics and to consequently solve complex problems in the collective. Emerging positioning and communication technologies allow extending swarm intelligence to the traffic system. Vehicles equipped with sensors, actuators and wireless communication technology virtually annotate their local environment for indirect communication and therefore form a smart collective with self-organizing capabilities following the example of nature. This paper presents and empirically verifies a decentralized self-organizing traffic flow model using a complex micro simulator capable of simulating real city networks based on authentic data acquisitions.

Learning the Topology of Object Views

A visual representation of an object must meet at least three basic requirements. First, it must allow identification of the object in the presence of slight but unpredictable changes in its visual appearance. Second, it must account for larger changes in appearance due to variations in the objects fundamental degrees of freedom, such as, e.g., changes in pose. And last, any object representation must be derivable from visual input alone, i.e., it must be learnable.We here construct such a representation by deriving transformations between the different views of a given object, so that they can be parameterized in terms of the objects physical degrees of freedom. Our method allows to automatically derive the appearance representations of an object in conjunction with their linear deformation model from example images. These are subsequently used to provide linear charts to the entire appearance manifold of a three-dimensional object. In contrast to approaches aiming at mere dimensionality reduction the local linear charts to the objects appearance manifold are estimated on a strictly local basis avoiding any reference to a metric embedding space to all views. A real understanding of the objects appearance in terms of its physical degrees of freedom is this way learned from single views alone.

Pose-Independent Object Representation by 2-D Views

We here describe a view-based system for the pose-independent representation of objects without making reference to 3-D models. Input to the system is a collection of pictures covering the viewing sphere with no pose information being provided. We merge pictures into a continuous pose-parameterized coverage of the viewing sphere. This can serve as a basis for pose-independent recognition and for the reconstruction of object aspects from arbitrary pose. Our data format for individual pictures has the form of graphs labeled with Gabor jets. The object representation is constructed in two steps. Local aspect representations are formed from clusters of similar views related by point correspondences. Principal component analysis (PCA) furnishes parameters that can be mapped onto pose angles. A global representation is constructed by merging these local aspects.

Finding Faces in Cluttered Still Images with Few Examples

Elastic graph matching and its extension bunch graph matching have proven to be among the best methods for face recognition and the interpretation of facial expressions. We here demonstrate for the first time that, in combination with a simple color template, it is also an excellent means for the localization of faces in cluttered still images. The system does not need extensive learning, all information is extracted from a handful of example face images.

Anomaly detection in self-organizing industrial systems using pathlets

In this paper, we present a novel anomaly detection method which addresses the main challenge of self-organizing industrial systems: the state space explosion. In particular, the flexibility and dynamic nature of such systems result in an exponentially growing number of possible execution plans. To handle this problem, we propose to learn the underlying topology, instead of storing whole paths a work-piece can take through the factory. Therefore, we use the concept of pathlet learning. With it, the topology is represented by a pathlet dictionary, which contains significant sub-paths which have been extracted in a pre-processing step from a training data set. These sub-paths can then be used to evaluate at runtime the incoming trajectories. We show that with this approach we are able to detect both, global anomalous events, like the fail of a production station, as well as single anomalous trajectories, e.g. work-pieces which moves out of the known paths.

Building scalable models for anomaly detection in self-organizing industrial systems

The main challenge for anomaly detection in Self-Organizing Industrial Systems (SOIS) is the high degree of freedom of the system, which causes a state-space explosion. Since the system is free to choose at runtime any solution out of the vast amount of possible ones, to ensure that the production process is optimal at all times, classic anomaly detection techniques can not be used one-to-one in SOISs. For this reason, we already presented in previous work, a novel anomaly detection method, which exploits the idea that many products will share a larger fraction of the production process. Accordingly, it learns at first such recurrent “building blocks” of object movements and represents then incoming movements in relation to these known building blocks. With it, anomalous trajectories and global anomalous events like the omitting of a system component, can be detected. In this paper, we present a new algorithm which extracts such “building blocks” more efficiently. In particular, the new approach scales linear with the number of samples per trajectory, while the existing approach scales quadratic.