PoCA 2011 – 2nd International Conference on
Positioning and Context-Awareness
Thursday 24 March 2011 – Brussels, Belgium
Menu
Accepted Papers
The following papers are expected to be presented at PoCA 2011. By clicking on a title, you can view the paper abstract.
-
Christian Beder and Martin Klepal
Abstract: Localisation systems will become more and more an important tool for a variety of applications ranging from personalised location based services to controlling large-scale infrastructures. Although singular localisation systems limit their use to a limited number of environments, scenarios, and data sources, the diverse applicability of localisation systems and environments requires a hybrid combination of different technologies. However, fusing information from multiple different sources requires the assessment of the quality of the obtained data to calibrate the data fusion and obtain optimal fusion results. In this paper we will present a method for assessing the quality of location data received from multiple sources based on a simple motion model. This assessment enables the calibration of subsequent fusion algorithms allowing to optimally combine heterogeneous technologies into a seamless application. We will demonstrate the approach for a combination of GPS, LPR, Wi-Fi, UWB and RFID systems in a combined indoor and outdoor environment.
-
Thorsten Edelhäußer, Michael Philippsen and Christopher Mutschler
Abstract: The traditional representation of object trajectories as spatio-temporal data is not suitable for all applications. We present a trajectory representation called Trajectory Behavior Language (TBL) for three dimensional data that better fits trajectory comparison or analyzing the behavior of moving objects. Our representation is based on a Chomsky-2 formal language and can be generated online. We explain the grammar and present an algorithm for translating spatio-temporal data into the novel representation at runtime. This presented algorithm only needs one sample per time step and introduces no latency. Further, we present a sliding window based online TBL-to-TBL transformation that combines repeated elements of a trajectory, expresses them with additional grammar elements, and thus increases the readability and further compresses a trajectory. On a benchmark, we achieve a compression rate of 66.5%.
-
Tom Heyman, Vincent Spruyt and Alessandro Ledda
Abstract: Estimating a user's gaze direction, one of the main novel user interaction technologies, will eventually be used for numerous applications where current methods are becoming less effective. In this paper, a new method is presented for estimating the gaze direction using Canonical Correlation Analysis (CCA), which finds a linear relationship between two datasets defining the face pose and the corresponding facial appearance changes. Afterwards, iris tracking is performed by blob detection using a 4-connected component labeling algorithm. Finally, a gaze vector is calculated based on gathered eye properties. Results obtained from datasets and real-time input confirm the robustness of this method.
-
Christopher Mutschler, Gabriella Kokai and Thorsten Edelhäußer
Abstract: In sports, especially soccer and other ball-sports, the interaction between trajectories of players take a major role in purposes of game analysis. Existing approaches follow the way of mining spatio-temporal, sequential patterns or spatial patterns, but do not incorporate interactions between multiple, interactive trajectories. This paper proposes an online data mining method that is able to recognize repeating patterns of trajectory movements regardless of how they are scaled, rotated or translated. The result is an efficient data stream mining application, which provides meaningful information within the actual game. The framework is designed in a modular manner in order to enhance the capabilities easily. The evaluation of the algorithms proves the efficiency of the provided concepts.
-
Wim Van Looy, Kris Cuppens and Bart Vanrumste
Abstract: In this paper we investigate whether it is possible to detect movement out of video images recorded from sleeping patients with epilepsy. This information is used to detect possible epileptic seizures, normal movement, breathing and other kinds of movement. For this we use optical flow and clustering algorithms. As a result, different motion patterns can be extracted out of the clustered body parts.
-
Jeroen Wyffels, Henk Motte, Lieven De Strycker, Jean-Pierre Goemaere and Bart Nauwelaers
Abstract: This paper describes a system for improving indoor localization by means of a ZigBee network, by adding extra information to the ZigBee localization engine. Typically, only RSS Received Signal Strength) values are used in the ZigBee network while performing indoor localization. In this research, we add a Pedestrian Dead Reckoning device (PDR) to the ZigBee mobile node. This PDR device uses extra sensors such as a compass and a step detection mechanism (accelerometer) in order to provide extra localization information. The localization capabilities of the combined ZigBee and PDR system are evaluated in an indoor environment and put to the test in an indoor/outdoor field case in which the system proved to be very useful.
-
Matthias Schneider and Ralf Salomon
Abstract: Many everyday life activities require precise localization information. Navigation by means of the global positioning system (GPS) is a well-know example. Despite its broad usage, this localization method cannot be utilized in all application areas. Logistics, factory and laboratory automation, as well as warehouse management, for example, require the low-cost localization of various objects with a precision of a few centimeters, particularly in indoor environments. For this application domain, this paper proposes a new procedure to measures the relatively distance difference between two points (e.g., two transmitters) to a third point (e.g., a receiver) with a low resource complexity. The procedure based on the superposition of a particularly parametrized beats whereby the carrier phase difference can be directly read. In additional, this paper also present a preliminary theoretical analysis as well as some laboratory experiments.
-
Peter Van Hese, Sebastian Gruenwedel, Vedran Jelaca, Jorge Nino and Wilfried Philips
Abstract: An occupancy map provides a top view of a scene and can be used for monitoring the activity of people. We estimate occupancy maps using foreground silhouettes from multiple camera views. The ground occupancies computed from each view are fused in a Dempster-Shafer framework. However, it is not clear which background/foreground segmentation method for deriving the silhouettes is most suited for estimating our occupancy maps. We evaluated three segmentation methods from literature (Vibe, Mixture of Gaussians, method by Petrovic et al.), and one new segmentation method based on the analysis of edges. Occupancy maps were calculated for the APIDIS dataset, and the obtained maps were evaluated using the players' ground truth positions. We found that all methods perform similar in terms of the accuracy of the estimated maps, except the edges based segmentation method which outperforms all other methods. Future work will include texture based segmentation methods, and will focus on robustness with regard to lighting changes.
-
Maarten Weyn, Martin Klepal, Sylvie Couronee, Glenn Ergeerts and Mark Fassbinder
Abstract: Localisation systems will become more and more an important tool for controlling large-scale infrastructures. Although singular localisation systems limit their use to a limited number of environments and scenarios, the diverse applicability of localisation systems and environments requires a hybrid combination of different technologies. In this paper we combine GPS, LPR, Wi-Fi, UWB and RFID systems in a test bed and we describe the necessity of a standardised data protocol. We evaluate the architecture of the fusion of different indoor and outdoor systems. The study showed that the systems can improve and complement each other while overcoming gaps and shortcomings in applicability of individual systems.