DCVISIGRAPP 2015 Abstracts


Full Papers
Paper Nr: 3
Title:

Fast and Robust Cyclist Detection for Monocular Camera Systems

Authors:

Wei Tian and Martin Lauer

Abstract:

Paper Nr: 4
Title:

Integrating Explicit Knowledge in the Visual Analytics Process - Knowledge-assisted Visual Analytics Methods for Time-oriented Data

Authors:

Markus Wagner

Abstract: In this paper, I describe my thesis project for the integration of explicit knowledge from domain experts into the visual analytics process. As base for the implementation of the research project, I will follow the nested model for visualization design and validation. Additionally, I use a problem-driven approach to study knowledge-assisted visualization systems for time-oriented data in the context of real world problems. At first, my research will focus on the ITsecurity domain where I analyze the needs of malware analysts to support them during their work. Therefore I have currently prepared a problem characterization and abstraction to understand the needs of the domain experts to gain more insight into their workflow. Based on that findings, I am currently working on the design and the implementation of a prototype. Next, I will evaluate these visual analytics methods and finally I will test the generalizability of the knowledgeassisted visual analytics methods in a second domain.

Paper Nr: 6
Title:

Interactive Mobile Data Visualization for Second Screen

Authors:

Kerstin Blumenstein

Abstract: Traditional medial content was consumed with one device at a time. With the increasing simultaneous usage of several different devices like smartphone, tablet, and connected TV new approaches for media consumption are conceivable. One specific instance is a Second Screen scenario where users complement information from unidirectional media broadcasts (i.e. TV) with additional facts from a secondary Internet connected source (e.g. smartphone or tablet). However Second Screen applications are still in its infancy and very little is known on how to properly design them. The focus in the thesis will be on the role of data visualizations and how it can be used in Second Screen application for both sides: for the viewer, allowing interactive access to additional, visual, and personalized information that is not included in the broadcast TV content; but also for the TV stations, in order to get richer data about their audience by providing a direct backchannel. By answering the research questions the complete process of designing and developing interactive data visualization in the context of Second Screen applications for mobile touch devices will be investigated. In addition to several state-of-the-art reports a tested framework, which includes all relevant parts of a Second Screen application (e.g. content creation, synchronization, different types of visualization), and guidelines for designing and developing mobile data visualization for Second Screen applications, which are synchronized with the broadcast, will be developed.

Paper Nr: 7
Title:

Interactive System for Objects Recognition using 3D Camera, Point Cloud Segmentation and Augmented Reality User Interface

Authors:

Matej Nikorovic, Radoslav Gargalik and Zoltan Tomori

Abstract: Depth-sensing cameras are frequently used in computer vision and augmented reality applications as a key component of the point cloud acquisition system as well as a natural user interface tool. We integrated both these functions into the automatic objects recognition system based on the machine learning. Acquired point cloud is segmented by the region growing algorithm exploiting smoothness constraint as a homogeneity criterion. Segmented objects lying on the ground plane are recognized via the supervised machine learning and the corresponding label is is projected near to the object. Natural user interface controls the learning process as well as the mode of operation. System is proper for specific environments like e.g. science center (museum).

Paper Nr: 8
Title:

Monoscopic Automotive Ego-motion Estimation and Cyclist Tracking

Authors:

Johannes Gräter and Martin Lauer

Abstract: