Selim Balcisoy

Computer and information sciences-ISCIS 2006

This book constitutes the refereed proceedings of the 21st International Symposium on Computer and Information Sciences, ISCIS 2006, held in Istanbul, Turkey in October 2006. The 106 revised full papers presented together with 5 invited lectures were carefully reviewed and selected from 606 submissions. The papers are organized in topical sections on algorithms and theory, bioinformatics, computational intelligence, computer architecture, computer graphics, computer networks, computer vision, data mining, databases, embedded systems, information retrieval, mobile computing, parallel and distributed computing, performance evaluation, security and cryptography, as well as software engineering.

Augmented reality for real and virtual humans

Current virtual reality technologies provide many ways to interact with virtual humans. Most of those techniques, however, are limited to synthetic elements and require cumbersome sensors. We have combined a real-time simulation and rendering platform with a real-time, non-invasive vision-based recognition system to investigate interactions in a mixed environment with real and synthetic elements. In this paper, we present the resulting system, the example of a checkers game between a real person and an autonomous virtual human to demonstrate its performance.

Designing Progressive and Interactive Analytics Processes for High-Dimensional Data Analysis

In interactive data analysis processes, the dialogue between the human and the computer is the enabling mechanism that can lead to actionable observations about the phenomena being investigated. It is of paramount importance that this dialogue is not interrupted by slow computational mechanisms that do not consider any known temporal human-computer interaction characteristics that prioritize the perceptual and cognitive capabilities of the users. In cases where the analysis involves an integrated computational method, for instance to reduce the dimensionality of the data or to perform clustering, such non-optimal processes are often likely. To remedy this, progressive computations, where results are iteratively improved, are getting increasing interest in visual analytics. In this paper, we present techniques and design considerations to incorporate progressive methods within interactive analysis processes that involve high-dimensional data. We define methodologies to facilitate processes that adhere to the perceptual characteristics of users and describe how online algorithms can be incorporated within these. A set of design recommendations and according methods to support analysts in accomplishing high-dimensional data analysis tasks are then presented. Our arguments and decisions here are informed by observations gathered over a series of analysis sessions with analysts from finance. We document observations and recommendations from this study and present evidence on how our approach contribute to the efficiency and productivity of interactive visual analysis sessions involving high-dimensional data.

Integrating Information Theory in Agent-Based Crowd Simulation Behavior Models

Crowds must be simulated believable in terms of their appearance and behavior to improve a virtual environments realism. Due to the complex nature of human behavior, realistic behavior of agents in crowd simulations is still a challenging problem. In this paper, we propose a novel behavioral model which builds analytical maps to control agents’ behavior adaptively with agent–crowd interaction formulations. We introduce information theoretical concepts to construct analytical maps automatically. Our model can be integrated into crowd simulators and enhance their behavioral complexity. We made comparative analyses of the presented behavior model with measured crowd data and two agent-based crowd simulators.

An information theoretic approach to camera control for crowded scenes

Navigation and monitoring of large and crowded virtual environments is a challenging task and requires intuitive camera control techniques to assist users. In this paper, we present a novel automatic camera control technique providing a scene analysis framework based on information theory. The developed framework contains a probabilistic model of the scene to build entropy and expectancy maps. These maps are utilized to find interest points which represent either characteristic behaviors of the crowd or novel events occurring in the scene. After an interest point is chosen, the camera is updated accordingly to display this point. We tested our model in a crowd simulation environment and it performed successfully. Our method can be integrated into existent camera control modules in computer games, crowd simulations and movie pre-visualization applications.

Real-time interactions with virtual agents driven by human action identification

The authors evaluate a multi-level action recognition algorithm for behavioral interactions in inhabited virtual worlds

VEA 2012: Automatic path generation for terrain navigation

Navigation in 3D terrain is considered to be a challenging task and requires virtual camera control skills such as zooming, panning and tilting. Novice users can easily get distracted and disorientated which may result in being lost in space. Solutions for the virtual environment exploration problems are still being researched in order to assist users during their journey inside virtual environments. Among these solutions, assisted camera control techniques require viewpoint computation and path planning. This paper introduces a novel approach to navigate over a 3D terrain using best viewpoints. We exploit the concept of Viewpoint Entropy for best view determination and use Greedy N-Best View Selection for visibility calculations. We integrate road network data to extract regions for detailed visibility analysis in subsections of the terrain. In order to connect the calculated viewpoints, we use an evolutionary programming approach for the Traveling Salesman problem. We present the generated tour using a Google Earth framework. The computed and planned viewpoints in our solution reduce human effort when used as starting points for scene exploration or to generate the representative images of the terrain dataset. The proposed framework can be integrated into 3D game engines or urban visualization systems. This integration gives quickly a glimpse or tour of the environment for novice users without the help of prior planning. Furthermore, terrain visibility used together with road network data and an optimization method for final path construction allows the computed path to be used for large urban area reconnaissance and surveillance tasks with aerial vehicles.

Representational image generation for 3D objects

Finding good representational images for 3D object exploration is a highly subjective problem in the cognitive field. The “best” or “good” definitions do not depend on any metric. We have explained the VKL distance concept and introduced a novel view descriptor called vSKL distance for finding “good” representational images. The image generation is done by projecting the surfaces of 3D objects onto the screen or any planar surface. The projection process depends on parameters such as camera position, camera vector, up vector, and clipping plane positions. In this work we present a technique to find such camera positions that the 3D object is projected in “good” or “best” way where those subjective definitions are mapped to Information Theoretical distances. We compared greedy view selection integrated vSKL with two well known techniques: VKL and VMI. vSKL performs very close to the other two, hence face coverage perturbation is minimal, but it is 3 to 4 times faster. Furthermore, the saliency information is conveyed to users with generated images.

Entropy Based Sensitivity Analysis and Visualization of Social Networks

This paper introduces a technique to analyze and visualize social networks using Shannons entropy model. Entropy is exploited to measure the information amount in social network graphs, and to conduct sensitivity analyses. Novel measures such as degree, betweenness and closeness entropies are evaluated to find the change in graph entropy or the actors. In this work we present a visualization approach that uses coloring, sizing and filtering to help the users perceive the communicated information. The result of sensitivity analyses is integrated into the visualization using the change amount caused by the actors as information. The main contribution of this study is a visualization where the information communicated from a social network is enhanced by the help of sensitivity analyses.

Hybrid participant embodiments in networked collaborative virtual environments

The authors present a novel approach to participant embodiment in networked collaborative virtual environments. The embodiment approach integrates live video into 3D objects for a hybrid participant representation. They implemented their ideas in a Networked Collaborative Virtual Environment system, VLNET and investigated network and rendering issues in comparison with virtual human participant embodiment. The paper presents two distinct case studies demonstrating their ideas. The first one is a tele-teaching application, in which they investigate a shared environment with virtual humans and hybrid embodiments. The second one presents a distributed augmented reality application, in which participants share a mixed environment with real and virtual elements.