Markos Mentzelopoulos

Key-frame extraction algorithm using entropy difference

The fast evolution of the digital video technology has opened new areas of research. The most important aspect will be to develop algorithms to perform video cataloguing, indexing and retrieval. The basic step is to find a way for video abstraction, as this will help us more for browsing a large set of video data with sufficient content representation. In this paper we present an overview of the current key-frame extraction algorithms. We propose the Entropy-Difference, an algorithm that performs spatial frame segmentation. We present evaluation of the algorithm on several video clips. Quantitative results show that the algorithm is successful in helping annotators automatically identify video key-frames

Active Foreground Region Extraction and Tracking for Sports Video Annotation

Automatic video segmentation plays a vital role in sports videos annotation. This paper presents a fully automatic and computationally efficient algorithm for analysis of sports videos. Various methods of automatic shot boundary detection have been proposed to perform automatic video segmentation. These investigations mainly concentrate on detecting fades and dissolves for fast processing of the entire video scene without providing any additional feedback on object relativity within the shots. The goal of the proposed method is to identify regions that perform certain activities in a scene. The model uses some low-level feature video processing algorithms to extract the shot boundaries from a video scene and to identify dominant colours within these boundaries. An object classification method is used for clustering the seed distributions of the dominant colours to homogeneous regions. Using a simple tracking method a classification of these regions to active or static is performed. The efficiency of the proposed framework is demonstrated over a standard video benchmark with numerous types of sport events and the experimental results show that our algorithm can be used with high accuracy for automatic annotation of active regions for sport videos.

Natural User Interfaces in Volume Visualisation Using Microsoft Kinect

This paper presents the integration of human-machine interaction technologies within a virtual reality environment to allow for real-time manipulation of 3D objects using different gestures. We demonstrate our approach by developing a fully operational, natural user interface (NUI) system, which provides a front-end framework for back-end applications that use more traditional forms of input, such as wear cable sensors attached to the users. The implementation is a user-friendly system that has immense potential in a number of fields, especially in the medical sciences where it would be possible to increase the productivity of surgeons by providing them with easy access to relevant MRI scans.

Human Computer Interaction using gestures for mobile devices and serious games: A review

The Human-Computer Interaction (HCI) with interfaces is an active challenge field in the industry over the past decades and has opened the way to communicate with the means of verbal, hand and body gestures using the latest technologies for a variety of different applications in areas such as video games, training and simulation. However, accurate recognition of gestures is still a challenge. In this paper, we review the basic principles and current methodologies used for collecting the raw gesture data from the user for recognize actions the users perform and the technologies currently used for gesture-HCI in games enterprise. In addition, we present a set of projects from various applications in games industry that are using gestural interaction.

Treasure hunt pervasive games in cultural organisations

This paper introduces an approach of connecting cultural organizations, such as Museums and archaeological sites and enhancing visiting experience in both sites with the use of a treasure hunt game. The paper shows how the treasure hunt game utilizes pervasive technology and connects remotely located groups of users (in a Museum and in an archaeological site) by involving them in a live collaborative activity where one group assists the other to find hidden treasures and discover related information. The paper articulates the educational value of pervasive treasure hunt games. The paper put emphasis on the gamified elements of the system and their role in enhancing the visiting experience and concludes with directions of future work and development.

A dynamic role-playing platform for simulations in legal and political education

One big challenge in deploying games-based learning, is the high cost and specialised skills associated with customised development. In this paper we present a serious games platform that offers tools that allow educators without special programming or artistic skills to dynamically create three dimensional (3D) scenes and verbal and non-verbal interaction with fully embodied conversational agents (ECAs) that can be used to simulate numerous educational scenarios. We present evaluation results based on the use of the platform to create two educational scenarios for politics and law in higher education. We conclude with a discussion of directions for the further work.

Explosive ordinance disposal: motion sensor simulator in nintendo wii

Simulation based games attempt to replicate real life or fiction scenarios for the purposes of learning, training, investigating or predicting results. This paper presents a case study of a simulation based on terrestrial which are primarily used by Explosive Ordinance Disposal Units (E.O.D.) in the investigation and disposal of bomb threats in Nintendo Wii, to examine different methods and techniques of player immersion, adaptation and learning. The paper presents background research that has been conducted for the design and implementation of the E.O.D. simulator. The simulated environment demonstrates its usefulness over a number of real bomb scenarios where player has to actively inspect the environment to locate and dispose of any potential bomb threats in an efficient manner.

Hardware Interfaces for VR Applications: Evaluation on Prototypes

The advancement of recent developments over the VR with the expansion of new Head Mount Displays (H.M.D.) such as Oculus Rift and Morpheus have opened new challenges in the already active research filed of the industry of Human-Computer Interaction (HCI) by exploring new means of communication with the support of the new hardware devices adjustable to body movements and hand position. The paper explores the hardware interactivity and VR H.M.Ds through two games designed to use the latest Oculus Rift SDK technology with alternative methods of hardware communication. A usability evaluation study was conducted with 18 participants and the results presented and discussed.

Adaptive learning in motion analysis with self-organising maps

Growing models have been widely used for clustering or topology learning. Traditionally these models work on stationary environments, grow incrementally and adapt their nodes to a given distribution based on global parameters. In this paper, we present an enhanced unsupervised self-organising network for the modelling of visual objects. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. This model is used to the representation of motion in image sequences by initialising a suitable segmentation. We present experimental results for hands and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product.

Football video annotation based on player motion recognition using enhanced entropy

This paper presents a semi-parametric Algorithm for parsing football video structures. The approach works on a two interleaved based process that closely collaborate towards a common goal. The core part of the proposed method focus perform a fast automatic football video annotation by looking at the enhance entropy variance within a series of shot frames. The entropy is extracted on the Hue parameter from the HSV color system, not as a global feature but in spatial domain to identify regions within a shot that will characterize a certain activity within the shot period. The second part of the algorithm works towards the identification of dominant color regions that could represent players and playfield for further activity recognition. Experimental Results shows that the proposed football video segmentation algorithm performs with high accuracy