Detection of events and actions in video entails substantial processing of very large, even open-ended, video streams. Video data presents a unique challenge for the information retrieval community because properly representing video events is challenging. We propose a novel approach to analyze temporal aspects of video data. We consider video data as a sequence of images that form a 3-dimensional spatiotemporal structure, and perform multiview orthographic projection to transform the video data into 2-dimensional representations. The projected views allow a unique way to rep- resent video events and capture the temporal aspect of video data. We extract local salient points from 2D projection views and perform detection-via-similarity approach on a wide range of events against real-world surveillance data. We demonstrate our example-based detection framework is competitive and robust. We also investigate the synthetic example driven retrieval as a basis for query-by-example.

Theses (M.A.(Media Studies)) --University of Limpopo, 2014 / The purpose of this study was to outline the effects of violent films and video games on children in Giyani. The study used both qualitative and quantitative methods. Data collection was done using three methods, namely: structured questionnaires, interviews and observations. Participants for this study were sixty (60) children from four selected villages, namely Ndhambhi, Mageva , Bambeni and nwamarhanga. Twenty (20) parents from the same villages were also selected. Films and video games remain the source of entertainment for media consumers although they have effects. Such effects may be seen through long and short time exposures. There are positive and negative effects of media violence exposure. The effectiveness of effects on children may be determined by several factors such as: cognitive development of one’s mind, time spent consuming violent films and video games, age and interpretation attached to messages portrayed by the media. The findings reveal that children’s perceptions of the reality may be affected by media violence. Furthermore, parents do not always monitor what their children consume on daily basis. Repeated exposure of violence on children might result in aggressiveness and the syndrome world effects. Children should be taught about the importance of age restrictions and television guidelines.

Video game addiction often leads to a tremendous burden on those afflicted with the condition, draining their time, resources, and life away until they have nothing left. To further elucidate the problem of video game addiction, the current research examines the level of video game addiction of 111 participants, along with their motivation for their addictive behaviors, the quality of life of addicted individuals, and possible relations between video game addiction and other forms of addiction. Results of the current research indicate a correlation between addictive video game use and depression, alcohol use, a desire for escapism, a need for social interaction, and lack of self-control. The results of a multiple regression indicate that, amongst the various research factors, depression is the factor with the most significant link to addictive video game use, implying a dangerous correlation between mental health and an addictive behavior that some erroneously disqualify as a true addiction.

Video games as an entertainment form are very popular. Understanding what video games do to us in a long-term and short-term manner is therefore of interest. Attention is a widely studied field and research into how attentional networks are affected by video is a research field on the rise. Here, I will be investigating how video game play affects our attentional networks and if it is possible for elderly individuals to train their attentional networks with video games. Video game players have high performance in reaction time and accuracy in different attentional, working memory, and cognitive control tasks. As the difficulty of video games increase video game players seem to more efficiently utilize their attentional networks. Whilst some articles cannot replicate findings in other articles this irregularity might be explained with by level of difficulty or load during task performance. Studies see group differences only when the task difficulty is high. Therefore, an important part of video game research is to find an effective and replicable standard for video game research. Measuring video game play with EEG shows that players better can forgo distracting stimuli in central and peripheral view and discriminating stimuli giving video game players more confidence when making decisions. Video game players also seem to have more efficient processes and functional connectivity in attentional networks but utilizing these networks more as non-video game players as mental load increases. Not only does video game players have more efficient attentional networks, but attentional benefits from video games is also something that can be trained with those who do not play video games. Suggesting that older individuals can utilize video games to train attentional networks.

Au cours de cette dernière dizaine d’années, l’intérêt pour la diffusion en temps réel de séquences vidéo sur réseaux sans fil ad-hoc a grandi sans cesse, en raison de l'attrayante propriété d’être capable de déployer un système de communication visuelle à tout moment et en tout lieu, sans la nécessité d'une infrastructure préexistante. Une large gamme d'applications des opérations militaires et de sauvetage, jusqu'aux applications commerciales, éducatives, récréatives, a été envisagée, ce qui a crée un grand intérêt pour toutes les technologies concernées. L'objectif de cette thèse est de fournir un service efficace et robuste de diffusion vidéo en temps réel sur réseaux mobiles ad-hoc, avec un aperçu des solutions disponibles à ce moment, et de proposer de nouvelles solutions qui permettraient de surmonter les limites de celles actuelles. Nos contributions touchent à plusieurs aspects du paradigme mobile vidéo streaming : une nouvelle technique de codage vidéo par descriptions multiples, qui fournit une qualité vidéo acceptable, même en présence d'un taux élevé de pertes ; un protocole cross-layer pour la création et le maintien d'un réseau de overlay, qui, avec un échange de messages limité, géré de façon repartie un ensemble d'arbres de multicast, un pour chaque description du flux ; un cadre original de fonctions distribuées pour l'optimisation congestion-distorsion, qui, grâce à une représentation compacte des informations de topologie, permet aux nœuds d'apprendre la structure du overlay et d'optimiser leur comportement en conséquence ; et enfin, une intégration avec le paradigme émergent du codage réseau. / During the last decade, real-time video streaming over ad-hoc networks has gathered an increasing interest, because of the attractive property of being able to deploy a visual communication system anytime and anywhere, without the need for a pre-existing infrastructure. A wide range of target applications, from military and rescue operations, to business, educational, and recreational scenarios, has been envisaged, which has created great expectations with respect to the involved technologies. The goal of this thesis is to provide an efficient and robust real-time video streaming system over mobile ad-hoc networks, proposing cross-layer solutions that overcome the limitations of both the application and network solutions available at this time. Our contributions cover several aspects of the mobile video streaming paradigm: a new multiple description video coding technique, which provides an acceptable video quality even in presence of high loss rates; a novel cross-layer design for an overlay creation and maintenance protocol, which, with a low overhead, distributedly manages a set of multicast trees, one for each description of the stream; an original distributed congestion-distortion optimisation framework, which, through a compact representation of the topology information, enables the nodes to learn the structure of the overlay and optimise their behaviour accordingly; and, finally, an integration with the emerging network coding paradigm.

Le codage de source distribué est un paradigme qui consiste à encoder indépendamment deux sources corrélées et à les décoder conjointement. Wyner et Ziv ont montré que le codage de source distribué peut atteindre les mêmes performances débit-distorsion que le codage de source conjoint, pourvu que certaines contraintes soient satisfaites. Cette caractéristique rend le codage de source distribué très attractif pour des applications qui demandent un encodeur à faible complexité ou pour ne pas être obligé à avoir des communications entre les sources. Dans le cadre du codage vidéo distribué, les trames corrélées sont encodées séparément et décodées conjointement. Dans l'architecture ainsi dite de Stanford, le flux vidéo est séparée en trames clés et Wyner-Ziv. Les trames clés sont encodées INTRA. Les trames Wyner-Ziv sont données en entrée à un codeur de canal systématique ; seulement les bits de parité sont envoyés. Au décodeur, on produit une estimation de la trame Wyner-Ziv, appelée information adjacente, en interpolant les trames clés reçues. L'information adjacente, considérée comme une version bruitée de la trame Wyner-Ziv, est corrigée par les bits de parité. Dans cette thèse, nous proposons plusieurs algorithmes pour la génération de l'information adjacente et pour l'interpolation temporelle et inter-vue. On propose aussi un algorithme de fusion bayésienne des deux interpolations. Tous les algorithmes proposés donnent des résultats meilleurs par rapport à l'état de l'art en termes de performance débit-distorsion. Nous proposons aussi plusieurs algorithmes pour l'estimation de la trame Wyner-Ziv dans le cadre de la vidéo multi-vues plus profondeur. / Distributed source coding is a paradigm that consists in encoding two correlated sources independently, provided that they are decoded jointly.Wyner and Ziv proved that distributed source coding can attain the same rate distortion performance of joint coding, under some constraints.This feature makes distributed source coding very attractive for applications that require a low-complexity encoder or for avoiding communication between the sources. In distributed video coding, correlated frames are encoded separately but decoded jointly. In the Stanford Architecture, the video is split into Key Frames and Wyner-Ziv Frames. The Key Frames are INTRA coded. The Wyner-Ziv Frames are fed into a systematic channel coder and only the parity bits are sent to the decoder. At the decoder side, an estimation of the Wyner-Ziv Frame, called side information, is produced by interpolating the available frames. The side information, that can be considered as a noisy version of the real Wyner-Ziv Frame, is corrected by the parity bits sent by the encoder. In this thesis, we propose several algorithms for side information generation both for the temporal and inter-view interpolation. We also propose a Bayesian fusion of the two estimations. All our algorithms outperform the state-of-the-art in terms of rate distortion performance. We also propose several algorithms for Wyner-Ziv estimation in the context of multiview video plus depth.

Instalation which explore possibilities of visual language and poetry.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第17919号 / 情博第501号 / 新制||情||89(附属図書館) / 30739 / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 松山 隆司, 教授 美濃 導彦, 教授 中村 裕一 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

No description available.

By observing human driving with a “digital head" (combined video camera and accelerometers) and taking a few hand annotations, we can automatically annotate regions in a robot's field of view that should be interpreted as obstacles to be avoided. This is accomplished by detecting the movement for a given frame in a video. Some hand annotations of video frames are necessary and they are used to create Probability Grids. Using the movement data and the Probability Grids, it is possible to annotate large amounts of video data quickly in an automated system.