Image Processing Reference
In-Depth Information
This is accomplished by extending various spatial domain approaches to the
temporal domain. Proposed saliency detection methods (with and without using
depth information) are applied on the video to detect salient regions. Finally,
experimental results are shown in order to validate the saliency map quality with
the eye tracking system results. This chapter also deals with the integration of visual
attention models in video compression algorithms. Jointly with the eye tracking
data, this use case provides a validation framework to assess the relevance of
saliency extraction methods.
Chapter 7 is entitled “Dynamic cloud resource migration for efficient 3D video
processing in mobile computing environments”. The chapter presents a dynamic
cloud computing scheme for efficient resource migration and 3D media content
processing in mobile computing environments. It elaborates on location and capac-
ity issues to offload resources from mobile devices due to their processing limita-
tions, towards efficiently manipulating 3D video content. The proposed scheme
adopts a rack-based approach that enables cooperative migration for redundant
resources to be offloaded towards facilitating 3D media content manipulation. The
rack-based approach significantly reduces crash failures that lead all servers to
become unavailable within a rack and enables mobile devices with limited
processing capabilities to reproduce multimedia services at an acceptable level of
Quality of Experience (QoE). The presented scheme is thoroughly evaluated
through simulation tests, where the resource migration policy was used in the
context of cloud rack failures for delay-bounded resource availability of mobile
users.
Chapter 8 is entitled “Cooperative Strategies for End-to-End Energy Saving and
QoS Control”. Energy efficiency and Quality of Service (QoS) have become major
requirements in the research and commercial community to develop green com-
munication technologies for cost-effective and seamless convergence of all services
(e.g. data, 3D media, Haptics, etc.) over the Internet. In particular, efforts in
wireless networks demonstrate that energy saving can be achieved through coop-
erative communication techniques such as multihop communications or coopera-
tive relaying. Game-theoretic techniques are known to enable interactions between
collaborating entities in which each player can dynamically adopt a strategy that
maximises the number of bits successfully transmitted per unit of energy consumed,
contributing to the overall optimisation of the network in a distributed fashion. As
for the core networks, recent findings claimed that resource over-provisioning is
promising since it allows for dynamically booking more resources in advance, and
multiple service requests can be admitted in a network without incurring the
traditional per-flow signalling, while guaranteeing differentiated QoS. Indeed,
heavy control signalling load has recently raised unprecedented concerns due to
the related undue processing overhead in terms of energy, CPU, and memory
consumption. While cooperative communication and resource over-provisioning
have been researched for many years, the former focuses on wireless access and the
latter on the wired core networks only. Therefore, this chapter investigates existing
solutions in these fields and proposes new design approach and guidelines to
integrate both access and core technologies in such a way as to provide a scalable
Search WWH ::




Custom Search