In this work, we present an integrated system for spatiotemporal
summarization of 360-degrees videos. The video summary production mainly
involves the detection of salient events and their synopsis into a concise
summary. The analysis relies on state-of-the-art methods for saliency detection
in 360-degrees video (ATSal and SST-Sal) and video summarization (CA-SUM). It
also contains a mechanism that classifies a 360-degrees video based on the use
of static or moving camera during recording and decides which saliency
detection method will be used, as well as a 2D video production component that
is responsible to create a conventional 2D video containing the salient events
in the 360-degrees video. Quantitative evaluations using two datasets for
360-degrees video saliency detection (VR-EyeTracking, Sports-360) show the
accuracy and positive impact of the developed decision mechanism, and justify
our choice to use two different methods for detecting the salient events. A
qualitative analysis using content from these datasets, gives further insights
about the functionality of the decision mechanism, shows the pros and cons of
each used saliency detection method and demonstrates the advanced performance
of the trained summarization method against a more conventional approach.

该研究提出了一个综合的系统，用于 360 度视频的时空摘要。该系统通过检测显著事件并将其摘要成简洁的摘要来生成视频摘要。研究使用了最先进的 360 度视频显著性检测和视频摘要方法，并包含了一种根据录制过程中使用的静态或移动摄像机分类 360 度视频并决定使用哪种显著性检测方法的机制，以及一个负责在 360 度视频中创建包含显著事件的传统 2D 视频的二维视频生成组件。通过使用两个 360 度视频显著性检测数据集（VR-EyeTracking、Sports-360）对系统进行定量评估，证明了开发的决策机制的准确性和良好影响，并验证了使用两种不同方法检测显著事件的选择。对这些数据集内容进行定性分析，可以进一步了解决策机制的功能，展示所使用的每种显著性检测方法的优缺点，并展示经过训练的摘要方法对比传统方法的高级性能。

360 度视频的时空摘要集成系统

An Integrated System for Spatio-Temporal Summarization of 360-degrees  Videos

Communications are realized as a result of successive decisions at the
physical layer, from modulation selection to multi-antenna strategy, and each
decision affects the performance of the communication systems. Future
communication systems must include extensive capabilities as they will
encompass a wide variety of devices and applications. Conventional physical
layer decision mechanisms may not meet these requirements, as they are often
based on impractical and oversimplifying assumptions that result in a trade-off
between complexity and efficiency. By leveraging past experiences,
learning-driven designs are promising solutions to present a resilient decision
mechanism and enable rapid response even under exceptional circumstances. The
corresponding design solutions should evolve following the lines of
learning-driven paradigms that offer more autonomy and robustness. This
evolution must take place by considering the facts of real-world systems and
without restraining assumptions. In this paper, the common assumptions in the
physical layer are presented to highlight their discrepancies with practical
systems. As a solution, learning algorithms are examined by considering the
implementation steps and challenges. Furthermore, these issues are discussed
through a real-time case study using software-defined radio nodes to
demonstrate the potential performance improvement. A cyber-physical framework
is presented to incorporate future remedies.

本文介绍了物理层中的典型假设及其与实际系统的差异，并考虑到实现步骤和挑战，系统地讨论了基于学习算法的决策机制设计。此外，通过使用软件定义无线电节点进行实时案例研究，论述了潜在的性能改进和未来措施的物理层的学习驱动框架。