通过全局时空优化实现紧凑的视频摘要。

Compact video synopsis via global spatiotemporal optimization.

机构信息

Computer School of Wuhan University, Hubei 430072, China.

出版信息

IEEE Trans Vis Comput Graph. 2013 Oct;19(10):1664-76. doi: 10.1109/TVCG.2012.176.

DOI:10.1109/TVCG.2012.176

Abstract

Video synopsis aims at providing condensed representations of video data sets that can be easily captured from digital cameras nowadays, especially for daily surveillance videos. Previous work in video synopsis usually moves active objects along the time axis, which inevitably causes collisions among the moving objects if compressed much. In this paper, we propose a novel approach for compact video synopsis using a unified spatiotemporal optimization. Our approach globally shifts moving objects in both spatial and temporal domains, which shifting objects temporally to reduce the length of the video and shifting colliding objects spatially to avoid visible collision artifacts. Furthermore, using a multilevel patch relocation (MPR) method, the moving space of the original video is expanded into a compact background based on environmental content to fit with the shifted objects. The shifted objects are finally composited with the expanded moving space to obtain the high-quality video synopsis, which is more condensed while remaining free of collision artifacts. Our experimental results have shown that the compact video synopsis we produced can be browsed quickly, preserves relative spatiotemporal relationships, and avoids motion collisions.

摘要

视频摘要旨在提供现今可从数码相机轻松获取的视频数据集的浓缩表示形式，特别是对于日常监控视频。以前的视频摘要工作通常沿时间轴移动活动对象，如果压缩太多，这不可避免地会导致对象之间发生碰撞。在本文中，我们提出了一种使用统一的时空优化进行紧凑视频摘要的新方法。我们的方法在空间和时间域全局移动运动对象，通过在时间上移动对象来缩短视频长度，并在空间上移动碰撞对象以避免可见的碰撞伪影。此外，使用多级补丁重定位（MPR）方法，将原始视频的移动空间扩展到基于环境内容的紧凑背景中，以适应移动对象。最后，将移动对象与扩展的移动空间合成，以获得高质量的视频摘要，在保持无碰撞伪影的同时更加紧凑。我们的实验结果表明，我们生成的紧凑视频摘要可以快速浏览，保留相对的时空关系，并且避免运动碰撞。