Ruan Tao, Wei Shikui, Li Jia, Zhao Yao
IEEE Trans Image Process. 2019 Aug;28(8):3873-3884. doi: 10.1109/TIP.2019.2903322. Epub 2019 Mar 8.
To efficiently browse long surveillance videos, the video synopsis technique is often used to rearrange tubes (i.e., tracks of moving objects) along the temporal axis to form a much shorter video. In this process, two key issues need to be addressed, i.e., the minimization of spatial tube collision and the maximization of temporal video condensation. In addition, when a surveillance video comes as a stream, an online algorithm with the capability of dynamically rearranging tubes is also required. Toward this end, this paper proposes a novel graph-based tube rearrangement approach for online video synopsis. The relationships among tubes are modeled with a dynamic graph, whose nodes (i.e., object masks of tubes) and edges (i.e., relationships) can be progressively inserted and updated. Based on this graph, we propose a dynamic graph coloring algorithm to efficiently rearrange all tubes by determining when they should appear. Extensive experimental results show that our approach can condense online surveillance video streams in real time with less tube collision and high compact ratio.
为了高效浏览长时间的监控视频，视频摘要技术经常被用于沿时间轴重新排列轨迹（即移动物体的轨迹）以形成一个短得多的视频。在此过程中，需要解决两个关键问题，即空间轨迹碰撞的最小化和时间视频压缩的最大化。此外，当监控视频以流的形式出现时，还需要一种具有动态重新排列轨迹能力的在线算法。为此，本文提出了一种用于在线视频摘要的基于新颖图形的轨迹重新排列方法。轨迹之间的关系用动态图建模，其节点（即轨迹的对象掩码）和边（即关系）可以逐步插入和更新。基于此图，我们提出了一种动态图着色算法，通过确定轨迹何时出现来有效地重新排列所有轨迹。大量实验结果表明，我们的方法可以实时压缩在线监控视频流，同时具有较少的轨迹碰撞和高紧凑率。
