Supervoxel segmentation algorithm has been applied as a preprocessing step for many vision tasks. However, existing supervoxel segmentation algorithms cannot generate hierarchical supervoxel segmentation well preserving the spatiotemporal boundaries in real time, which prevents the downstream applications from accurate and efficient processing. In this paper, we propose a real-time hierarchical supervoxel segmentation algorithm based on the minimum spanning tree (MST), which achieves state-of-the-art accuracy meanwhile at least $11\times $ faster than existing methods. In particular, we present a dynamic graph updating operation into the iterative construction process of the MST, which can geometrically decrease the numbers of vertices and edges. In this way, the proposed method is able to generate arbitrary scales of supervoxels on the fly. We prove the efficiency of our algorithm that can produce hierarchical supervoxels in the time complexity of $O(n)$ , where $n$ denotes the number of voxels in the input video. Quantitative and qualitative evaluations on public benchmarks demonstrate that our proposed algorithm significantly outperforms the state-of-the-art algorithms in terms of supervoxel segmentation accuracy and computational efficiency. Furthermore, we demonstrate the effectiveness of the proposed method on a downstream application of video object segmentation.

中文翻译：

---

通过最小生成树进行实时分层Supervoxel分割

Supervoxel分割算法已被用作许多视觉任务的预处理步骤。但是，现有的超级体素分割算法无法实时很好地保留时空边界的层次化超级体素分割，这会阻止下游应用程序进行准确，高效的处理。在本文中，我们提出了一种基于最小生成树（MST）的实时分层超体素分割算法，该算法至少可以达到最新的精度 $ 11 \次$ 比现有方法更快。特别是，我们在MST的迭代构造过程中提出了动态图更新操作，该操作可以在几何上减少顶点和边的数量。以这种方式，所提出的方法能够动态地生成任意比例的超体素。我们证明了在时间复杂度高的情况下可以产生分层超体素的算法的效率 $ O（n）$ ，在哪里 $ n $ 表示输入视频中的体素数量。在公共基准上的定量和定性评估表明，在超级体素分割的准确性和计算效率方面，我们提出的算法明显优于最新算法。此外，我们证明了该方法在视频对象分割的下游应用中的有效性。