Real-time hierarchical supervoxel segmentation via a minimum spanning tree

Publication Type

Journal Article

Publication Date

1-2020

Abstract

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 11x 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-ofthe-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.

Keywords

Supervoxel, video segmentation, minimum spanning tree

Discipline

Information Security

Research Areas

Information Systems and Management

Publication

IEEE Transactions on Image Processing

Volume

29

First Page

9665

Last Page

9677

ISSN

1057-7149

Identifier

10.1109/TIP.2020.3030502

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TIP.2020.3030502

This document is currently not available here.

Share

COinS