Improved Image Boundaries for Better Video Segmentation
arXiv:1605.03718
Abstract
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as solving the graph partitioning problem, this paper focuses on better superpixels for video segmentation. We demonstrate by a comparative analysis that superpixels extracted from boundaries perform best, and show that boundary estimation can be significantly improved via image and time domain cues. With superpixels generated from our better boundaries we observe consistent improvement for two video segmentation methods in two different datasets.
References in corpus (6)
- EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
- Fast Edge Detection Using Structured Forests
- DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
- Oriented Edge Forests for Boundary Detection
- Learning to Segment Moving Objects in Videos
- Point-wise mutual information-based video segmentation with high temporal consistency