Improved Image Boundaries for Better Video Segmentation
This work addresses video segmentation for computer vision applications, but it is incremental as it builds on existing graph-based methods by refining superpixel quality.
The paper tackled the problem of improving video segmentation by focusing on better superpixels derived from enhanced boundary estimation, resulting in consistent improvements for two methods across two datasets.
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.