Improving Streaming Video Segmentation with Early and Mid-Level Visual Processing
This work addresses video segmentation for applications like foreground recognition, but it is incremental as it builds on an existing method.
The paper tackled the problem of streaming video segmentation by improving the streamGBH method with early and mid-level visual cues like motion and color filtering, resulting in enhanced hierarchical supervoxel representations validated through extensive experiments.
Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues. We propose improvements to the leading streaming graph-based hierarchical video segmentation (streamGBH) method based on early and mid level visual processing. The extensive experimental analysis of our approach validates the improvement of hierarchical supervoxel representation by incorporating motion and color with effective filtering. We also pose and illuminate some open questions towards intermediate level video analysis as further extension to streamGBH. We exploit the supervoxels as an initialization towards estimation of dominant affine motion regions, followed by merging of such motion regions in order to hierarchically segment a video in a novel motion-segmentation framework which aims at subsequent applications such as foreground recognition.