# Selective Video Object Cutout

## TL;DR

This paper introduces a novel video object segmentation method that combines structure-aware confidence maps, geodesic models, and uncertainty propagation to improve accuracy, efficiency, and reduce manual labeling.

## Contribution

It proposes a pyramid histogram confidence map with structure information, integrates geodesic distance models, and employs uncertainty measures to refine segmentation and minimize manual effort.

## Key findings

- Achieves superior segmentation accuracy on benchmark datasets.
- Demonstrates improved computational efficiency over existing methods.
- Reduces manual labeling requirements significantly.

## Abstract

Conventional video segmentation approaches rely heavily on appearance models. Such methods often use appearance descriptors that have limited discriminative power under complex scenarios. To improve the segmentation performance, this paper presents a pyramid histogram based confidence map that incorporates structure information into appearance statistics. It also combines geodesic distance based dynamic models. Then, it employs an efficient measure of uncertainty propagation using local classifiers to determine the image regions where the object labels might be ambiguous. The final foreground cutout is obtained by refining on the uncertain regions. Additionally, to reduce manual labeling, our method determines the frames to be labeled by the human operator in a principled manner, which further boosts the segmentation performance and minimizes the labeling effort. Our extensive experimental analyses on two big benchmarks demonstrate that our solution achieves superior performance, favorable computational efficiency, and reduced manual labeling in comparison to the state-of-the-art.