Tukey-Inspired Video Object Segmentation
This work addresses the challenge of automating video object segmentation for applications like video editing or surveillance without requiring manual annotations, though it is incremental as it builds on existing outlier detection concepts.
The paper tackles the problem of unsupervised video object segmentation by using a Tukey-inspired measure of outlierness to separate primary objects from background without any user input or training on annotated data, achieving state-of-the-art results on the DAVIS dataset and improving Jaccard measures by up to 28% when combining multiple segmentation methods.
We investigate the problem of strictly unsupervised video object segmentation, i.e., the separation of a primary object from background in video without a user-provided object mask or any training on an annotated dataset. We find foreground objects in low-level vision data using a John Tukey-inspired measure of "outlierness". This Tukey-inspired measure also estimates the reliability of each data source as video characteristics change (e.g., a camera starts moving). The proposed method achieves state-of-the-art results for strictly unsupervised video object segmentation on the challenging DAVIS dataset. Finally, we use a variant of the Tukey-inspired measure to combine the output of multiple segmentation methods, including those using supervision during training, runtime, or both. This collectively more robust method of segmentation improves the Jaccard measure of its constituent methods by as much as 28%.