Tukey-inspired video object segmentation

Brent A. Griffin, Jason J. Corso

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Scopus citations

Abstract

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%.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Pages1723-1733
Number of pages11
ISBN (Electronic)9781728119755
DOIs
StatePublished - 4 Mar 2019
Event19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019 - Waikoloa Village, United States
Duration: 7 Jan 201911 Jan 2019

Publication series

NameProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019

Conference

Conference19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Country/TerritoryUnited States
CityWaikoloa Village
Period7/01/1911/01/19

Fingerprint

Dive into the research topics of 'Tukey-inspired video object segmentation'. Together they form a unique fingerprint.

Cite this