TY - GEN
T1 - Tukey-inspired video object segmentation
AU - Griffin, Brent A.
AU - Corso, Jason J.
N1 - Publisher Copyright:
© 2019 IEEE
PY - 2019/3/4
Y1 - 2019/3/4
N2 - 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%.
AB - 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%.
UR - http://www.scopus.com/inward/record.url?scp=85063594076&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063594076&partnerID=8YFLogxK
U2 - 10.1109/WACV.2019.00188
DO - 10.1109/WACV.2019.00188
M3 - Conference contribution
AN - SCOPUS:85063594076
T3 - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
SP - 1723
EP - 1733
BT - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
T2 - 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Y2 - 7 January 2019 through 11 January 2019
ER -