Instance-Level Video Segmentation From Object Tracks

Guillaume Seguin, Piotr Bojanowski, Remi Lajugie, Ivan Laptev; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 3678-3687

Abstract


We address the problem of segmenting multiple object instances in complex videos. Our method does not require manual pixel-level annotation for training, and relies instead on readily-available object detectors or visual object tracking only. Given object bounding boxes at input, we cast video segmentation as a weakly-supervised learning problem. Our proposed objective combines (a) a discriminative clustering term for background segmentation, (b) a spectral clustering one for grouping pixels of same object instances, and (c) linear constraints enabling instance-level segmentation. We propose a convex relaxation of this problem and solve it efficiently using the Frank-Wolfe algorithm. We report results and compare our method to several baselines on a new video dataset for multi-instance person segmentation.

Related Material


[pdf]
[bibtex]
@InProceedings{Seguin_2016_CVPR,
author = {Seguin, Guillaume and Bojanowski, Piotr and Lajugie, Remi and Laptev, Ivan},
title = {Instance-Level Video Segmentation From Object Tracks},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}