Video Object Segmentation via Super-trajectories
Authors:
- Wenguan WangWWWenguan Wang
- Jianbing ShenJSJianbing Shen
- Fatih PorikliFPFatih Porikli
Preprint
Abstract
We introduce a novel semi-supervised video segmentation approach based on an efficient video representation, called as "super-trajectory". Each super-trajectory corresponds to a group of compact trajectories that exhibit consistent motion patterns, similar appearance and close spatiotemporal relationships. We generate trajectories using a probabilistic model, which handles occlusions and drifts in a robust and natural way. To reliably group trajectories, we adopt a modified version of the density peaks based clustering algorithm that allows capturing rich spatiotemporal relations among trajectories in the clustering process. The presented video representation is discriminative enough to accurately propagate the initial annotations in the first frame onto the remaining video frames. Extensive experimental analysis on challenging benchmarks demonstrate our method is capable of distinguishing the target objects from complex backgrounds and even reidentifying them after long-term occlusions.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Spatio-temporal Object Detection Proposals2014
- Supervoxel-Consistent Foreground Propagation in Video2014
- Active Frame Selection for Label Propagation in Videos2012
- Streaming Hierarchical Video Segmentation2012
- Motion Coherent Tracking Using Multi-label MRF OptimizationInternational Journal of Computer Vision, 2011
- Efficient hierarchical graph-based video segmentation2010
- Label propagation in video sequences2010
- Object Segmentation by Long Term Analysis of Point Trajectories2010
- Multiple Hypothesis Video Segmentation from Superpixel Flows2010
- Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow2010