Super-Trajectory for Video Segmentation
This addresses video segmentation for computer vision applications, but it is incremental as it builds on existing trajectory and clustering methods.
The authors tackled video segmentation by introducing a semi-supervised approach using super-trajectories, which group trajectories with consistent motion and appearance, achieving accurate propagation of annotations from the first frame to others and reidentifying objects after occlusions.
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.