• Corpus ID: 236976004

Two is a crowd: tracking relations in videos

@article{Moskalev2021TwoIA,
  title={Two is a crowd: tracking relations in videos},
  author={Artem Moskalev and Ivan Sosnovik and Arnold W. M. Smeulders},
  journal={ArXiv},
  year={2021},
  volume={abs/2108.05331}
}
Tracking multiple objects individually differs from tracking groups of related objects. When an object is a part of the group, its trajectory depends on the trajectories of the other group members. Most of the current state-of-the-art trackers follow the approach of tracking each object independently, with the mechanism to handle the overlapping trajectories where necessary. Such an approach does not take inter-object relations into account, which may cause unreliable tracking for the members… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 33 REFERENCES

Tracking Objects as Points

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that

Towards Real-Time Multi-Object Tracking

TLDR
This work incorporates the appearance embedding model into a single-shot detector, such that the model can simultaneously output detections and the corresponding embeddings, and is formulated as a multi-task learning problem.

Tracking Without Bells and Whistles

TLDR
Overall, Tracktor yields superior tracking performance than any current tracking method and the analysis exposes remaining and unsolved tracking challenges to inspire future research directions.

MOTS: Multi-Object Tracking and Segmentation

TLDR
This paper creates dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure, and proposes a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network.

Multiple People Tracking by Lifted Multicut and Person Re-identification

TLDR
A novel graph-based formulation that links and clusters person hypotheses over time by solving an instance of a minimum cost lifted multicut problem and is reported a new state-of-the-art for the MOT16 benchmark.

Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking

TLDR
A heterogeneous association graph is constructed that fuses high-level detections and low-level image evidence for target association and the novel idea of adaptive weights is proposed to analyze the contribution between motion and appearance.

Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics

TLDR
This work introduces two intuitive and general metrics to allow for objective comparison of tracker characteristics, focusing on their precision in estimating object locations, their accuracy in recognizing object configurations and their ability to consistently label objects over time.

MOT20: A benchmark for multi object tracking in crowded scenes

TLDR
The MOT20benchmark, consisting of 8 new sequences depicting very crowded challenging scenes, is presented, and gives to chance to evaluate state-of-the-art methods for multiple object tracking when handling extremely crowded scenarios.

Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering

TLDR
This work states this joint problem as a co-clustering problem that is principled and tractable by existing algorithms, and demonstrates the effectiveness of this approach by combining bottom-up motion segmentation by grouping of point trajectories with high-level multiple object tracking by clustering of bounding boxes.

MOT16: A Benchmark for Multi-Object Tracking

TLDR
A new release of the MOTChallenge benchmark, which focuses on multiple people tracking, and offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest.