Robust Unsupervised Multiobject Tracking In Noisy Environments

# Robust Unsupervised Multi-Object Tracking in Noisy Environments

**arXiv ID:** 2105.10005
**Authors:** C. -H. Huck Yang, Mohit Chhabra, Y. -C. Liu, Quan Kong, Tomoaki Yoshinaga, Tomokazu Murakami
**Published:** 2021-05-20T19:38:03Z
**Abstract:**
Physical processes, camera movement, and unpredictable environmental conditions like the presence of dust can induce noise and artifacts in video feeds. We observe that popular unsupervised MOT methods are dependent on noise-free inputs. We show that the addition of a small amount of artificial random noise causes a sharp degradation in model performance on benchmark metrics. We resolve this problem by introducing a robust unsupervised multi-object tracking (MOT) model: AttU-Net. The proposed single-head attention model helps limit the negative impact of noise by learning visual representations at different segment scales. AttU-Net shows better unsupervised MOT tracking performance over variational inference-based state-of-the-art baselines. We evaluate our method in the MNIST-MOT and the Atari game video benchmark. We also provide two extended video datasets: ``Kuzushiji-MNIST MOT'' which consists of moving Japanese characters and ``Fashion-MNIST MOT'' to validate the effectiveness of the MOT models.

## Skill Description

This skill is generated from the arXiv paper: Robust Unsupervised Multi-Object Tracking in Noisy Environments (2105.10005).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2105.10005](http://arxiv.org/abs/2105.10005v4)