Robust Unsupervised Multi-Object Tracking in Noisy Environments

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.

arXiv commentAccepted to IEEE ICIP 2021

References in corpus (14)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Attention U-Net: Learning Where to Look for the Pancreas
• A Survey of Deep Learning Techniques for Autonomous Driving
• Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
• A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases
• Robustness Analysis of Visual QA Models by Basic Questions
• LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement
• Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning
• S3Net: A Single Stream Structure for Depth Guided Image Relighting
• PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
• Contextualized Keyword Representations for Multi-modal Retinal Image Captioning
• Multi-modal Bifurcated Network for Depth Guided Image Relighting
• GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization