TY - JOUR

T1 - Using synthetic data for person tracking under adverse weather conditions

AU - Kerim, A.

AU - Celikcan, U.

AU - Erdem, E.

AU - Erdem, A.

N1 - This is the author’s version of a work that was accepted for publication in Image and Vision Computing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Image and Vision Computing, 111, 2021 DOI: 10.1016/j.imavis.2021.104187

PY - 2021/7/31

Y1 - 2021/7/31

N2 - Robust visual tracking plays a vital role in many areas such as autonomous cars, surveillance and robotics. Recent trackers were shown to achieve adequate results under normal tracking scenarios with clear weather conditions, standard camera setups and lighting conditions. Yet, the performance of these trackers, whether they are correlation filter-based or learning-based, degrade under adverse weather conditions. The lack of videos with such weather conditions, in the available visual object tracking datasets, is the prime issue behind the low performance of the learning-based tracking algorithms. In this work, we provide a new person tracking dataset of real-world sequences (PTAW172Real) captured under foggy, rainy and snowy weather conditions to assess the performance of the current trackers. We also introduce a novel person tracking dataset of synthetic sequences (PTAW217Synth) procedurally generated by our NOVA framework spanning the same weather conditions in varying severity to mitigate the problem of data scarcity. Our experimental results demonstrate that the performances of the state-of-the-art deep trackers under adverse weather conditions can be boosted when the available real training sequences are complemented with our synthetically generated dataset during training.

AB - Robust visual tracking plays a vital role in many areas such as autonomous cars, surveillance and robotics. Recent trackers were shown to achieve adequate results under normal tracking scenarios with clear weather conditions, standard camera setups and lighting conditions. Yet, the performance of these trackers, whether they are correlation filter-based or learning-based, degrade under adverse weather conditions. The lack of videos with such weather conditions, in the available visual object tracking datasets, is the prime issue behind the low performance of the learning-based tracking algorithms. In this work, we provide a new person tracking dataset of real-world sequences (PTAW172Real) captured under foggy, rainy and snowy weather conditions to assess the performance of the current trackers. We also introduce a novel person tracking dataset of synthetic sequences (PTAW217Synth) procedurally generated by our NOVA framework spanning the same weather conditions in varying severity to mitigate the problem of data scarcity. Our experimental results demonstrate that the performances of the state-of-the-art deep trackers under adverse weather conditions can be boosted when the available real training sequences are complemented with our synthetically generated dataset during training.

KW - Person tracking

KW - Procedural generation

KW - Rendering

KW - Synthetic data

KW - Meteorology

KW - Correlation filters

KW - Lighting conditions

KW - Real-world sequences

KW - State of the art

KW - Synthetic sequence

KW - Tracking algorithm

KW - Training sequences

KW - Visual object tracking

KW - Object tracking

U2 - 10.1016/j.imavis.2021.104187

DO - 10.1016/j.imavis.2021.104187

M3 - Journal article

VL - 111

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

M1 - 104187

ER -