Computer vision for autonomous vehicles: Problems, datasets and state of the art

J Janai, F Güney, A Behl, A Geiger - Foundations and Trends® …, 2020 - nowpublishers.com
Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Multiple object tracking: A literature review

W Luo, J Xing, A Milan, X Zhang, W Liu, TK Kim - Artificial intelligence, 2021 - Elsevier
Abstract Multiple Object Tracking (MOT) has gained increasing attention due to its academic
and commercial potential. Although different approaches have been proposed to tackle this …

Motsynth: How can synthetic data help pedestrian detection and tracking?

M Fabbri, G Brasó, G Maugeri… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep learning-based methods for video pedestrian detection and tracking require large
volumes of training data to achieve good performance. However, data acquisition in …

Deep affinity network for multiple object tracking

SJ Sun, N Akhtar, HS Song, A Mian… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Multiple Object Tracking (MOT) plays an important role in solving many fundamental
problems in video analysis and computer vision. Most MOT methods employ two steps …

Tracking the untrackable: Learning to track multiple cues with long-term dependencies

A Sadeghian, A Alahi… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
The majority of existing solutions to the Multi-Target Tracking (MTT) problem do not combine
cues over a long period of time in a coherent fashion. In this paper, we present an online …

How to train your deep multi-object tracker

Y Xu, A Osep, Y Ban, R Horaud… - Proceedings of the …, 2020 - openaccess.thecvf.com
The recent trend in vision-based multi-object tracking (MOT) is heading towards leveraging
the representational power of deep learning to jointly learn to detect and track objects …

Tarvis: A unified approach for target-based video segmentation

A Athar, A Hermans, J Luiten… - Proceedings of the …, 2023 - openaccess.thecvf.com
The general domain of video segmentation is currently fragmented into different tasks
spanning multiple benchmarks. Despite rapid progress in the state-of-the-art, current …

Quo vadis: Is trajectory forecasting the key towards long-term multi-object tracking?

P Dendorfer, V Yugay, A Osep… - Advances in Neural …, 2022 - proceedings.neurips.cc
Recent developments in monocular multi-object tracking have been very successful in
tracking visible objects and bridging short occlusion gaps, mainly relying on data-driven …

Deep-cascade: Cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenes

M Sabokrou, M Fayyaz, M Fathy… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
This paper proposes a fast and reliable method for anomaly detection and localization in
video data showing crowded scenes. Time-efficient anomaly localization is an ongoing …

You'll never walk alone: Modeling social behavior for multi-target tracking

S Pellegrini, A Ess, K Schindler… - 2009 IEEE 12th …, 2009 - ieeexplore.ieee.org
Object tracking typically relies on a dynamic model to predict the object's location from its
past trajectory. In crowded scenarios a strong dynamic model is particularly important …