Understanding cities with machine eyes: A review of deep computer vision in urban analytics

MR Ibrahim, J Haworth, T Cheng - Cities, 2020‏ - Elsevier
Modelling urban systems has interested planners and modellers for decades. Different
models have been achieved relying on mathematics, cellular automation, complexity, and …

Deep learning in visual tracking: A review

L Jiao, D Wang, Y Bai, P Chen… - IEEE transactions on …, 2021‏ - ieeexplore.ieee.org
Deep learning (DL) has made breakthroughs in many computer vision tasks and also in
visual tracking. From the beginning of the research on the automatic acquisition of high …

Transmot: Spatial-temporal graph transformer for multiple object tracking

P Chu, J Wang, Q You, H Ling… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of
the objects. In this paper, we propose TransMOT, which leverages powerful graph …

Mots: Multi-object tracking and segmentation

P Voigtlaender, M Krause, A Osep… - Proceedings of the …, 2019‏ - openaccess.thecvf.com
This paper extends the popular task of multi-object tracking to multi-object tracking and
segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two …

End-to-end learning of driving models with surround-view cameras and route planners

S Hecker, D Dai, L Van Gool - Proceedings of the european …, 2018‏ - openaccess.thecvf.com
For human drivers, having rear and side-view mirrors is vital for safe driving. They deliver a
more complete view of what is happening around the car. Human drivers also heavily exploit …

Probabilistic tracklet scoring and inpainting for multiple object tracking

F Saleh, S Aliakbarian, H Rezatofighi… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Despite the recent advances in multiple object tracking (MOT), achieved by joint detection
and tracking, dealing with long occlusions remains a challenge. This is due to the fact that …

TransCenter: Transformers with dense representations for multiple-object tracking

Y Xu, Y Ban, G Delorme, C Gan, D Rus… - IEEE transactions on …, 2022‏ - ieeexplore.ieee.org
Transformers have proven superior performance for a wide variety of tasks since they were
introduced. In recent years, they have drawn attention from the vision community in tasks …

Towards discriminative representation: Multi-view trajectory contrastive learning for online multi-object tracking

E Yu, Z Li, S Han - … of the IEEE/CVF Conference on …, 2022‏ - openaccess.thecvf.com
Discriminative representation is crucial for the association step in multi-object tracking.
Recent work mainly utilizes features in single or neighboring frames for constructing metric …

[HTML][HTML] Recent trends in crowd analysis: A review

M Bendali-Braham, J Weber, G Forestier… - Machine Learning with …, 2021‏ - Elsevier
When overpopulated cities face frequent crowded events like strikes, demonstrations,
parades or other sorts of people gatherings, they are confronted to multiple security issues …

Posetrack21: A dataset for person search, multi-object tracking and multi-person pose tracking

A Doering, D Chen, S Zhang… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Current research evaluates person search, multi-object tracking and multi-person pose
estimation as separate tasks and on different datasets although these tasks are very akin to …