Track, then decide: Category-agnostic vision-based multi-object tracking

A Ošep, W Mehner, P Voigtlaender… - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
The most common paradigm for vision-based multi-object tracking is tracking-by-detection,
due to the availability of reliable detectors for several important object categories such as …

Anthropological Comparative Analysis of CCTV Footage in a 3D Virtual Environment

K Maksymowicz, A Kuzan, Ł Szleszkowski… - Applied Sciences, 2023 - mdpi.com
The image is a particularly valuable data carrier in medical forensic and forensic analyses.
One of the analyses, as mentioned above, is to assess whether a graphically captured …

[PDF][PDF] Unsupervised Learning of Shape-Motion Patterns for Objects in Urban Street Scenes.

D Klostermann, A Osep, J Stückler… - BMVC, 2016 - web-info8.informatik.rwth-aachen.de
Tracking in urban street scenes is predominantly based on pretrained object-specific
detectors and Kalman filter based tracking. More recently, methods have been proposed that …

Merging, extending and learning representations for 3D shape matching

R Marin - 2021 - diglib.cgv.tugraz.at
In the last decades, researchers devoted considerable attention to shape matching.
Correlating surfaces unlocks otherwise impossible applications and analysis. However, non …

POP: Full parametric model estimation for occluded people

R Marin, S Melzi, NJ Mitra… - … Workshop on 3D Object …, 2019 - discovery.ucl.ac.uk
In the last decades, we have witnessed advances in both hardware and associated
algorithms resulting in unprecedented access to volumes of 2D and, more recently, 3D data …

[PDF][PDF] Supplementary Material-Unsupervised Learning of Shape-Motion Patterns for Objects in Urban Street Scenes

D Klostermann, A Osep, J Stückler, B Leibe - vci.rwth-aachen.de
Our shape clustering and matching approach requires repeatable descriptors represented
by the GCTs. To retrieve such features, we take care that the GCTs are aligned consistently …