Real-time and Online Segmentation Multi-target Tracking with Track Revival Re-identification

Martin Ahrnbom, Mikael Nilsson, Håkan Ardö

Abstract

The first online segmentation multi-target tracking algorithm with reported real-time speeds is presented. Based on the popular and fast bounding box based tracker SORT, our method called SORTS is able to utilize segmentations for tracking while keeping the real-time speeds. To handle occlusions, which neither SORT nor SORTS do, we also present SORTS+RReID, an optional extension which uses ReID vectors to revive lost tracks from SORTS to handle occlusions. Despite only computing ReID vectors for 6.9% of the detections, ID switches are decreased by 45%. We evaluate on the MOTS dataset and run at 54.5 and 36.4 FPS for SORTS and SORT+RReID respectively, while keeping 78-79% of the sMOTSA of the current state of the art, which runs at 0.3 FPS. Furthermore, we include an experiment using a faster instance segmentation method to explore the feasibility of a complete real-time detection and tracking system. Code is available: https://github.com/ahrnbom/sorts.

Download


Paper Citation


in Harvard Style

Ahrnbom M., Nilsson M. and Ardö H. (2021). Real-time and Online Segmentation Multi-target Tracking with Track Revival Re-identification.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 777-784. DOI: 10.5220/0010190907770784


in Bibtex Style

@conference{visapp21,
author={Martin Ahrnbom and Mikael Nilsson and Håkan Ardö},
title={Real-time and Online Segmentation Multi-target Tracking with Track Revival Re-identification},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={777-784},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010190907770784},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Real-time and Online Segmentation Multi-target Tracking with Track Revival Re-identification
SN - 978-989-758-488-6
AU - Ahrnbom M.
AU - Nilsson M.
AU - Ardö H.
PY - 2021
SP - 777
EP - 784
DO - 10.5220/0010190907770784