Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Real-Time and Online Segmentation Multi-Target Tracking with Track Revival Re-Identification

Ahrnbom, Martin LU orcid ; Nilsson, Mikael LU and Ardö, Håkan LU (2021) 5. p.777-784
Abstract (Swedish)
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.... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
volume
5
pages
777 - 784
external identifiers
  • scopus:85102977844
ISBN
978-989-758-488-6
DOI
10.5220/0010190907770784
language
Swedish
LU publication?
yes
id
5f6bf791-d5cd-448e-8afe-5e578a356583
date added to LUP
2021-02-08 11:08:30
date last changed
2022-05-04 23:41:21
@inproceedings{5f6bf791-d5cd-448e-8afe-5e578a356583,
  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.}},
  author       = {{Ahrnbom, Martin and Nilsson, Mikael and Ardö, Håkan}},
  booktitle    = {{Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications}},
  isbn         = {{978-989-758-488-6}},
  language     = {{swe}},
  pages        = {{777--784}},
  title        = {{Real-Time and Online Segmentation Multi-Target Tracking with Track Revival Re-Identification}},
  url          = {{http://dx.doi.org/10.5220/0010190907770784}},
  doi          = {{10.5220/0010190907770784}},
  volume       = {{5}},
  year         = {{2021}},
}