Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Author: Shuhei Tarashima

Affiliation: Innovation Center, NTT Communications Corporation, Japan

Keyword(s): Multi-Object Tracking, CPU-GPU Data Transfer, Data Association.

Abstract: In most multi-object tracking (MOT) approaches under the tracking-by-detection framework, object detection and hypothesis association are addressed separately by setting bounding boxes as interfaces among them. This subdivision has greatly yielded advantages with respect to tracking accuracy, but it often lets researchers overlook the efficiency of whole MOT pipelines, since these interfaces can cause the time-consuming data communication between CPU and GPU. Alternatively, in this work we define an object hypothesis as a keypoint representing the object center, and propose simple data association algorithms based on the spatial proximity of keypoints. Different from standard data association methods like Hungarian algorithm, our approach can easily be run on GPU, which enables direct feed of detection results generated on GPU to our tracking module without the need of CPU-GPU data transfer. In this paper we conduct a series of experiments on MOT16, MOT17 and MOT-Soccer datasets in o rder to show that (1) our tracking module is much more efficient than existing methods while achieving competitive MOTA scores, (2) our tracking module run on GPU can improve the whole MOT efficiency via reducing the overhead of CPU-GPU data transfer between detection and tracking, and (3) our tracking module can be combined to a state-of-the-art unsupervised MOT method based on joint detection and embedding and successfully improve its efficiency. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.188.115.61

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Tarashima, S. (2021). Object Hypotheses as Points for Efficient Multi-Object Tracking. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6; ISSN 2184-4321, SciTePress, pages 828-835. DOI: 10.5220/0010343508280835

@conference{visapp21,
author={Shuhei Tarashima},
title={Object Hypotheses as Points for Efficient Multi-Object Tracking},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={828-835},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010343508280835},
isbn={978-989-758-488-6},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Object Hypotheses as Points for Efficient Multi-Object Tracking
SN - 978-989-758-488-6
IS - 2184-4321
AU - Tarashima, S.
PY - 2021
SP - 828
EP - 835
DO - 10.5220/0010343508280835
PB - SciTePress