Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing

Tsaipei Wang; Sheng Ho Chiang

doi:10.1109/ICIP49359.2023.10222224

Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing

Tsaipei Wang^*, Sheng Ho Chiang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper describes a dense fisheye camera network for pedestrian tracking in an indoor environment, with the target scenario being an unmanned store. Each fisheye camera is connected to a single-board computer for local tracking using its own images. The local tracks are integrated and global tracks generated at a central computer in an online manner. The local trackers are based on the popular DeepSORT algorithm, and the global tracker combines distance and novel specialization based factors to update global tracks from local tracks, avoiding the need of matching local tracks. Experiments on a self-collected dataset demonstrate highly accurate tracking over several minutes of videos.

Original language	English
Title of host publication	2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings
Publisher	IEEE Computer Society
Pages	3518-3522
Number of pages	5
ISBN (Electronic)	9781728198354
DOIs	https://doi.org/10.1109/ICIP49359.2023.10222224
State	Published - 2023
Event	30th IEEE International Conference on Image Processing, ICIP 2023 - Kuala Lumpur, Malaysia Duration: 8 Oct 2023 → 11 Oct 2023

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Conference

Conference	30th IEEE International Conference on Image Processing, ICIP 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	8/10/23 → 11/10/23

Keywords

Multi-object tracking
camera network
edge computing
fisheye camera
multi-camera tracking

Access to Document

10.1109/ICIP49359.2023.10222224

Cite this

@inproceedings{d6fe0c4339464304b97f5ce0fb177dbd,

title = "Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing",

abstract = "This paper describes a dense fisheye camera network for pedestrian tracking in an indoor environment, with the target scenario being an unmanned store. Each fisheye camera is connected to a single-board computer for local tracking using its own images. The local tracks are integrated and global tracks generated at a central computer in an online manner. The local trackers are based on the popular DeepSORT algorithm, and the global tracker combines distance and novel specialization based factors to update global tracks from local tracks, avoiding the need of matching local tracks. Experiments on a self-collected dataset demonstrate highly accurate tracking over several minutes of videos.",

keywords = "Multi-object tracking, camera network, edge computing, fisheye camera, multi-camera tracking",

author = "Tsaipei Wang and Chiang, {Sheng Ho}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 30th IEEE International Conference on Image Processing, ICIP 2023 ; Conference date: 08-10-2023 Through 11-10-2023",

year = "2023",

doi = "10.1109/ICIP49359.2023.10222224",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3518--3522",

booktitle = "2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings",

address = "美國",

}

Wang, T & Chiang, SH 2023, Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing. in 2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 3518-3522, 30th IEEE International Conference on Image Processing, ICIP 2023, Kuala Lumpur, Malaysia, 8/10/23. https://doi.org/10.1109/ICIP49359.2023.10222224

Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing. / Wang, Tsaipei; Chiang, Sheng Ho.
2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings. IEEE Computer Society, 2023. p. 3518-3522 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing

AU - Wang, Tsaipei

AU - Chiang, Sheng Ho

PY - 2023

Y1 - 2023

N2 - This paper describes a dense fisheye camera network for pedestrian tracking in an indoor environment, with the target scenario being an unmanned store. Each fisheye camera is connected to a single-board computer for local tracking using its own images. The local tracks are integrated and global tracks generated at a central computer in an online manner. The local trackers are based on the popular DeepSORT algorithm, and the global tracker combines distance and novel specialization based factors to update global tracks from local tracks, avoiding the need of matching local tracks. Experiments on a self-collected dataset demonstrate highly accurate tracking over several minutes of videos.

AB - This paper describes a dense fisheye camera network for pedestrian tracking in an indoor environment, with the target scenario being an unmanned store. Each fisheye camera is connected to a single-board computer for local tracking using its own images. The local tracks are integrated and global tracks generated at a central computer in an online manner. The local trackers are based on the popular DeepSORT algorithm, and the global tracker combines distance and novel specialization based factors to update global tracks from local tracks, avoiding the need of matching local tracks. Experiments on a self-collected dataset demonstrate highly accurate tracking over several minutes of videos.

KW - Multi-object tracking

KW - camera network

KW - edge computing

KW - fisheye camera

KW - multi-camera tracking

UR - http://www.scopus.com/inward/record.url?scp=85180811944&partnerID=8YFLogxK

U2 - 10.1109/ICIP49359.2023.10222224

DO - 10.1109/ICIP49359.2023.10222224

M3 - Conference contribution

AN - SCOPUS:85180811944

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3518

EP - 3522

BT - 2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings

PB - IEEE Computer Society

T2 - 30th IEEE International Conference on Image Processing, ICIP 2023

Y2 - 8 October 2023 through 11 October 2023

ER -

Online Pedestrian Tracking Using A Dense Fisheye Camera Network With Edge Computing

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this