Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50

Shaurya Pal; Tasos Dagiuklas

doi:10.1109/HCCS59561.2023.10452624

Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50

Shaurya Pal, Tasos Dagiuklas

London South Bank University

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

Abstract

The primary aim of this paper is to benchmark reidentification within a multi-camera tracking system. This benchmark has been developed by leveraging transfer learning, utilizing YOLOv8 for real-time object detection and ResNet-50 for feature extraction. The objective is to evaluate the system's performance in accurately reidentifying vehicles across multiple cameras in real-world traffic surveillance scenarios. This benchmarking endeavor aims to provide a standardized evaluation framework for assessing the capabilities and limitations of vehicle reidentification techniques, with a focus on their applicability in challenging conditions such as low-light environments, image compression, and object occlusions.

Original language	English
Title of host publication	Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350359183
DOIs	https://doi.org/10.1109/HCCS59561.2023.10452624 https://doi.org/10.1109/hccs59561.2023.10452624
Publication status	Published - 16 Dec 2023
Event	2023 International Conference on Human-Centered Cognitive Systems (HCCS) - Duration: 16 Dec 2023 → …

Publication series

Name	Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023

Conference

Conference	2023 International Conference on Human-Centered Cognitive Systems (HCCS)
Period	16/12/23 → …

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Feature Extraction
Intelligent Transportation Systems
Multi-Camera Tracking
Object Detection
Transfer Learning
Vehicle Reidentification

Access to Document

HCCS-2023-11747Accepted author manuscript, 535 KBLicence: CC BY 4.0

Cite this

Pal, S., & Dagiuklas, T. (2023). Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50. In Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023 (Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HCCS59561.2023.10452624, https://doi.org/10.1109/hccs59561.2023.10452624

@inproceedings{25a8416b311a46ec92422ea53abdbf13,

title = "Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50",

abstract = "The primary aim of this paper is to benchmark reidentification within a multi-camera tracking system. This benchmark has been developed by leveraging transfer learning, utilizing YOLOv8 for real-time object detection and ResNet-50 for feature extraction. The objective is to evaluate the system's performance in accurately reidentifying vehicles across multiple cameras in real-world traffic surveillance scenarios. This benchmarking endeavor aims to provide a standardized evaluation framework for assessing the capabilities and limitations of vehicle reidentification techniques, with a focus on their applicability in challenging conditions such as low-light environments, image compression, and object occlusions.",

keywords = "Feature Extraction, Intelligent Transportation Systems, Multi-Camera Tracking, Object Detection, Transfer Learning, Vehicle Reidentification",

author = "Shaurya Pal and Tasos Dagiuklas",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Human-Centered Cognitive Systems (HCCS) ; Conference date: 16-12-2023",

year = "2023",

month = dec,

day = "16",

doi = "10.1109/HCCS59561.2023.10452624",

language = "English",

series = "Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023",

address = "United States",

}

Pal, S & Dagiuklas, T 2023, Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50. in Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023. Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023, Institute of Electrical and Electronics Engineers Inc., 2023 International Conference on Human-Centered Cognitive Systems (HCCS), 16/12/23. https://doi.org/10.1109/HCCS59561.2023.10452624, https://doi.org/10.1109/hccs59561.2023.10452624

Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50. / Pal, Shaurya; Dagiuklas, Tasos.
Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023).

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

TY - GEN

T1 - Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50

AU - Pal, Shaurya

AU - Dagiuklas, Tasos

PY - 2023/12/16

Y1 - 2023/12/16

N2 - The primary aim of this paper is to benchmark reidentification within a multi-camera tracking system. This benchmark has been developed by leveraging transfer learning, utilizing YOLOv8 for real-time object detection and ResNet-50 for feature extraction. The objective is to evaluate the system's performance in accurately reidentifying vehicles across multiple cameras in real-world traffic surveillance scenarios. This benchmarking endeavor aims to provide a standardized evaluation framework for assessing the capabilities and limitations of vehicle reidentification techniques, with a focus on their applicability in challenging conditions such as low-light environments, image compression, and object occlusions.

AB - The primary aim of this paper is to benchmark reidentification within a multi-camera tracking system. This benchmark has been developed by leveraging transfer learning, utilizing YOLOv8 for real-time object detection and ResNet-50 for feature extraction. The objective is to evaluate the system's performance in accurately reidentifying vehicles across multiple cameras in real-world traffic surveillance scenarios. This benchmarking endeavor aims to provide a standardized evaluation framework for assessing the capabilities and limitations of vehicle reidentification techniques, with a focus on their applicability in challenging conditions such as low-light environments, image compression, and object occlusions.

KW - Feature Extraction

KW - Intelligent Transportation Systems

KW - Multi-Camera Tracking

KW - Object Detection

KW - Transfer Learning

KW - Vehicle Reidentification

UR - http://www.scopus.com/inward/record.url?scp=85187199696&partnerID=8YFLogxK

U2 - 10.1109/HCCS59561.2023.10452624

DO - 10.1109/HCCS59561.2023.10452624

M3 - Conference contribution

T3 - Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023

BT - Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Conference on Human-Centered Cognitive Systems (HCCS)

Y2 - 16 December 2023

ER -

Pal S, Dagiuklas T. Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50. In Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings - 2023 Human-Centered Cognitive Systems, HCCS 2023). doi: 10.1109/HCCS59561.2023.10452624, 10.1109/hccs59561.2023.10452624

Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this