Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8
Computer simulations using agent-based approach aimed at modeling human behavior require a robust dataset derived from actual observation to serve as ground truth. This paper details an approach for developing a movement behavior dataset generator from CCTV footages with respect to two health-relate...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Published: |
Archīum Ateneo
2023
|
Subjects: | |
Online Access: | https://archium.ateneo.edu/discs-faculty-pubs/393 https://doi.org/10.1007/978-3-031-43129-6_29 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Ateneo De Manila University |
id |
ph-ateneo-arc.discs-faculty-pubs-1393 |
---|---|
record_format |
eprints |
spelling |
ph-ateneo-arc.discs-faculty-pubs-13932024-02-20T09:26:04Z Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 Abao, Roland P. Estuar, Ma. Regina Justina Abu, Patricia Angela R Computer simulations using agent-based approach aimed at modeling human behavior require a robust dataset derived from actual observation to serve as ground truth. This paper details an approach for developing a movement behavior dataset generator from CCTV footages with respect to two health-related behaviors: face mask wearing and physical distancing, while addressing the privacy concerns of confidential CCTV data. A two-stage YOLOv8-based cascaded approach was implemented for object tracking and detection. The first stage involves tracking of individuals in the video feed to determine physical distancing behavior using the pre-trained YOLOv8 xLarge model paired with Bot-SORT multi-object tracker and OpenCV Perspective-n-Point pose estimation. The second stage involves determining the mask wearing behavior of the tracked individuals using the best-performing model among the five YOLOv8 models (nano, small, medium, large, and xLarge), each trained for 50 epochs on a custom CCTV dataset. Results show that the custom-trained xLarge model performed the best on the mask detection task with the following metric scores: mAP50 = 0.94; mAP50-95 = 0.63; and F1 = 0.872. The faces of all the tracked individuals are blurred-out in the resulting video frames to preserve the privacy of the CCTV data. Finally, the developed system is able to generate the corresponding mask-distancing behavior dataset and annotated output videos from the input CCTV raw footages. 2023-01-01T08:00:00Z text https://archium.ateneo.edu/discs-faculty-pubs/393 https://doi.org/10.1007/978-3-031-43129-6_29 Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo CCTV data dataset generator mask wearing physical distancing YOLOv8 Computer Engineering Electrical and Computer Engineering Engineering |
institution |
Ateneo De Manila University |
building |
Ateneo De Manila University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
Ateneo De Manila University Library |
collection |
archium.Ateneo Institutional Repository |
topic |
CCTV data dataset generator mask wearing physical distancing YOLOv8 Computer Engineering Electrical and Computer Engineering Engineering |
spellingShingle |
CCTV data dataset generator mask wearing physical distancing YOLOv8 Computer Engineering Electrical and Computer Engineering Engineering Abao, Roland P. Estuar, Ma. Regina Justina Abu, Patricia Angela R Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 |
description |
Computer simulations using agent-based approach aimed at modeling human behavior require a robust dataset derived from actual observation to serve as ground truth. This paper details an approach for developing a movement behavior dataset generator from CCTV footages with respect to two health-related behaviors: face mask wearing and physical distancing, while addressing the privacy concerns of confidential CCTV data. A two-stage YOLOv8-based cascaded approach was implemented for object tracking and detection. The first stage involves tracking of individuals in the video feed to determine physical distancing behavior using the pre-trained YOLOv8 xLarge model paired with Bot-SORT multi-object tracker and OpenCV Perspective-n-Point pose estimation. The second stage involves determining the mask wearing behavior of the tracked individuals using the best-performing model among the five YOLOv8 models (nano, small, medium, large, and xLarge), each trained for 50 epochs on a custom CCTV dataset. Results show that the custom-trained xLarge model performed the best on the mask detection task with the following metric scores: mAP50 = 0.94; mAP50-95 = 0.63; and F1 = 0.872. The faces of all the tracked individuals are blurred-out in the resulting video frames to preserve the privacy of the CCTV data. Finally, the developed system is able to generate the corresponding mask-distancing behavior dataset and annotated output videos from the input CCTV raw footages. |
format |
text |
author |
Abao, Roland P. Estuar, Ma. Regina Justina Abu, Patricia Angela R |
author_facet |
Abao, Roland P. Estuar, Ma. Regina Justina Abu, Patricia Angela R |
author_sort |
Abao, Roland P. |
title |
Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 |
title_short |
Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 |
title_full |
Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 |
title_fullStr |
Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 |
title_full_unstemmed |
Physical Distancing and Mask Wearing Behavior Dataset Generator from CCTV Footages Using YOLOv8 |
title_sort |
physical distancing and mask wearing behavior dataset generator from cctv footages using yolov8 |
publisher |
Archīum Ateneo |
publishDate |
2023 |
url |
https://archium.ateneo.edu/discs-faculty-pubs/393 https://doi.org/10.1007/978-3-031-43129-6_29 |
_version_ |
1792202617076580352 |