Crowd Detection: Leveraging YOLO for Human Recognition

Gülsüm Yiğit

Makale detayları

Crowd Detection: Leveraging YOLO for Human Recognition

Yazarlar:

Gülsüm Yiğit

Yayıncı:

Murat YAKAR

Ana Başlıklar:

Software Engineering (Other)

Dergi:

Turkish Journal of Engineering Vol.9 Issue 3, pp.571-577

Belge Tipi:

Makale

Yayın Tarihi:

1/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001339468

pISSN:

2587-1366

Anahtar kelimeler:

Özet:

 Human detection in crowded environments is essential for applications such as surveillance, autonomous navigation, and crowd management. This study examines the performance of various YOLO You Only Look Once models in detecting humans. We combined four public human detection datasets to create a comprehensive dataset for crowd detection. Experiments were conducted on YOLOv5, YOLOv8, and YOLOv11 models, employing different architectures and model sizes. Performance was evaluated using mean Average Precision mAP at Intersection over Union IoU thresholds of 50 mAP50 and across 50-95 mAP50-95. The results indicate that the YOLOv8m model achieved the highest mAP50 of 0.944 and mAP50-95 of 0.697, surpassing larger models such as YOLOv11x, which attained 0.90 and 0.632 respectively. Additionally, other YOLOv8 variants demonstrated superior or comparable performance to their YOLOv5 and YOLOv11 counterparts. These findings highlight the effectiveness of YOLOv8s optimized structures in delivering accurate and efficient human detection in high-density settings.

 Human detection in crowded environments is essential for applications such as surveillance, autonomous navigation, and crowd management. This study examines the performance of various YOLO You Only Look Once models in detecting humans. We combined four public human detection datasets to create a comprehensive dataset for crowd detection. Experiments were conducted on YOLOv5, YOLOv8, and YOLOv11 models, employing different architectures and model sizes. Performance was evaluated using mean Average Precision mAP at Intersection over Union IoU thresholds of 50 mAP50 and across 50-95 mAP50-95. The results indicate that the YOLOv8m model achieved the highest mAP50 of 0.944 and mAP50-95 of 0.697, surpassing larger models such as YOLOv11x, which attained 0.90 and 0.632 respectively. Additionally, other YOLOv8 variants demonstrated superior or comparable performance to their YOLOv5 and YOLOv11 counterparts. These findings highlight the effectiveness of YOLOv8s optimized structures in delivering accurate and efficient human detection in high-density settings.

 Human detection in crowded environments is essential for applications such as surveillance, autonomous navigation, and crowd management. This study examines the performance of various YOLO You Only Look Once models in detecting humans. We combined four public human detection datasets to create a comprehensive dataset for crowd detection. Experiments were conducted on YOLOv5, YOLOv8, and YOLOv11 models, employing different architectures and model sizes. Performance was evaluated using mean Average Precision mAP at Intersection over Union IoU thresholds of 50 mAP50 and across 50-95 mAP50-95. The results indicate that the YOLOv8m model achieved the highest mAP50 of 0.944 and mAP50-95 of 0.697, surpassing larger models such as YOLOv11x, which attained 0.90 and 0.632 respectively. Additionally, other YOLOv8 variants demonstrated superior or comparable performance to their YOLOv5 and YOLOv11 counterparts. These findings highlight the effectiveness of YOLOv8s optimized structures in delivering accurate and efficient human detection in high-density settings.

 Human detection in crowded environments is essential for applications such as surveillance, autonomous navigation, and crowd management. This study examines the performance of various YOLO You Only Look Once models in detecting humans. We combined four public human detection datasets to create a comprehensive dataset for crowd detection. Experiments were conducted on YOLOv5, YOLOv8, and YOLOv11 models, employing different architectures and model sizes. Performance was evaluated using mean Average Precision mAP at Intersection over Union IoU thresholds of 50 mAP50 and across 50-95 mAP50-95. The results indicate that the YOLOv8m model achieved the highest mAP50 of 0.944 and mAP50-95 of 0.697, surpassing larger models such as YOLOv11x, which attained 0.90 and 0.632 respectively. Additionally, other YOLOv8 variants demonstrated superior or comparable performance to their YOLOv5 and YOLOv11 counterparts. These findings highlight the effectiveness of YOLOv8s optimized structures in delivering accurate and efficient human detection in high-density settings.

Makale detayları

Crowd Detection: Leveraging YOLO for Human Recognition

Yazarlar:

Gülsüm Yiğit

Yayıncı:

Murat YAKAR

Ana Başlıklar:

Software Engineering (Other)

Dergi:

Turkish Journal of Engineering Vol.9 Issue 3, pp.571-577

Belge Tipi:

Makale

Yayın Tarihi:

1/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001339468

pISSN:

2587-1366

Human Detection

Yolo Models

Crowd Detection

Object Detection

Mean Average Precision

Sayı

Makale detayları

Crowd Detection: Leveraging YOLO for Human Recognition

Yazarlar: Gülsüm Yiğit

Yayıncı: Murat YAKAR

Ana Başlıklar: Software Engineering (Other)

Dergi: Turkish Journal of Engineering Vol.9 Issue 3, pp.571-577

Belge Tipi: Makale

Yayın Tarihi: 1/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001339468

pISSN: 2587-1366

Human Detection

Yolo Models

Crowd Detection

Object Detection

Mean Average Precision

Sayı

Yazarlar:

Gülsüm Yiğit

Yayıncı:

Murat YAKAR

Ana Başlıklar:

Software Engineering (Other)

Dergi:

Turkish Journal of Engineering Vol.9 Issue 3, pp.571-577

Belge Tipi:

Makale

Yayın Tarihi:

1/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001339468

pISSN:

2587-1366