RPEE-Heads Benchmark: A Dataset and Empirical Comparison of Deep Learning Algorithms for Pedestrian Head Detection in Crowds

The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings such as high dense railway platforms and event entrances. These environments, characterized by dense crowds and dynamic movements, are underrep...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE access Ročník 13; s. 73451 - 73467
Hlavní autori: Abubaker, Mohamad, Alsadder, Zubayda, Abdelhaq, Hamed, Boltes, Maik, Alia, Ahmed
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: IEEE 2025
Predmet:
Accuracy
Annotations
Computer vision
Deep learning
Head
machine learning
Magnetic heads
object detection algorithms
pedestrian head detection
Pedestrians
public dataset
Rail transportation
railway platforms and event entrances
real-time detection transformer
Training
Transformers
YOLO
you only look once
ISSN:2169-3536, 2169-3536
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings such as high dense railway platforms and event entrances. These environments, characterized by dense crowds and dynamic movements, are underrepresented in public datasets, posing challenges for existing deep learning models. To address this gap, we introduce the Railway Platforms and Event Entrances-Heads (RPEE-Heads) dataset, a novel, diverse, high-resolution, and accurately annotated resource. It includes 109,913 annotated pedestrian heads across 1,886 images from 66 video recordings, with an average of 56.2 heads per image. Annotations include bounding boxes for visible head regions. In addition to introducing the RPEE-Heads dataset, this paper evaluates eight state-of-the-art object detection algorithms using the dataset and analyzes the impact of head size on detection accuracy. The experimental results show that You Only Look Once v9 and Real-Time Detection Transformer outperform the other algorithms, achieving mean average precisions of 90.7% and 90.8%, with inference times of 11 and 14 milliseconds, respectively. Moreover, the findings underscore the need for specialized datasets like RPEE-Heads for training and evaluating accurate models for head detection in railway platforms and event entrances. The dataset and pretrained models are available at https://doi.org/10.34735/ped.2024.2 .
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2025.3563311