Communication Dans Un Congrès Année : 2025

eCHFD : extended Ceasefire Hierarchical Firearm Dataset

Sylvie Chambon

Résumé

In recent years, the demand for large, diverse, and well-annotated firearm datasets has grown, particularly for advancing firearm recognition systems. However, existing datasets often lack sufficient variety in viewpoints, configurations, and model versions. To address these challenges, this paper introduces an extented version of the Ceasefire Hierarchical Firearm Dataset (eCHFD), a large image dataset of firearms consisting of over 93,000 images in 505 classes. It was constructed from more than 240 videos filmed at the Toulouse Forensics Laboratory (France) and further enriched with images from the existing CHFD dataset and additional downloaded images. Automated post-processing techniques were employed to efficiently build this large-scale dataset. In addition, a hierarchical annotation scheme validated by forensics experts was used to classify firearms at multiple levels, enabling its utility for fine-grained classification tasks. Experimental results was conducted using models such as HERBS and FGVC-PIM to demonstrate the effectiveness of the dataset.

Dates et versions

hal-05056799 , version 1 (05-05-2025)

Identifiants

Citer

Loubna Lechelek, Sylvie Chambon, Alain Crouzil, Saddam Abdulwahab, Grégory Jalabert, et al.. eCHFD : extended Ceasefire Hierarchical Firearm Dataset. MMSys '25: 16th ACM Multimedia Systems Conference, Mar 2025, Stellenbosch, South Africa, South Africa. pp.214-220, ⟨10.1145/3712676.3718333⟩. ⟨hal-05056799⟩
109 Consultations
0 Téléchargements

Altmetric

Partager

  • More