Conference paper Open Access

A Crowd Analysis Framework for Detecting Violence Scenes

Konstantinos Gkountakos; Konstantinos Ioannidis; Theodora Tsikrika; Stefanos Vrochidis; Ioannis Kompatsiaris

This work examines violence detection in video scenes of crowds and proposes a crowd violence detection framework based on a 3D convolutional deep learning architecture, the 3D-ResNet model with 50 layers. The proposed framework is evaluated on the Violent Flows dataset against several state-of-the-art approaches and achieves higher accuracy values in almost all cases, while also performing the violence detection activities in (near) real-time.

Files (2.0 MB)
Name Size
A_Crowd_Analysis_Framework_for_Detecting_Violence_Scenes_v0.1.pdf
md5:a15d1fa1d7fb2fb5a576dbe7292b30de
2.0 MB Download
86
49
views
downloads
All versions This version
Views 8686
Downloads 4949
Data volume 97.5 MB97.5 MB
Unique views 6161
Unique downloads 4242

Share

Cite as