Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/113705
Título: Inflated 3D ConvNet context analysis for violence detection
Autores/as: Freire Obregón, David Sebastián 
Barra, P
Castrillón Santana, Modesto Fernando 
De Marsico, M
Clasificación UNESCO: 120304 Inteligencia artificial
220990 Tratamiento digital. Imágenes
Palabras clave: Violence detection
People tracking
I3D model
Context analysis
Transfer learning
Fecha de publicación: 2022
Publicación seriada: Machine Vision and Applications 
Resumen: According to the Wall Street Journal, one billion surveillance cameras will be deployed around the world by 2021. This amount of information can be hardly managed by humans. Using a Inflated 3D ConvNet as backbone, this paper introduces a novel automatic violence detection approach that outperforms state-of-the-art existing proposals. Most of those proposals consider a pre-processing step to only focus on some regions of interest in the scene, i.e., those actually containing a human subject. In this regard, this paper also reports the results of an extensive analysis on whether and how the context can affect or not the adopted classifier performance. The experiments show that context-free footage yields substantial deterioration of the classifier performance (2% to 5%) on publicly available datasets. However, they also demonstrate that performance stabilizes in context-free settings, no matter the level of context restriction applied. Finally, a cross-dataset experiment investigates the generalizability of results obtained in a single-collection experiment (same dataset used for training and testing) to cross-collection settings (different datasets used for training and testing).
URI: http://hdl.handle.net/10553/113705
ISSN: 0932-8092
DOI: 10.1007/s00138-021-01264-9
Fuente: Machine Vision and Applications [ISSN 0932-8092], v. 33(1), (Enero 2022)
Colección:Artículos
Adobe PDF (1,8 MB)
Vista completa

Citas SCOPUSTM   

18
actualizado el 24-mar-2024

Visitas

54
actualizado el 03-jun-2023

Descargas

36
actualizado el 03-jun-2023

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.