The automatic detection of violence and crimes in videos is gaining attention, specifically as a tool to unburden security officers and authorities from the need to watch hours of footages to identify event lasting few seconds. So far, most of the available datasets was composed of few clips, in low resolution, often built on too specific cases (e.g. hockey fight). While high resolution datasets are emerging, there is still the need of datasets to test the robustness of violence detection techniques to false positives, due to behaviours which might resemble violent actions. To this end, we propose a dataset composed of 350 clips (MP4 video files, 1920 x 1080 pixels, 30 fps), labelled as non-violent (120 clips) when representing non-violent behaviours, and violent (230 clips) when representing violent behaviours. In particular, the non-violent clips include behaviours (hugs, claps, exulting, etc.) that can cause false positives in the violence detection task, due to fast movements and the similarity with violent behaviours. The clips were performed by non-professional actors, varying from 2 to 4 per clip.

A dataset for automatic violence detection in videos / Bianculli, M; Falcionelli, N; Sernani, P; Tomassini, S; Contardo, P; Lombardi, M; Dragoni, Af. - In: DATA IN BRIEF. - ISSN 2352-3409. - ELETTRONICO. - 33:(2020), pp. 1065871-1065876. [10.1016/j.dib.2020.106587]

A dataset for automatic violence detection in videos

Tomassini, S;
2020-01-01

Abstract

The automatic detection of violence and crimes in videos is gaining attention, specifically as a tool to unburden security officers and authorities from the need to watch hours of footages to identify event lasting few seconds. So far, most of the available datasets was composed of few clips, in low resolution, often built on too specific cases (e.g. hockey fight). While high resolution datasets are emerging, there is still the need of datasets to test the robustness of violence detection techniques to false positives, due to behaviours which might resemble violent actions. To this end, we propose a dataset composed of 350 clips (MP4 video files, 1920 x 1080 pixels, 30 fps), labelled as non-violent (120 clips) when representing non-violent behaviours, and violent (230 clips) when representing violent behaviours. In particular, the non-violent clips include behaviours (hugs, claps, exulting, etc.) that can cause false positives in the violence detection task, due to fast movements and the similarity with violent behaviours. The clips were performed by non-professional actors, varying from 2 to 4 per clip.
2020
Bianculli, M; Falcionelli, N; Sernani, P; Tomassini, S; Contardo, P; Lombardi, M; Dragoni, Af
A dataset for automatic violence detection in videos / Bianculli, M; Falcionelli, N; Sernani, P; Tomassini, S; Contardo, P; Lombardi, M; Dragoni, Af. - In: DATA IN BRIEF. - ISSN 2352-3409. - ELETTRONICO. - 33:(2020), pp. 1065871-1065876. [10.1016/j.dib.2020.106587]
File in questo prodotto:
File Dimensione Formato  
2020 - DiB (2).pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 715.85 kB
Formato Adobe PDF
715.85 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/403287
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 36
  • ???jsp.display-item.citation.isi??? 20
social impact