Data generation via diffusion models for crowd anomaly detection

Giulia Orru'
;
Riccardo Puddu;Simone Maurizio La Cava;Marco Micheletto;Gian Luca Marcialis
2025-01-01

Abstract

Crowd analysis is a critical aspect of public security and video surveillance. One of the primary challenges in developing effective crowd anomaly detectors is the lack of comprehensive training data. To address this issue, we investigate using synthetic data to enhance training for anomaly detection in crowded environments by generating a dataset of synthetic videos using two open-source diffusion models. Each synthetic video depicts typical crowded scenes that may be either normal or anomalous. To assess the effectiveness of our approach, we compare the model’s performance across three training scenarios: using only real videos, only synthetic videos, and a combination of both. This preliminary analysis highlights the potential of data generated via diffusion models to improve crowd anomaly detectors’ stability and classification capabilities.
2025
Inglese
35th British Machine Vision Conference 2024, BMVC 2024. Worshops Proceedings
BMVA press
13
https://bmva-archive.org.uk/bmvc/2024/workshops/SRBS/0005.pdf
35th British Machine Vision Conference 2024, BMVC 2024
Esperti anonimi
November 25-28, 2024
Glasgow, UK
internazionale
scientifica
no
4 Contributo in Atti di Convegno (Proceeding)::4.1 Contributo in Atti di convegno
Orru', Giulia; Lecca, Riccardo; Puddu, Riccardo; LA CAVA, SIMONE MAURIZIO; Micheletto, Marco; Marcialis, GIAN LUCA
273
6
4.1 Contributo in Atti di convegno
open
info:eu-repo/semantics/conferencePaper
Files in This Item:
File Size Format  
0005.pdf

open access

Type: versione editoriale
Size 2.47 MB
Format Adobe PDF
2.47 MB Adobe PDF View/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Questionnaire and social

Share on:
Impostazioni cookie