Abnormal crowd behaviour detection attracts a large interest due to its importance in video surveillance scenarios.However, the ambiguity and the lack of sufficient abnormal ground truth data makes end-to-end training of large deep networks hard in this domain. In this paper we propose to use Generative Adversarial Nets (GANs), which are trained to generate only the normal distribution of the data. During the adversarial GAN training, a discriminator (D) is used as a supervisor for the generator network(G) and vice versa. At testing time we use D to solve our discriminative task (abnormality detection), where D has been trained without the need of manually-annotated abnormal data. Moreover, in order to prevent G learn a trivial identity function, we use a cross-channel approach, forcing G to transform raw-pixel data in motion information and vice versa. The quantitative results on standard benchmarks show that our method outperforms previous state-of-the-art methods in both the frame-level and the pixel-level evaluation.

Training adversarial discriminators for cross-channel abnormal event detection in crowds / Ravanbakhsh, M.; Sangineto, E.; Nabi, M.; Sebe, N.. - (2019), pp. 1896-1904. (Intervento presentato al convegno IEEE Winter Conference on Application of Computer Vision tenutosi a Hawaii nel January 8-10, 2019) [10.1109/WACV.2019.00206].

Training adversarial discriminators for cross-channel abnormal event detection in crowds

E. Sangineto;M. Nabi;N. Sebe
2019-01-01

Abstract

Abnormal crowd behaviour detection attracts a large interest due to its importance in video surveillance scenarios.However, the ambiguity and the lack of sufficient abnormal ground truth data makes end-to-end training of large deep networks hard in this domain. In this paper we propose to use Generative Adversarial Nets (GANs), which are trained to generate only the normal distribution of the data. During the adversarial GAN training, a discriminator (D) is used as a supervisor for the generator network(G) and vice versa. At testing time we use D to solve our discriminative task (abnormality detection), where D has been trained without the need of manually-annotated abnormal data. Moreover, in order to prevent G learn a trivial identity function, we use a cross-channel approach, forcing G to transform raw-pixel data in motion information and vice versa. The quantitative results on standard benchmarks show that our method outperforms previous state-of-the-art methods in both the frame-level and the pixel-level evaluation.
2019
IEEE Winter Conference on Application of Computer Vision
New York
IEEE
978-1-7281-1975-5
Ravanbakhsh, M.; Sangineto, E.; Nabi, M.; Sebe, N.
Training adversarial discriminators for cross-channel abnormal event detection in crowds / Ravanbakhsh, M.; Sangineto, E.; Nabi, M.; Sebe, N.. - (2019), pp. 1896-1904. (Intervento presentato al convegno IEEE Winter Conference on Application of Computer Vision tenutosi a Hawaii nel January 8-10, 2019) [10.1109/WACV.2019.00206].
File in questo prodotto:
File Dimensione Formato  
08658774.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.56 MB
Formato Adobe PDF
1.56 MB Adobe PDF   Visualizza/Apri
1706.07680.pdf

Open Access dal 01/04/2021

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.1 MB
Formato Adobe PDF
1.1 MB 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/11572/250684
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 145
  • ???jsp.display-item.citation.isi??? 110
social impact