Semi-supervised anomaly detection in video-surveillance scenes in the wild
Authors
Sarker, Mohammad Ibrahim; Losada Gutiérrez, Cristina; Marrón Romera, Marta; Fuentes Jiménez, David; Luengo Sánchez, SaraIdentifiers
Permanent link (URI): http://hdl.handle.net/10017/58360DOI: 10.3390/s21123993
ISSN: 1424-8220
Publisher
MDPI
Date
2021-06-04Funders
info:eu-repo/grantAgreement/UAH//CCG2020%2FIA-043
Agencia Estatal de Investigación
Ministerio de Economía y Competitividad
Universidad de Alcalá
Bibliographic citation
Sarker, M.I., Losada Gutiérrez, C., Marrón Romera, M., Fuentes Jiménez, D. & Luengo Sánchez, S. 2021, "Semi-supervised anomaly detection in video-surveillance scenes in the wild", Sensors, vol. 21, no. 12, art. no. 3993, pp. 1-20.
Keywords
Anomaly detection
RGB
CNN
Multiple instance learning
Video-surveillance
Project
info:eu-repo/grantAgreement/MINECO//TIN2016-75982-C2-1-R/ES/DETECCION SEMANTICA MULTISENSORIAL DE SITUACIONES ANOMALAS EN ENTORNOS SIN RESTRICCIONES/
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2016-80939-R/ES/RECONSTRUCCION DE OBJETOS DEFORMABLES A PARTIR DE IMAGENES Y SUS APLICACIONES A LA REALIDAD AUMENTADA EN CIRUGIA MINIMAMENTE INVASIVA/
info:eu-repo/grantAgreement/UAH//CCG2020%2FIA-043
info:eu-repo/grantAgreement/UAH//CCG2019%2FIA-024
Document type
info:eu-repo/semantics/article
Version
info:eu-repo/semantics/publishedVersion
Publisher's version
https://doi.org/10.3390/s21123993Rights
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Access rights
info:eu-repo/semantics/openAccess
Abstract
Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.
Files in this item
Files | Size | Format |
|
---|---|---|---|
Semi_supervised_Sarker_Sensors ... | 584.7Kb |
|
Files | Size | Format |
|
---|---|---|---|
Semi_supervised_Sarker_Sensors ... | 584.7Kb |
|
Collections
- ELECTRON - Artículos [245]