Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/16751
Title: A Deep Learning Based Technique for Anomaly Detection in Surveillance Videos
Authors: Singh P.
Pankajakshan V.
Published in: Proceedings of 2018 24th National Conference on Communications, NCC 2018
Abstract: In this paper the problem of anomaly detection in surveillance videos is addressed, which refers to the detection of events that do not conform to normal behaviour. To solve this problem, this paper proposes an approach that utilizes a Deep Neural Network (DNN) to model normal behaviour. Specifically, a DNN is built that learns to predict future frames from past frames using a normal (anomaly free) dataset. The predictions from the model are then compared with testing video for similarity, and the resulting error is used to detect anomalies. Benchmarks of the proposed approach on two datasets common in the anomaly detection literature show that it performs comparably to other methods in the literature, even though it does not rely on any hand-crafted features. Moreover, comparison to other deep learning techniques in the literature shows that the proposed approach is significantly less complex. © 2018 IEEE.
Citation: Proceedings of 2018 24th National Conference on Communications, NCC 2018, (2019)
URI: https://doi.org/10.1109/NCC.2018.8599969
http://repository.iitr.ac.in/handle/123456789/16751
Issue Date: 2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Deep neural networks
Security systems
Learning techniques
Surveillance video
Anomaly detection
ISBN: 9.78E+12
Author Scopus IDs: 57206269701
6506890403
Author Affiliations: Singh, P., IIT Roorkee, Dept. of Electronics and Communication Engineering, Roorkee, Uttarakhand, India
Pankajakshan, V., IIT Roorkee, Dept. of Electronics and Communication Engineering, Roorkee, Uttarakhand, India
Appears in Collections:Conference Publications [ECE]

Files in This Item:
There are no files associated with this item.
Show full item record


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