Real-time Anomaly Detection and Localization in Crowded Scenes
aut.relation.endpage | 62 | |
aut.relation.startpage | 56 | |
aut.researcher | Klette, Reinhard | |
dc.contributor.author | Sabokrou, M | en_NZ |
dc.contributor.author | Fathy, M | en_NZ |
dc.contributor.author | Hoseini, M | en_NZ |
dc.contributor.author | Klette, R | en_NZ |
dc.date.accessioned | 2017-06-05T23:46:06Z | |
dc.date.available | 2017-06-05T23:46:06Z | |
dc.date.copyright | 2015 | en_NZ |
dc.date.issued | 2015 | en_NZ |
dc.description.abstract | In this paper, we propose a method for real-time anomaly detection and localization in crowded scenes. Each video is defined as a set of non-overlapping cubic patches, and is described using two local and global descriptors. These descriptors capture the video properties from different aspects. By incorporating simple and cost-effective Gaussian classifiers, we can distinguish normal activities and anomalies in videos. The local and global features are based on structure similarity between adjacent patches and the features learned in an unsupervised way, using a sparse autoencoder. Experimental results show that our algorithm is comparable to a state-of-the-art procedure on UCSD ped2 and UMN benchmarks, but even more time-efficient. The experiments confirm that our system can reliably detect and localize anomalies as soon as they happen in a video. | |
dc.identifier.citation | 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, 2015, pp. 56-62. | en_NZ |
dc.identifier.doi | 10.1109/CVPRW.2015.7301284 | en_NZ |
dc.identifier.isbn | 978-1-4673-6759-2 | en_NZ |
dc.identifier.uri | https://hdl.handle.net/10292/10519 | |
dc.publisher | IEEE | en_NZ |
dc.relation.uri | http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7301284&isnumber=7301265 | en_NZ |
dc.rights | Copyright © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
dc.rights.accessrights | OpenAccess | en_NZ |
dc.subject | Streaming media; Feature extraction; Training; Real-time systems; Gaussian distribution; Benchmark testing; Reliability | |
dc.title | Real-time Anomaly Detection and Localization in Crowded Scenes | en_NZ |
dc.type | Conference Contribution | |
pubs.elements-id | 194350 | |
pubs.organisational-data | /AUT | |
pubs.organisational-data | /AUT/Design & Creative Technologies | |
pubs.organisational-data | /AUT/Design & Creative Technologies/School of Engineering |