Real-time Anomaly Detection and Localization in Crowded Scenes

Simple item page
aut.relation.endpage62
aut.relation.startpage56
aut.researcherKlette, Reinhard
dc.contributor.authorSabokrou, Men_NZ
dc.contributor.authorFathy, Men_NZ
dc.contributor.authorHoseini, Men_NZ
dc.contributor.authorKlette, Ren_NZ
dc.date.accessioned2017-06-05T23:46:06Z
dc.date.available2017-06-05T23:46:06Z
dc.date.copyright2015en_NZ
dc.date.issued2015en_NZ
dc.description.abstractIn 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.citation2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, 2015, pp. 56-62.en_NZ
dc.identifier.doi10.1109/CVPRW.2015.7301284en_NZ
dc.identifier.isbn978-1-4673-6759-2en_NZ
dc.identifier.urihttps://hdl.handle.net/10292/10519
dc.publisherIEEEen_NZ
dc.relation.urihttp://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7301284&isnumber=7301265en_NZ
dc.rightsCopyright © 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.accessrightsOpenAccessen_NZ
dc.subjectStreaming media; Feature extraction; Training; Real-time systems; Gaussian distribution; Benchmark testing; Reliability
dc.titleReal-time Anomaly Detection and Localization in Crowded Scenesen_NZ
dc.typeConference Contribution
pubs.elements-id194350
pubs.organisational-data/AUT
pubs.organisational-data/AUT/Design & Creative Technologies
pubs.organisational-data/AUT/Design & Creative Technologies/School of Engineering
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1511.06936v1.pdf
Size:
2.68 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
RE4.10 Grant of Licence.docx
Size:
14.05 KB
Format:
Microsoft Word 2007+
Description:
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau