Autoencoder‐based abnormal activity detection using parallelepiped spatio‐temporal region. Issue 1 (30th November 2018)

• Record Type: Journal Article
• Authors: George, Michael; Jose, Babita Roslind; Mathew, Jimson; Kokare, Pranjali
• Is Part Of: IET computer vision. Volume 13:Issue 1(2019)
• Page Start: 23
• Page End: 30
• Publication Date: 2018-11-30
• Subjects: video signal processing -- image motion analysis -- object detection -- feature extraction -- video surveillance -- image sequences -- video cameras -- image reconstruction -- neural nets; standard abnormality detection datasets -- autoencoder-based abnormal activity detection -- parallelepiped spatio-temporal region -- surveillance cameras -- manual monitoring system -- automatic abnormal activity detection -- spatio-temporal feature -- novel nonuniform spatio-temporal region -- histogram of optical flow orientation and magnitude -- HOFM feature extraction -- surveillance video feeds; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5240
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : The spread of surveillance cameras has necessitated the monitoring of large quantities of surveillance video feeds. A manual monitoring system is near impossible due to the large man‐hour requirements. Recently, automatic abnormal activity detection has been an area of interest among researchers. A spatio‐temporal feature, histogram of optical flow orientation and magnitude (HOFM), has produced impressive ability in detecting abnormal activities. The authors propose a novel non‐uniform spatio‐temporal region resembling parallelepipeds, from which they extract the HOFM features. Autoencoders can be configured to detect abnormal patterns. The authors have used these abilities of the autoencoders to detect abnormalities in the HOFM features extracted from their novel spatio‐temporal regions of the video feeds. The autoencoders are trained on the HOFM features of the videos containing no abnormalities. The autoencoders are then fed with the HOFM features of the videos to be tested for abnormal activities, and these are detected based on the abilities of the autoencoders to reconstruct these features. The proposed method is tested on the standard abnormality detection datasets: UCSD Ped1, UCSD Ped2, Subway Entrance, Subway Exit, and UMN.