The LV dataset: A realistic surveillance video dataset for abnormal event detection

Roberto Leyva, Victor Sanchez, Chang Tsun Li

    Research output: Book chapter/Published conference paperConference paperpeer-review

    25 Citations (Scopus)

    Abstract

    In recent years, designing and testing video anomaly detection methods have focused on synthetic or unrealistic sequences. This has mainly four drawbacks: 1) events are controlled and predictable because they are usually performed by actors; 2) environmental conditions, e.g. camera motion and illumination, are usually ideal thus realistic conditions are not well reflected; 3) events are usually short and repetitive; and 4) the material is captured from scenarios that do not necessarily match the testing scenarios. This leads us to propose a new rich collection of realistic videos captured by surveillance cameras in challenging environmental conditions, the Live Videos (LV) dataset. We explore the performance of a number of state-of-the-art video anomaly detection methods on the LV dataset. Our results confirm the need to design methods that are capable of handling realistic videos captured by surveillance cameras with acceptable processing times. The proposed LV dataset, thus, will facilitate the design and testing of such new methods.
    Original languageEnglish
    Title of host publicationProceedings of the 5th International workshop on biometrics and forensics (IWBF 2017)
    Place of PublicationUnited States
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-6
    Number of pages6
    ISBN (Electronic)9781509057917
    ISBN (Print)9781509057924 (Print on demand)
    DOIs
    Publication statusPublished - 29 May 2017
    Event5th International Workshop on Biometrics and Forensics: IWBF 2017 - University of Warwick, Coventry, United Kingdom
    Duration: 04 Apr 201705 Apr 2017
    https://warwick.ac.uk/fac/sci/dcs/people/chang-tsun_li/iwbf2017/ (Conference website)

    Conference

    Conference5th International Workshop on Biometrics and Forensics
    Country/TerritoryUnited Kingdom
    CityCoventry
    Period04/04/1705/04/17
    OtherIWBF is an international forum devoted specifically to facilitate synergies in research and development in the areas of multimedia forensics, forensicbiometrics and forensic science. IWBF provides the meeting place for those concerned with the usage of multimedia analysis in forensic applications and biometric recognition systems, attracting participants from industry, research, academia and end-users.
    Internet address

    Fingerprint

    Dive into the research topics of 'The LV dataset: A realistic surveillance video dataset for abnormal event detection'. Together they form a unique fingerprint.

    Cite this