Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Video Anomaly Detection With Compact Feature Sets for Online Performance.

Roberto Leyva, Victor Sanchez, Chang-Tsun Li

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 25, 2017
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Difference from Background: Limit of Detection01:05

    Difference from Background: Limit of Detection

    8.7K
    The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
    The LOD indicates the presence or absence...
    8.7K

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Outcomes of Laser Retinopexy for Retinal Tears by Fellow-Eye Detachment History.

    Ophthalmology. Retina·2026
    Same author

    Recommendations for genetic counseling for individuals at risk of autosomal dominant Alzheimer's disease in Latin America.

    Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
    Same author

    Endophthalmitis caused by gram-negative bacteria: etiologies, antibiotic susceptibilities, and treatment outcomes.

    Journal of ophthalmic inflammation and infection·2026
    Same author

    Automated detection of stereotyped animal sounds using data augmentation and transfer learning.

    Scientific reports·2026
    Same author

    Hierarchical Bayesian constitutive model selection for high-strain-rate soft material characterization.

    Soft matter·2026
    Same author

    First detection of Nyssorhynchus rondoniensis (Diptera: Culicidae) in southern Venezuela and its infection with Plasmodium falciparum.

    Acta tropica·2025

    This study introduces an efficient online framework for video anomaly detection using novel features and multiple inference models. It achieves superior performance compared to existing online methods and competitive results against non-online approaches.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Video anomaly detection research has yielded significant results, but online methodologies remain underdeveloped.
    • Existing methods often struggle with real-time processing demands for anomaly detection.

    Purpose of the Study:

    • To present a novel online framework for effective video anomaly detection.
    • To address the limitations of current online anomaly detection techniques.

    Main Methods:

    • Extraction of compact, descriptive features using a novel cell structure for coarse-to-fine support region definition.
    • Utilizing foreground occupancy and optical flow features, processed selectively based on scene activity.
    • Employing Gaussian Mixture Models, Markov Chains, and Bag-of-Words for inference, with joint spatio-temporal neighborhood analysis.

    Related Experiment Videos

    Main Results:

    • The proposed framework demonstrates superior performance over existing online video anomaly detection methods.
    • Achieves highly competitive detection accuracy when compared to state-of-the-art non-online methods.
    • Validated on diverse datasets, including a new one with realistic surveillance scenarios.

    Conclusions:

    • The novel online framework offers an efficient and accurate solution for video anomaly detection.
    • The compact feature set and multi-model inference contribute to its strong performance.
    • The framework shows promise for real-world surveillance and security applications.