Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same authorSame journal

Spatial transcriptomics on an expanded dataset at the brain-electrode interface: exploration of variability and identification of novel biomarkers.

Frontiers in neuroscience·2026

Same author

Molecular Interplay of PARN and Telomerase: Tail Modifiers and Disease Implications.

Wiley interdisciplinary reviews. RNA·2026

Same author

Correction: F2,6BP restores mitochondrial genome integrity in Huntington's disease.

The Journal of biological chemistry·2026

Same author

Realization of a spin glass in a two-dimensional van der Waals material.

Science (New York, N.Y.)·2026

Same author

Retraction Note: Transgenic expression of an unedited mitochondrial orfB gene product from wild abortive (WA) cytoplasm of rice (Oryza sativa L.) generates male sterility in fertile rice lines.

Planta·2026

Same author

Higher-order neuromorphic Ising machines-autoencoders and Fowler-Nordheim annealers are all you need for scalability.

Nature communications·2026

Same journal

Sex-divergent intrinsic brain function in Parkinson's disease: elevated nigral fluctuations and premotor-visuospatial coupling in female patients.

Frontiers in neuroscience·2026

Same journal

A novel <i>de novo QRICH1</i> variant causing Ververi-Brady syndrome with infantile epileptic spasms syndrome: clinical and genetic analysis.

Frontiers in neuroscience·2026

Same journal

Distribution of bladder afferent activity across the sacral roots in sheep shows marked individual variation: implications for neuroprosthesis design.

Frontiers in neuroscience·2026

Same journal

Editorial: Neuromuscular disorders: biomarkers, precision diagnosis, and targeted therapeutics.

Frontiers in neuroscience·2026

Same journal

The exercise-microbiota-queuine-tRNA axis in Parkinson's disease: evidence, uncertainties, and experimental priorities.

Frontiers in neuroscience·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 24, 2025

Automated Measurements of Sleep and Locomotor Activity in Mexican Cavefish

Automated Measurements of Sleep and Locomotor Activity in Mexican Cavefish

Published on: March 21, 2019

EvAn: Neuromorphic Event-Based Sparse Anomaly Detection.

Lakshmi Annamalai^1,2, Anirban Chakraborty³, Chetan Singh Thakur²

¹Defence Research and Development Organisation (DRDO), Bangalore, India.

Frontiers in Neuroscience

|August 16, 2021

Summary

This summary is machine-generated.

Event-based cameras offer advantages for video anomaly detection. This study introduces a novel deep learning method using sparse convolutions and a DL memory surface for efficient and effective event-domain anomaly detection.

Keywords:

anomaly detection event data neuromorphic camera silicon retina sparse

More Related Videos

Patch-clamp Capacitance Measurements and Ca2+ Imaging at Single Nerve Terminals in Retinal Slices

Patch-clamp Capacitance Measurements and Ca2+ Imaging at Single Nerve Terminals in Retinal Slices

Published on: January 19, 2012

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Published on: September 20, 2016

Related Experiment Videos

Last Updated: Oct 24, 2025

Automated Measurements of Sleep and Locomotor Activity in Mexican Cavefish

Automated Measurements of Sleep and Locomotor Activity in Mexican Cavefish

Published on: March 21, 2019

Patch-clamp Capacitance Measurements and Ca2+ Imaging at Single Nerve Terminals in Retinal Slices

Patch-clamp Capacitance Measurements and Ca2+ Imaging at Single Nerve Terminals in Retinal Slices

Published on: January 19, 2012

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Published on: September 20, 2016

Area of Science:

Computer Vision
Artificial Intelligence
Sensor Technology

Background:

Event-based cameras offer advantages like low power, high dynamic range, and no motion blur due to asynchronous illumination change recording.
These cameras generate sparse data by encoding only relative motion, unlike conventional cameras that capture full frames.
Video anomaly detection is a critical application that can benefit from the unique properties of event-based sensors.

Purpose of the Study:

To propose a novel video anomaly detection solution operating directly in the event data domain.
To introduce a Deep Learning (DL) memory surface for encoding temporal information from event cameras while preserving data sparsity.
To address the lack of existing datasets by creating a new anomaly detection event dataset.

Main Methods:

Development of a conditional Generative Adversarial Network (cGAN) utilizing sparse submanifold convolution layers for anomaly detection.
Introduction of an unsupervised deep learning approach to generate a DL memory surface for temporal information encoding.
Creation and utilization of a new dataset for anomaly detection in the event domain, alongside an existing online dataset.

Main Results:

The proposed cGAN architecture with sparse convolutions demonstrates effective anomaly detection in the event domain.
The DL memory surface successfully encodes temporal dynamics from sparse event data.
Empirical validation on both the proposed and online datasets shows significant reduction in computational complexity compared to frame-based methods.

Conclusions:

The developed event-domain anomaly detection method offers a computationally efficient and high-performing alternative to traditional frame-based approaches.
Event-based cameras and the proposed deep learning techniques show great promise for advanced video analytics.
The new dataset facilitates further research and development in event-based video anomaly detection.