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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

LFVB-BioSLAM: A Bionic SLAM System with a Light-Weight LiDAR Front End and a Bio-Inspired Visual Back End.

Biomimetics (Basel, Switzerland)·2023
Same author

IDSNN: Towards High-Performance and Low-Latency SNN Training via Initialization and Distillation.

Biomimetics (Basel, Switzerland)·2023
Same author

Direct training high-performance spiking neural networks for object recognition and detection.

Frontiers in neuroscience·2023
Same author

Stable Isotopes Reveal Photoreduction of Particle-Bound Mercury Driven by Water-Soluble Organic Carbon during Severe Haze.

Environmental science & technology·2022

Related Experiment Video

Updated: Jul 18, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Energy-Efficient Spiking Segmenter for Frame and Event-Based Images.

Hong Zhang1, Xiongfei Fan1, Yu Zhang1,2

  • 1State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.

Biomimetics (Basel, Switzerland)
|August 25, 2023
PubMed
Summary

This study introduces a Spiking Context Guided Network (Spiking CGNet) for energy-efficient semantic segmentation. The novel Spiking CGNet achieves comparable performance to artificial neural networks with significantly lower energy consumption on both frame and event-based cameras.

Keywords:
frame and event-based imagesneuromophic computingsemantic segmentationspiking context guided networkspiking neural network

More Related Videos

Automated Analysis of Dynamic Ca2+ Signals in Image Sequences
06:49

Automated Analysis of Dynamic Ca2+ Signals in Image Sequences

Published on: June 16, 2014

17.2K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K

Related Experiment Videos

Last Updated: Jul 18, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441
Automated Analysis of Dynamic Ca2+ Signals in Image Sequences
06:49

Automated Analysis of Dynamic Ca2+ Signals in Image Sequences

Published on: June 16, 2014

17.2K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Neuromorphic Engineering

Background:

  • Semantic segmentation is vital for autonomous systems, requiring energy-efficient models for mobile applications.
  • Existing artificial neural networks (ANNs) struggle with efficient segmentation across both frame and event-based cameras.
  • Spiking neural networks (SNNs) offer inherent energy efficiency on neuromorphic hardware.

Purpose of the Study:

  • To develop an energy-efficient semantic segmentation network capable of processing both frame and event-based images.
  • To introduce a novel spiking context guided block for feature and context extraction using spike computations.
  • To evaluate the performance and energy efficiency of the proposed Spiking CGNet against existing methods.

Main Methods:

  • Development of a Spiking Context Guided Network (Spiking CGNet) utilizing a novel spiking context guided block.
  • Direct training of Spiking CGNet variants (SCGNet-S and SCGNet-L) for frame and event-based image segmentation.
  • Verification on the Cityscapes (frame-based) and DDD17 (event-based) datasets.

Main Results:

  • SCGNet-S demonstrated comparable segmentation results to ANN CGNet on Cityscapes with 4.85x greater energy efficiency.
  • On the DDD17 dataset, Spiking CGNet significantly outperformed other spiking segmentation methods.
  • The proposed spiking context guided block effectively extracts local features and context information.

Conclusions:

  • Spiking CGNet offers a viable, energy-efficient solution for semantic segmentation in autonomous perception systems.
  • The developed SNN approach bridges the gap for efficient segmentation across diverse camera types.
  • This work highlights the potential of SNNs for low-power, high-performance computer vision tasks.