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 Video

Updated: Mar 25, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

Local-Contextual Feature Fusion Network Based on Nonlinear Spiking Neural Model for Semantic Segmentation of Remote

Junhao Du1, Hong Peng1, Bing Li1

  • 1School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China.

International Journal of Neural Systems
|March 24, 2026
PubMed
Summary

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

Spiking Neural Membrane Systems with Temporal Coding.

International journal of neural systems·2026
Same author

An Attention-Gated Graph Spiking Neural Membrane System for Structure-Activity Relationship Prediction.

International journal of neural systems·2026
Same author

Knowledge Graph Embedding Model Based on Spiking Neural-like Graph Attention Network for Relation Prediction.

International journal of neural systems·2025
Same author

A Multivariate Cloud Workload Prediction Method Integrating Convolutional Nonlinear Spiking Neural Model with Bidirectional Long Short-Term Memory.

International journal of neural systems·2025
Same author

A Salient Object Detection Network Enhanced by Nonlinear Spiking Neural Systems and Transformer.

International journal of neural systems·2025
Same author

Nonlinear Spiking Neural Systems for Thermal Image Semantic Segmentation Networks.

International journal of neural systems·2025

This study introduces a new deep learning network for semantic segmentation of remote sensing images, improving land monitoring and environmental protection with enhanced feature recovery. The model achieves high accuracy on benchmark datasets.

Area of Science:

  • Computer Science
  • Remote Sensing
  • Artificial Intelligence

Background:

  • Semantic segmentation of remote sensing (RS) images is vital for geographic research, land monitoring, and environmental protection.
  • Deep learning models, including Convolutional Neural Networks (CNNs) and Transformers, have shown effectiveness in RS image semantic segmentation.
  • Increasing RS image resolution and scene complexity, especially in urban areas, presents challenges due to rich textures, edges, and irregular object distributions.

Purpose of the Study:

  • To propose a novel semantic segmentation network for remote sensing images that addresses challenges posed by high-resolution and complex urban scenes.
  • To enhance feature recovery in the decoder by effectively utilizing local contextual features.
  • To improve the accuracy and effectiveness of semantic segmentation for remote sensing applications.
Keywords:
Remote sensingdeep learningnonlinear spiking neural P systemssemantic segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Related Experiment Videos

Last Updated: Mar 25, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Main Methods:

  • An encoder-decoder architecture is employed, utilizing four ResNet-18 blocks as encoders and four custom local-contextual Transformer blocks as decoders.
  • A channel attention-feature fusion module, incorporating a novel nonlinear spiking neuron model, is designed to aid the decoder in feature recovery.
  • The proposed network is evaluated on benchmark datasets such as Potsdam, Vaihingen, LoveDA, and UAVid.

Main Results:

  • The proposed method demonstrates feasibility and effectiveness for semantic segmentation of remote sensing images.
  • Achieved mean Intersection over Union (mIoU) scores of 86.42% (suboptimal) and 82.25% (optimal) on the Potsdam and Vaihingen datasets, respectively.
  • Obtained mIoU scores of 52.4% (best) and 65.3% (near-optimal) on the LoveDA and UAVid datasets, respectively.

Conclusions:

  • The developed semantic segmentation network is effective for processing high-resolution remote sensing images with complex scenes.
  • The integration of local-contextual Transformer blocks and the novel channel attention-feature fusion module significantly contributes to improved feature recovery.
  • The experimental results validate the proposed model's performance on diverse remote sensing datasets, highlighting its potential for practical applications.