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: Jul 1, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

DSD-Mamba: Dual-Stream Semantic Segmentation of Remote Sensing Imagery via Dense-Sparse Fusion.

Xinyi Feng1, Shaochen Jiang1, Liejun Wang1

  • 1School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China.

Sensors (Basel, Switzerland)
|June 26, 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

UHPose-VAD: Unsupervised Video Anomaly Detection via Pose-Graph Learning and Normalizing Flow.

Journal of imaging·2026
Same author

DHAFormer: Dual-channel hybrid attention network with transformer for polyp segmentation.

PloS one·2024
Same author

Nonlinear Regularization Decoding Method for Speech Recognition.

Sensors (Basel, Switzerland)·2024
Same author

RFE-UNet: Remote Feature Exploration with Local Learning for Medical Image Segmentation.

Sensors (Basel, Switzerland)·2023
Same author

HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation.

Sensors (Basel, Switzerland)·2023
Same author

TC-Net: Dual coding network of Transformer and CNN for skin lesion segmentation.

PloS one·2022

This study introduces DSD-Mamba, a novel deep learning model for high-resolution remote sensing image segmentation. It enhances urban mapping by improving semantic segmentation accuracy in complex aerial scenes.

Area of Science:

  • Computer Vision
  • Remote Sensing
  • Artificial Intelligence

Background:

  • High-resolution remote sensing image segmentation is crucial for urban mapping.
  • Challenges include spectral ambiguity, scale variations, and background interference.

Purpose of the Study:

  • To improve semantic segmentation in complex aerial scenes.
  • To introduce DSD-Mamba, an asymmetric dual-stream architecture.

Main Methods:

  • Utilized a ResNet-18 encoder and proposed Dense-Sparse Pyramid Fusion Module (DSPFM).
  • Incorporated Scale-Aware Strip Attention (SASA) and a Dual-Stream Context Decoder (DSCD).
  • Employed Top-k selective value aggregation for feature filtering.

Main Results:

Keywords:
MambaTop-k selective aggregationUAV imagerydual-stream decoderhigh-resolution imageryremote sensing image segmentationstate space modelsstrip attention

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Related Experiment Videos

Last Updated: Jul 1, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

  • DSD-Mamba achieved mIoU scores of 73.4% (UAVid), 85.2% (Vaihingen), and 87.2% (Potsdam).
  • Ablation studies confirmed the effectiveness of DSPFM, SASA, and DSCD.
  • The full model demonstrated superior performance over the baseline.

Conclusions:

  • DSD-Mamba significantly improves segmentation accuracy in complex aerial scenes.
  • The model is accuracy-oriented, prioritizing performance over lightweight design.