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 journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: May 17, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

333

Panoptic Image Segmentation Method Based on Dynamic Instance Query.

Lanshi Yang1, Shiguo Wang1, Shuhua Teng2

  • 1School of Computer Science and Technology, Changsha University of Science and Technology, Changsha 410076, China.

Sensors (Basel, Switzerland)
|May 14, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel panoptic segmentation method (PSM-DIQ) that uses dynamic instance queries to improve performance in complex scenes. PSM-DIQ enhances feature extraction and instance differentiation, outperforming existing static query methods.

Keywords:
deep learningdynamic instance queriesimage segmentationinstance segmentationpanoptic 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

2.6K
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

2.3K

Related Experiment Videos

Last Updated: May 17, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

333
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

2.6K
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

2.3K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Image Segmentation

Background:

  • Panoptic segmentation is crucial for autonomous driving and robot vision.
  • Current query-based deep learning methods often use static queries, limiting adaptability to scene complexity.
  • Static queries can lead to instance loss, confusion, and insufficient feature extraction.

Purpose of the Study:

  • To propose a novel panoptic segmentation method, PSM-DIQ, addressing limitations of static query mechanisms.
  • To enhance feature extraction and improve instance differentiation in complex scenes.
  • To optimize pixel-query interactions for better segmentation accuracy.

Main Methods:

  • Developed PSM-DIQ utilizing a multi-dimensional attention mechanism for enhanced feature extraction.
  • Implemented instance-activation-guided dynamic query generation for improved instance discrimination.
  • Employed a dual-path Transformer decoder to optimize pixel-query interactions.

Main Results:

  • PSM-DIQ significantly outperformed the Mask2Former baseline on Cityscapes and MS COCO datasets.
  • Achieved improvements of 1.8 and 1.7 percentage points in Panoptic Quality (PQ) using a ResNet-50 backbone.
  • Demonstrated effectiveness in handling complex scenes requiring accurate panoptic segmentation.

Conclusions:

  • PSM-DIQ effectively addresses the limitations of static queries in deep learning-based panoptic segmentation.
  • The dynamic instance query approach enhances model adaptability and segmentation accuracy in challenging environments.
  • The proposed method offers a significant advancement for real-world applications like autonomous driving.