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: May 28, 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

Structural-Prior Deep Learning Network for Millimeter-Wave Radar Image Enhancement in Autonomous Driving Road

Hongyan Chen1, Tonghui Huang1, Yuexia Wang1

  • 1School of Transportation and Civil Engineering, Nantong University, Nantong 226019, China.

Sensors (Basel, Switzerland)
|May 27, 2026
PubMed
Summary
This summary is machine-generated.

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

Tumor-targeted activatable molecular agent for synergistic chemo-photodynamic therapy.

Bioorganic chemistry·2026
Same author

RIME-Net: A Physics-Guided Unpaired Learning Framework for Automotive Radar Interference Mitigation and Weak Target Enhancement.

Sensors (Basel, Switzerland)·2026
Same author

Folic acid-targeted Mn-doped carbon dots for controlled ROS amplification and FL/MR imaging-guided synergistic Sono-Chemodynamic Cancer therapy.

Journal of colloid and interface science·2025
Same author

Pedestrian Pose Recognition Based on Frequency-Modulated Continuous-Wave Radar with Meta-Learning.

Sensors (Basel, Switzerland)·2024
Same author

A Novel Optimized iBeacon Localization Algorithm Modeling.

Sensors (Basel, Switzerland)·2023
Same author

Corrigendum to A hypochlorite-activated strategy for realizing fluorescence turn-on, type I and type II ROS-combined photodynamic tumor ablation Biomaterials Volume 297, 122108, (2023).

Biomaterials·2023
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

This study introduces a deep learning network to enhance millimeter-wave radar images, improving road perception for autonomous driving by reducing speckle noise and preserving structural details.

Area of Science:

  • Computer Vision
  • Signal Processing
  • Autonomous Systems

Background:

  • Millimeter-wave (mmWave) radar is crucial for autonomous driving perception due to its weather robustness.
  • Speckle noise in mmWave radar images degrades structural continuity and target boundaries, hindering scene understanding.

Purpose of the Study:

  • To develop a deep learning framework for enhancing mmWave radar images by suppressing speckle noise.
  • To improve the structural fidelity and perception of road scenes and objects in autonomous driving.

Main Methods:

  • A structural-prior deep learning network utilizing an adaptive Otsu-based masking strategy for structural prior extraction.
  • A continuous attention mechanism integrating residual channel attention, context-aware feature extraction, and convolutional block attention.
Keywords:
autonomous drivingdeep learningmillimeter-wave radarstructural prior

Related Experiment Videos

Last Updated: May 28, 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

  • A composite loss function combining logarithmic denoising gain, total variation, and β-index edge preservation.

    • Main Results:

    • The proposed network significantly outperforms conventional and deep learning methods in PSNR, SSIM, β-index, and ENL.
    • Demonstrated superior preservation of road structures, target contours, and scene geometry on synthetic and real-world datasets.
    • Achieved a rapid inference latency of 12.35 milliseconds, indicating practical applicability.

    Conclusions:

    • The structural-prior deep learning network offers an effective and robust solution for mmWave radar image enhancement.
    • The method provides practical value for downstream road-scene perception tasks in autonomous driving.
    • The continuous attention and structural prior guidance are key to the network's performance.