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

SGMR-LPR: A Semantic-Guided Network Robust to Movable Objects for LiDAR-Based Place Recognition.

Weizhong Jiang1, Zhipeng Xiao1, Lilin Qian1

  • 1Defense Innovation Institute, Beijing 100071, China.

Sensors (Basel, Switzerland)
|May 27, 2026
PubMed
Summary

Related Concept Videos

Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device01:30

Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device

Surveyors use Global Positioning System (GPS) technology to measure the precise location and elevation of points on Earth. In a recent survey, GPS receivers were used to determine the coordinates and elevations of two park monuments. The process involved careful mission planning, data collection, and correction to ensure accuracy. The survey began with mission planning to identify optimal satellite visibility and minimize Position Dilution of Precision (PDOP). A geodetic control point served as...

You might also read

Related Articles

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

Sort by
Same author

A case report of synchronous bilateral breast cancer with distinct histological subtypes and favorable long-term survival.

Frontiers in oncology·2026
Same author

The impact of drought stress on the physiological biochemical indexes and metabolites in Panax notoginseng.

Scientific reports·2026
Same author

Reinventing Cellulose into Sustainable and Versatile Bioplastics via Molecular-Scale Design.

Research (Washington, D.C.)·2026
Same author

Case Report: Serum IgG4-negative multifocal IgG4-related hepatic inflammatory pseudotumor: dissociation between circulating IgG4 and local immune activation.

Frontiers in immunology·2026
Same author

Smart molecular design for functional cellulose gels and flexible devices.

Smart molecules : open access·2026
Same author

Cellulosic Engineering Plastic with High Shapeability, Recyclability, Lightweight and High-Strength Properties.

Advanced materials (Deerfield Beach, Fla.)·2026

This study introduces SGMR-LPR, a novel framework for robust LiDAR-based place recognition (LPR) in dynamic environments. It effectively suppresses interference from movable objects, enhancing scene understanding for autonomous systems.

Area of Science:

  • Robotics and Autonomous Systems
  • Computer Vision
  • Remote Sensing

Background:

  • Processing LiDAR point clouds in dynamic outdoor environments presents challenges due to movable objects like vehicles and pedestrians.
  • LiDAR-based place recognition (LPR) is crucial for autonomous systems but is susceptible to dynamic scene elements.
  • Existing LPR methods often rely on external segmentation models or lack effective mechanisms to handle uncertain movable object predictions.

Purpose of the Study:

  • To develop an end-to-end framework for robust LiDAR-based place recognition (LPR) that explicitly addresses movable object interference.
  • To enhance the reliability of LPR in dynamic outdoor environments for applications in remote sensing and autonomous navigation.

Main Methods:

  • Proposed SGMR-LPR, an end-to-end semantic-guided framework for LiDAR point cloud processing.
Keywords:
3D point cloud processingBEV feature modulationLiDAR-based place recognitionattention mechanismmovable objects robustnessscene understandingsemantic guidance

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

  • Introduced a probabilistic movable object masking (PMOM) module to generate uncertainty-aware masks of movable regions.
  • Developed a movable-suppressed channel-spatial attention (MSCS) module to adaptively modulate features, suppressing movable objects and enhancing stable structures.

    • Main Results:

    • SGMR-LPR demonstrated enhanced robustness in place recognition without requiring external semantic models at inference.
    • The framework achieved consistent performance gains across multiple benchmarks, especially in scenes with dense movable objects.
    • The proposed method effectively suppresses movable object interference, improving point cloud-based scene understanding.

    Conclusions:

    • SGMR-LPR offers a robust solution for LiDAR-based place recognition in dynamic environments.
    • The explicit integration of movable object awareness into feature modulation enhances system reliability.
    • This work advances reliable scene understanding for autonomous systems operating in complex, dynamic outdoor settings.