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

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

304
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...
304

You might also read

Related Articles

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

Sort by
Same author

Sliding physical invariant neural operator for long-term prediction of complex dynamics in physical systems.

National science review·2026
Same author

Enhancing ethanol-driven chain elongation via iron speciation: impacts on metabolic flux and dual FAB/RBO pathway activation.

Bioresource technology·2026
Same author

Integrated Transcriptomic and Metabolomic Analysis Reveals Gut Microbiota-Mediated Regulation of Muscle Fiber Composition and Metabolism in Germ-Free Pigs.

Animal genetics·2026
Same author

Graph Rotation Network: Equivariant Graph Neural Network for Efficient Inverse Design in 4-D Printing.

IEEE transactions on neural networks and learning systems·2026
Same author

A bio-inspired customizable mechanical central pattern generator enables one-to-many scalable pneumatic control.

Communications engineering·2026
Same author

Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation.

Nature communications·2026

Related Experiment Video

Updated: Dec 20, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

587

Large-Scale Place Recognition Based on Camera-LiDAR Fused Descriptor.

Shaorong Xie1, Chao Pan2, Yaxin Peng3

  • 1School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China.

Sensors (Basel, Switzerland)
|May 23, 2020
PubMed
Summary

This study introduces a novel sensor fusion network for autonomous driving place recognition. By combining camera and LiDAR data, the system achieves more robust and accurate localization than using individual sensors.

Keywords:
deep learningplace recognitionretrievalsensor fusion

More Related Videos

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

335
Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.3K

Related Experiment Videos

Last Updated: Dec 20, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

587
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

335
Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.3K

Area of Science:

  • Robotics and Artificial Intelligence
  • Computer Vision and Sensor Fusion

Background:

  • Autonomous vehicles rely on sensors like cameras and LiDAR for navigation.
  • Cameras face illumination and occlusion challenges, while LiDAR has motion distortion and limited range issues.
  • Sensor fusion is crucial for overcoming individual sensor limitations in autonomous driving.

Purpose of the Study:

  • To develop a robust place recognition system for autonomous driving by fusing camera and LiDAR data.
  • To enhance the accuracy and reliability of localization in diverse environmental conditions.
  • To address the limitations of single-sensor perception systems.

Main Methods:

  • A novel fusion network designed to capture robust image and 3D point cloud descriptors.
  • Implementation of a trimmed strategy for point cloud global feature aggregation.
  • Development of a compact fusion framework and a learned metric for fused feature similarity.

Main Results:

  • The proposed fusion network effectively integrates visual and 3D spatial information.
  • The trimmed strategy significantly improves point cloud feature aggregation and recognition performance.
  • Experiments on KITTI and KAIST datasets demonstrate superior performance over single-sensor methods.

Conclusions:

  • Sensor fusion of camera and LiDAR data provides a more robust and discriminative descriptor for place recognition.
  • The proposed compact fusion framework and feature aggregation strategy enhance localization accuracy.
  • This approach offers a promising solution for reliable navigation in autonomous driving systems.