Jove
Visualize
Contact Us

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

Characteristic investigation of digital control four quadrant electro-hydrostatic actuator with separated hydraulic motor.

The Review of scientific instruments·2024
Same author

A Survey of Needle Steering Approaches in Minimally Invasive Surgery.

Annals of biomedical engineering·2024
Same author

Development of a large flow electro-hydrostatic actuator equipped with four magnetostrictive-actuated pumps.

The Review of scientific instruments·2024
Same author

Bilateral teleoperation with object-adaptive mapping.

Complex & intelligent systems·2022
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: Dec 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

876

Study on the Influence of Image Noise on Monocular Feature-Based Visual SLAM Based on FFDNet.

Like Cao1, Jie Ling1, Xiaohui Xiao1

  • 1Hubei Key Laboratory of Waterjet Theory and New Technology, Wuhan University, Wuhan 430072, China.

Sensors (Basel, Switzerland)
|September 4, 2020
PubMed
Summary

Image noise significantly impacts visual Simultaneous Localization and Mapping (SLAM). Denoising images improves feature matching and trajectory accuracy, enhancing SLAM performance, especially with the ORB algorithm.

Keywords:
FFDNetdatasetfeature matchingimage denoisingvisual SLAM

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.5K
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

950

Related Experiment Videos

Last Updated: Dec 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

876
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.5K
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

950

Area of Science:

  • Computer Vision
  • Robotics
  • Image Processing

Background:

  • Real-world camera images contain noise, affecting visual Simultaneous Localization and Mapping (SLAM) system accuracy.
  • Feature-based visual SLAM algorithms rely on accurate image feature detection and matching, which are sensitive to noise.

Purpose of the Study:

  • To investigate the influence of image noise on monocular feature-based visual SLAM.
  • To evaluate the effectiveness of image denoising techniques in improving SLAM performance.

Main Methods:

  • Utilized an open-source synthetic dataset with varying noise levels.
  • Applied Fast and Flexible Denoising convolutional neural Network (FFDNet) for image denoising.
  • Compared feature matching algorithms (SIFT, SURF, ORB) on noisy and denoised images.
  • Evaluated Absolute Trajectory Error (ATE) using ORB-SLAM2 on noisy and denoised sequences.

Main Results:

  • ORB demonstrated a higher correct matching rate than SIFT and SURF.
  • Denoised images yielded higher correct matching rates compared to noisy images.
  • Denoised sequences consistently outperformed noisy sequences in terms of ATE across all noise levels.
  • Denoising reduced ATE RMSE by 16.75% for a clean sequence and improved 7 out of 10 KITTI sequences.

Conclusions:

  • Image denoising can significantly enhance the accuracy of monocular feature-based visual SLAM.
  • The ORB feature descriptor is robust to noise, and denoising further improves its performance.
  • Denoising is a viable strategy to improve SLAM accuracy in noisy environments, particularly with algorithms like ORB-SLAM2.