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 author

Imaging Modalities in Inflammatory Breast Cancer (IBC) Diagnosis: A Computer-Aided Diagnosis System Using Bilateral Mammography Images.

Sensors (Basel, Switzerland)·2023
See all related articles

Related Experiment Video

Updated: Jan 18, 2026

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

1.0K

MINI-DROID-SLAM: Improving Monocular Visual SLAM Using MINI-GRU RNN Network.

Ismaiel Albukhari1, Ahmed El-Sayed2, Mohammad Alshibli3

  • 1Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT 06604, USA.

Sensors (Basel, Switzerland)
|September 13, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces MINI-DROID-SLAM, a deep-learning system enhancing Monocular Visual SLAM. It achieves improved robustness and efficiency by using a Mini-GRU (gated recurrent unit) for better camera localization.

Keywords:
Bundle AdjustmentCONV-GRUDROID-SLAMDeep LearningMini-GRUMonocular-SLAMSLAMVisual-SLAM

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

736
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

829

Related Experiment Videos

Last Updated: Jan 18, 2026

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

1.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

736
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

829

Area of Science:

  • Robotics
  • Computer Vision
  • Artificial Intelligence

Background:

  • Visual odometry and SLAM (Simultaneous Localization and Mapping) show promise but face real-time challenges.
  • Existing methods struggle with complexity and compatibility in dynamic environments.
  • LiDAR and 3D sensors have limitations in certain applications.

Purpose of the Study:

  • To present an enhanced deep-learning-based SLAM system for Monocular Visual SLAM.
  • To improve robustness and efficiency in camera position estimation.
  • To reduce computational complexity and processing time compared to existing SLAM networks.

Main Methods:

  • Utilized a Mini-GRU (gated recurrent unit) within a deep-learning framework.
  • Implemented pixel-wise depth mapping and Bundle Adjustment (BA) for pose estimation.
  • Trained the model on monocular camera images from the TartanAir datasets using a single GPU.

Main Results:

  • MINI-DROID-SLAM demonstrated significant improvements in robustness and persistent camera position iteration.
  • The proposed architecture reduced computation complexity and time compared to the original DROID-SLAM.
  • Evaluation using Absolute Trajectory Error (ATE) confirmed high performance and robustness.

Conclusions:

  • The MINI-DROID-SLAM system offers a more efficient and robust solution for Monocular Visual SLAM.
  • Deep learning with Mini-GRU integration enhances SLAM performance.
  • The system presents a viable alternative for real-time visual localization tasks.