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

Smart mobility infrastructure: improving campus parking efficiency in real time.

Scientific reports·2026
Same author

Enhanced performance of a hybrid PV/T V-shaped solar still using a graphene-silver-silica composite.

Scientific reports·2026
Same author

Deep learning-driven IoT solution for smart tomato farming.

Scientific reports·2025
Same author

Morphological, molecular, and pharmacological review of veldt grape (<i>Cissus quadrangularis</i> L.): an underutilized medicinal plant.

Frontiers in plant science·2025
Same author

Energy-efficient quad tree-based clustering using edge-assisted UAV-relay to enhance network lifetime in WSN.

Scientific reports·2024
Same author

Scrutinizing transport phenomena and recombination mechanisms in thin film Sb<sub>2</sub>S<sub>3</sub> solar cells.

Scientific reports·2024

Related Experiment Video

Updated: May 7, 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

426

Multi-sensor fusion and segmentation for autonomous vehicle multi-object tracking using deep Q networks.

K Vinoth1, P Sasikumar2

  • 1School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.

Scientific Reports
|December 29, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a multi-sensor fusion and segmentation approach for autonomous vehicles to improve object tracking in adverse weather conditions. The system enhances navigation safety by effectively processing camera and LiDAR data for reliable detection and path planning.

Keywords:
Dense net (D net)Energy Valley Optimizer (EVO)Multi-sensor fusionSegmentationSelf-driving vehiclesYOLO V7 model

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

318

Related Experiment Videos

Last Updated: May 7, 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

426
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

318

Area of Science:

  • Computer Vision
  • Robotics
  • Artificial Intelligence

Background:

  • Autonomous vehicles face navigation challenges due to obscured markings and sensor limitations in adverse weather.
  • Existing solutions lack robustness in real-world driving conditions, posing safety risks.

Purpose of the Study:

  • To develop a robust multi-sensor fusion and segmentation system for multi-object tracking in self-driving cars.
  • To enhance the safety and reliability of autonomous navigation under various environmental conditions.

Main Methods:

  • Implemented a pipeline for camera and LiDAR data processing, including noise reduction with Improved Adaptive Extended Kalman Filter (IAEKF).
  • Utilized NGT-CLAHE for contrast enhancement and IAWMF for adaptive thresholding during preprocessing.
  • Employed multi-segmentation techniques, dense net-based image fusion, YOLO V7 for object detection, and Energy Valley Optimizer (EVO) for path planning.

Main Results:

  • The proposed system demonstrates improved efficiency and processing speed through dense net-based fusion.
  • Achieved effective object detection and categorization using YOLO V7.
  • The EVO approach facilitated flexible, resilient, and scalable path and lane selection.

Conclusions:

  • The integrated multi-sensor fusion and segmentation approach significantly enhances autonomous vehicle perception and navigation capabilities.
  • The system offers a promising solution for safe and reliable self-driving in challenging environmental conditions.