Search research articles

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

Efficacy of paraspinal muscle-sparing approach in the treatment of thoracolumbar burst fractures with neurological deficits.

Pakistan journal of medical sciences·2026

Same author

PainFedMVL: A Federated Multi-View Learning Approach for Multi-Level Pain Recognition.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same author

Andrographolide attenuates microglial senescence in Alzheimer's disease mice by suppressing the STAT3 signaling.

iScience·2026

Same author

Wavelet-Transformer Attention Network for Accurate Fetal ECG Estimation from Multi-Channel Abdominal Signals.

IEEE journal of biomedical and health informatics·2026

Same author

An Efficient Regenerated Cross-Modal Hashing: Improving Existing Hash Codes with the Arbitrary Length.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Lesion Learning Network with Relation Aware Transformer for Diabetic Retinopathy Grading.

IEEE journal of biomedical and health informatics·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 25, 2025

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

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

Published on: December 15, 2023

Multimodal Fusion Network for 3-D Lane Detection.

Taiheng Liu, Guang-Zhong Cao, Zhaoshui He

IEEE Transactions on Neural Networks and Learning Systems

|May 22, 2024

Summary

This study introduces a multimodal fusion network (MFNet) for 3-D lane detection, overcoming limitations of traditional methods. MFNet enhances accuracy by fusing RGB, depth, and point cloud data for robust lane feature extraction and prediction.

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Related Experiment Videos

Last Updated: Jun 25, 2025

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

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

Published on: December 15, 2023

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Area of Science:

Computer Vision
Machine Learning
Robotics

Background:

Traditional 3-D lane detection relies on handcrafted features and single modalities, leading to poor scalability and performance.
Challenges include lane diversity, occlusion, and lighting variations, hindering accuracy.

Purpose of the Study:

To propose a novel multimodal fusion network (MFNet) for robust and accurate 3-D lane detection.
To improve lane feature extraction and prediction by integrating diverse sensor data.

Main Methods:

Developed a multimodal fusion network (MFNet) incorporating multihead nonlocal attention and feature pyramid.
Introduced Multihead Deformable Transformation (MDT) for optimal multimodal feature extraction.
Designed Multidirectional Attention Feature Pyramid Fusion (MA-FPF) to fuse multi-scale features.
Implemented Top-View Lane Prediction (TLP) for 3-D lane estimation.

Main Results:

MFNet demonstrated superior performance over state-of-the-art methods on 3-D lane synthetic and ONCE-3DLanes datasets.
Qualitative and quantitative analyses confirmed the effectiveness of the proposed approach.
Visual comparisons highlighted improved lane detection accuracy and robustness.

Conclusions:

The proposed MFNet effectively addresses the challenges in 3-D lane detection.
Multimodal fusion with advanced attention mechanisms significantly enhances lane feature extraction and prediction accuracy.
MFNet offers a promising solution for real-world autonomous driving applications.