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 Experiment Video

Updated: Jun 26, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Improved object detection method for unmanned driving based on Transformers.

Huaqi Zhao1, Xiang Peng1, Su Wang1

  • 1The Heilongjiang Provincial Key Laboratory of Autonomous Intelligence and Information Processing, School of Information and Electronic Technology, Jiamusi University, Jiamusi, China.

Frontiers in Neurorobotics
|May 16, 2024
PubMed
Summary
This summary is machine-generated.

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

Leveraging Feature Alignment in Grassmannian Manifold for Multi-Output Regression Tasks.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Video-based hand gesture recognition via SPD manifold spatial representation and optical flow motion features.

PloS one·2026
Same author

Ultrafast Synthesis of Phosphorus-Doped RuMoO<sub>x</sub> Electrocatalyst via Pulsed Joule Heating for Efficient Hydrogen Evolution.

Chemphyschem : a European journal of chemical physics and physical chemistry·2026
Same author

Multilayer Perceptron Grouping and Sparse Gaussian Process-Based Surrogate-Assisted Evolutionary Algorithm for Expensive Multiobjective Optimization.

IEEE transactions on cybernetics·2025
Same author

SleepHybridNet: A Lightweight Hybrid CNN-Transformer Model for Enhanced N1 Sleep Staging From Single-Channel EEG.

IEEE journal of biomedical and health informatics·2025
Same author

Multiscale SPD manifold learning for rehabilitation exercise evaluation.

Scientific reports·2025
Same journal

DSPE-ViT: a lightweight vision transformer with dynamic sparse positional encoding for dense small object detection in UAV imagery.

Frontiers in neurorobotics·2026
Same journal

ST-HONet: Spatio-Temporal Hierarchical Network for long-horizon bimanual visuomotor imitation.

Frontiers in neurorobotics·2026
Same journal

ST-HADP: Spatio-Temporal hierarchical attention diffusion policy for long-horizon generalizable bimanual visuomotor imitation.

Frontiers in neurorobotics·2026
Same journal

EQISP: efficient quantized image signal processing with multi-scale pyramid fusion for resource constrained embodied perception.

Frontiers in neurorobotics·2026
Same journal

Research on embodied agent multimodal perception and real-time path planning algorithms for complex unstructured environments.

Frontiers in neurorobotics·2026
Same journal

NL-YOLOv5: a model with a larger receptive field and the ability to globally acquire features.

Frontiers in neurorobotics·2026
See all related articles

This study introduces an improved object detection method for unmanned driving using Transformer architecture. The new approach enhances multi-scale detection, small object accuracy, and reduces false positives, achieving a 3% higher mean Average Precision (mAP).

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • Object detection is crucial for unmanned driving perception systems.
  • Existing methods struggle with multi-scale objects, small object accuracy, and occlusions.
  • Transformer architecture offers potential for advanced feature extraction.

Purpose of the Study:

  • To improve object detection performance in complex unmanned driving scenarios.
  • To address limitations in multi-scale detection, small object recognition, and occlusion handling.
  • To leverage Transformer architecture for enhanced perception capabilities.

Main Methods:

  • Implemented a multi-scale Transformer feature extraction with channel attention.
  • Utilized Query Denoising with Gaussian decay for small object representation learning.
Keywords:
Transformerfeature extractionobject detectionoptimal transportquery denoising

More Related Videos

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

522
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

392

Related Experiment Videos

Last Updated: Jun 26, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
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

522
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

392
  • Employed a hybrid Optimal Transport and Hungarian algorithm for improved sample matching.

    • Main Results:

    • Achieved a 3% higher mean Average Precision (mAP) compared to existing methods.
    • Demonstrated enhanced performance on the KITTI dataset.
    • Showcased improved accuracy in detecting objects across various scales and conditions.

    Conclusions:

    • The proposed Transformer-based object detection method significantly enhances unmanned driving perception.
    • The integrated techniques effectively address key challenges in real-world driving scenarios.
    • This advancement contributes to safer and more reliable autonomous vehicle systems.