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

Immunotherapy with or without low-intensity chemotherapy versus conventional chemotherapy as first-line treatment for newly diagnosed B-ALL patients fit for intensive chemotherapy: a propensity score-matched study.

Frontiers in medicine·2026
Same author

Manipulating CD38 ectoenzymatic activity revitalizes regulatory T cells via deacetylase Sirt-1 in immune thrombocytopenia.

Journal of thrombosis and haemostasis : JTH·2026
Same author

Chaperone-mediated autophagy reprograms heterogeneous subsets of activated macrophages in immune thrombocytopenia.

Autophagy·2026
Same author

Efficient Detection of Trace NO<sub>2</sub> in Humid Environments Induced by Increasing Formation of Free Radicals on SV-MoS<sub>2</sub>/Au.

ACS sensors·2026
Same author

Exploring the Burden on Patients Living With and Receiving Treatment for Immune Thrombocytopenia (ITP): Patient and Physician Perceptions From the ITP World Impact Survey (I-WISh) 2.0.

American journal of hematology·2026
Same author

Synopsis of the 2025 guideline for the diagnosis and management of adult primary immune thrombocytopenia.

Chinese medical journal·2026

Related Experiment Video

Updated: Jul 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

559

3D Object Detection Using Multiple-Frame Proposal Features Fusion.

Minyuan Huang1, Henry Leung1, Ming Hou2

  • 1Department of Electrical and Software Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada.

Sensors (Basel, Switzerland)
|November 25, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a novel multi-frame 3D object detection method, Proposal Features Fusion (PFF), which enhances accuracy by fusing features from associated proposals. The approach significantly improves performance on the nuScenes dataset.

Keywords:
3D object detectionautonomous drivingfeature and data fusionmultiple frame point clouds

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development
13:01

Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development

Published on: April 10, 2016

34.0K

Related Experiment Videos

Last Updated: Jul 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

559
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development
13:01

Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development

Published on: April 10, 2016

34.0K

Area of Science:

  • Computer Vision
  • Robotics
  • Artificial Intelligence

Background:

  • 2D object detection lacks depth and is sensitive to environmental conditions.
  • 3D point clouds offer superior depth and environmental detail but face sparsity challenges in single-frame detection.
  • Multi-frame approaches are needed to overcome single-frame limitations in 3D point cloud object detection.

Purpose of the Study:

  • To develop an effective multi-frame 3D object detection method for point clouds.
  • To address the sparsity challenge in single-frame 3D object detection.
  • To improve the precision and efficiency of 3D object detection.

Main Methods:

  • A two-stage, proposal-based feature fusion method (PFF) was developed.
  • Cosine similarity was used to associate proposals across multiple frames.
  • An attention-weighted fusion (AWF) module merged features from associated proposals for object-specific fusion.

Main Results:

  • The PFF method achieved a mean Average Precision (mAP) of 46.7% on the nuScenes dataset.
  • This represents a 1.3% improvement over existing state-of-the-art 3D object detection methods.
  • The approach demonstrated lower computational complexity with higher precision.

Conclusions:

  • The proposed Proposal Features Fusion (PFF) method effectively leverages multi-frame data for enhanced 3D object detection.
  • Feature fusion specific to individual objects, enabled by PFF and AWF, leads to significant performance gains.
  • This research offers a promising direction for improving autonomous driving perception systems.