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 Videos

Point Siamese Network for Person Tracking Using 3D Point Clouds.

Yubo Cui1, Zheng Fang1, Sifan Zhou1

  • 1Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110819, China.

Sensors (Basel, Switzerland)
|December 28, 2019
PubMed
Summary

This study introduces the Point Siamese Network (PSN), a novel neural network for robust 3D point cloud person tracking. PSN outperforms traditional methods in challenging scenarios, offering real-time accuracy.

Related Concept Videos

Distance Measurements by Taping01:18

Distance Measurements by Taping

341
Tapes are essential in surveying for accurate, durable, and short-distance measurements. Made from lightweight, nylon-coated steel, they offer flexibility and strength for rugged outdoor use. The nylon coating protects against rust and wear, extending the tape's life. Standard lengths, around 30 meters, are marked in meters and millimeters for precision.Surveyors select tapes based on site conditions and accuracy needs. Lightweight, nylon-coated tapes are commonly used for ease of handling and...
341

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Resilient odometry via hierarchical adaptation.

Science robotics·2025
Same author

Corrigendum to "Renal tubular in TCE-sensitization-induced immune kidney injury: Role of mitochondrial DNA in activating the cGAS-STING signaling pathway" [Int. Immunopharmacol. 113 (2022) 109432].

International immunopharmacology·2025
Same author

Effects of polystyrene microplastics on growth, physiological traits of Microcystis aeruginosa and microcystin production and release.

Environmental pollution (Barking, Essex : 1987)·2025
Same author

Kushenol O Regulates GALNT7/NF-κB axis-Mediated Macrophage M2 Polarization and Efferocytosis in Papillary Thyroid Carcinoma.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2025
Same author

Genetic associations of plasma metabolites with immune cells in hyperthyroidism revealed by Mendelian randomization and GWAS-sc-eQTLs xQTLbiolinks analysis.

Scientific reports·2025
Same author

Efficient Charge Carriers Separation and Transfer Driven by Interface Electric Field in FeS<sub>2</sub>@ZnIn<sub>2</sub>S<sub>4</sub> Heterojunction Boost Hydrogen Evolution.

Molecules (Basel, Switzerland)·2024

Area of Science:

  • Computer Vision
  • Robotics
  • Machine Learning

Background:

  • Person tracking with 3D point clouds is crucial for computer vision and robotics.
  • Existing Bayesian Filtering methods lack robustness in challenging tracking environments.
  • There is a need for more accurate and resilient person tracking techniques using 3D data.

Purpose of the Study:

  • To propose a novel neural network, the Point Siamese Network (PSN), for person tracking using solely 3D point cloud data.
  • To enhance the robustness and accuracy of person tracking in complex and cluttered scenes.
  • To provide a real-time capable solution for 3D point cloud based person tracking.

Main Methods:

  • Developed a Point Siamese Network (PSN) with distinct template and search branches for feature extraction.
Keywords:
3D person trackingLIDARconvolutional neural networks

Related Experiment Videos

  • Implemented a feature extraction network to create distinct feature spaces for target and search regions.
  • Introduced a similarity map derived from feature spaces to locate the target person.
  • Integrated an attention module within the template branch to refine feature extraction.

    • Main Results:

    • The PSN demonstrated superior performance compared to the Unscented Kalman Filter (UKF) in robustness and accuracy.
    • Evaluations were conducted on custom challenging scenes and the KITTI dataset.
    • The proposed method achieved real-time processing speeds, indicating practical applicability.

    Conclusions:

    • The Point Siamese Network (PSN) offers a significant advancement in 3D point cloud person tracking.
    • PSN provides a robust and accurate alternative to existing filtering-based methods, especially in difficult environments.
    • The public release of the dataset and labeled sequences will facilitate further research in this domain.