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

New Compact 3-Dimensional Shape Descriptor for a Depth Camera in Indoor Environments.

Hyukdoo Choi1,2, Euntai Kim3

  • 1School of Electrical & Electronic Engineering, Yonsei University, Seoul 03722, Korea. goodgodgd@yonsei.ac.kr.

Sensors (Basel, Switzerland)
|April 20, 2017
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

Correlation Verification for Image Retrieval and Its Memory Footprint Optimization.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Detection of Human Traffic Controllers Wearing Construction Workwear via Synthetic Data Generation.

Sensors (Basel, Switzerland)·2025
Same author

Uncertainty Prediction for Monocular 3D Object Detection.

Sensors (Basel, Switzerland)·2023
Same author

Content Swapping: A New Image Synthesis for Construction Sign Detection in Autonomous Vehicles.

Sensors (Basel, Switzerland)·2022
Same author

Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

Indoor Place Category Recognition for a Cleaning Robot by Fusing a Probabilistic Approach and Deep Learning.

IEEE transactions on cybernetics·2021
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Researchers developed a new compact shape descriptor, outperforming existing high-dimensional ones. This novel descriptor, based on principal curvatures, offers practical utility with significantly reduced dimensionality.

Area of Science:

  • Computer Vision
  • Geometric Deep Learning
  • 3D Shape Analysis

Background:

  • Existing local shape descriptors often possess high dimensionality (hundreds of dimensions), despite the inherent simplicity of local shapes.
  • Current depth sensing technology captures single-sided surface data with inherent noise, limiting the need for overly complex shape representations.
  • Complex shapes are infrequently encountered in typical real-world environments.

Purpose of the Study:

  • To investigate the reasons behind the high dimensionality of existing local shape descriptors.
  • To propose and validate a novel, compact shape descriptor that is practically effective.
  • To offer an alternative solution addressing the limitations of current descriptors in real-world scenarios.

Main Methods:

Keywords:
correspondencepoint cloudprincipal curvatureshape descriptor

Related Experiment Videos

  • A new compact descriptor was designed, leveraging the mathematical concept of principal curvatures.
  • The proposed descriptor's performance was evaluated against existing methods using established datasets: CoRBS, RGB-D Scenes, and RGB-D Object.
  • Comparative analysis focused on shape, instance, and category recognition rates.

    • Main Results:

    • The proposed descriptor achieved comparable performance to existing, higher-dimensional descriptors.
    • The new descriptor demonstrated significant compactness, with a dimensionality of only 4.
    • Validation across multiple datasets confirmed its efficacy in shape recognition tasks.

    Conclusions:

    • The proposed principal curvature-based descriptor offers a practical and compact alternative for 3D shape analysis.
    • Its low dimensionality (4D) makes it efficient without sacrificing recognition performance in real-world applications.
    • This research provides a more suitable approach for shape description given the constraints of current depth sensing and environmental complexity.