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

Tracking a dynamic set of feature points.

Y S Yao1, R Chellappa

  • 1Comput. Vision Lab., Maryland Univ., College Park, MD.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|January 1, 1995
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

[Analysis of risk factors and construction of nomogram model for local lymph node metastasis in salivary gland mucoepidermoid carcinoma].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2024
Same author

[The network investigation on knowledge, attitude and practice about COVID-19 of the residents in Anhui Province].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2020
Same author

[The network investigation on knowledge, attitude and practice about Novel coronavirus pneumonia of the residents in Anhui Province].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2020
Same author

Decreased serum levels of T-cell immunoglobulin mucin-1 and T-cell immunoglobulin mucin-3 in systemic lupus erythematosus patients.

Journal of biological regulators and homeostatic agents·2016
Same author

Fourier coding of image boundaries.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Estimation of object motion parameters from noisy images.

IEEE transactions on pattern analysis and machine intelligence·2011
Same journal

Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

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

Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a localized feature tracking algorithm for monocular image sequences. It efficiently tracks existing and new feature points despite complex 3-D camera motion.

Area of Science:

  • Computer Vision
  • Robotics
  • Image Processing

Background:

  • Tracking feature points in monocular image sequences is challenging due to varying image motion from 3-D camera movement.
  • Existing methods struggle with dynamic inclusion of new feature points and complex camera trajectories.

Purpose of the Study:

  • To develop a robust localized feature tracking algorithm for monocular image sequences.
  • To enable efficient tracking of both initial and newly detected feature points.
  • To accommodate general 3-D camera movements.

Main Methods:

  • A localized feature tracking algorithm decomposes tracking into independent, local problems.
  • Each feature point's trajectory is modeled using a 2-D kinematic model.
  • Interframe motion estimation and temporal information processing are employed for subpixel accuracy and robust tracking.

Related Experiment Videos

  • A dynamic inclusion strategy is implemented for newly detected feature points.

    • Main Results:

    • The algorithm successfully tracks feature points over long monocular image sequences.
    • It effectively handles image motion resulting from general 3-D camera movements.
    • New feature points are dynamically included, preserving sequence information.

    Conclusions:

    • The proposed localized feature tracking algorithm offers a robust solution for monocular vision tasks.
    • It enhances information preservation in image sequences by dynamically incorporating new features.
    • The method is suitable for applications involving complex 3-D camera motion.