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

Principal axis-based correspondence between multiple cameras for people tracking.

Weiming Hu1, Min Hu, Xue Zhou

  • 1National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, PO Box 2728, Beijing, 100080, P.R. China. wmhu@nlpr.ia.ac.cn

IEEE Transactions on Pattern Analysis and Machine Intelligence
|March 29, 2006
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

Aesthetics++: Refining Graphic Designs by Exploring Design Principles and Human Preference.

IEEE transactions on visualization and computer graphics·2022
Same author

The Relations between EGFR R521K Polymorphism and Risk of Cancer: Need for Clarification of Data in a Recent Meta-Analysis.

International journal of genomics·2015
Same author

Neural circuits containing olfactory neurons are involved in the prepulse inhibition of the startle reflex in rats.

Frontiers in behavioral neuroscience·2015
Same author

Andrographolide suppresses proliferation of nasopharyngeal carcinoma cells via attenuating NF-κB pathway.

BioMed research international·2015
Same author

Esophageal variceal pressure influence on the effect of ligation.

World journal of gastroenterology·2015
Same author

Conductive iron oxide minerals accelerate syntrophic cooperation in methanogenic benzoate degradation.

Journal of hazardous materials·2015

This study introduces a robust method for matching people across multiple cameras using principal axes, simplifying visual surveillance. This approach enhances tracking accuracy even with occlusions and without camera calibration.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • Multi-camera visual surveillance is increasingly important.
  • Matching individuals across different camera views (correspondence) is a fundamental challenge.

Purpose of the Study:

  • To propose a simple and robust method for cross-camera people matching.
  • To overcome limitations of existing methods, such as the need for camera calibration and sensitivity to noise.

Main Methods:

  • A novel approach based on principal axes of people for matching individuals across multiple cameras.
  • Calculating correspondence likelihood using relationships between detected ground-points and transformed principal axes intersections.
  • Leveraging fused data from correspondence results for accurate 3D positioning.

Related Experiment Videos

Main Results:

  • The method demonstrates robustness to noise, reducing the need for precise motion detection and segmentation.
  • Accurate localization of people is achieved even with partial occlusions across all camera views.
  • Experimental results on real-world outdoor video sequences confirm the method's effectiveness and efficiency.

Conclusions:

  • The proposed principal axis-based method offers a simple, robust, and effective solution for multi-camera visual surveillance.
  • The technique eliminates the requirement for camera calibration and is resilient to noise.
  • It enables accurate people tracking and localization in complex, real-world scenarios.