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 multiple humans in complex situations.

Tao Zhao1, Ram Nevatia

  • 1Sarnoff Corporation, Princeton, NJ 08543, USA. tzhao@sarnoff.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|March 4, 2005
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

Durvalumab-Associated Crescentic Glomerulonephritis With IgA Vasculitis-Like Features.

Kidney international reports·2025
Same author

Paper-Mill Waste Derived Bioplastic with Excitation- and Time-Dependent Phosphorescence Color for Sustainable Flexible Anti-Counterfeiting.

Nano letters·2025
Same author

A Generalized Udwadia-Kalaba Control Design With Speed Inequality Constraints.

IEEE transactions on cybernetics·2025
Same author

A generic method for PLC control system design based on Digital Twin.

PloS one·2025
Same author

JAK3 identified as a key toxicological target of aristolochic acid in clear cell renal cell carcinoma.

Molecular diversity·2025
Same author

Engineering Pore Chemistry and Environment in Robust Metal-Organic Frameworks for One-Step C<sub>2</sub>H<sub>4</sub> Purification from Ternary Mixtures.

Inorganic chemistry·2025
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study presents a novel approach for tracking multiple humans in complex 3D environments. Our method effectively segments and tracks human motion, even with occlusions and challenging conditions, improving multi-human tracking accuracy.

Area of Science:

  • Computer Vision
  • Robotics
  • Human Motion Analysis

Background:

  • Tracking multiple humans in complex scenarios presents significant challenges.
  • Existing methods often struggle with occlusions, shadows, and reflections.

Purpose of the Study:

  • To develop a robust approach for segmenting and tracking multiple human motions in 3D.
  • To estimate human locomotion modes and 3D body postures.

Main Methods:

  • Decomposition of human motion into global and limb components.
  • Utilizing ellipsoid human shape models for 3D global motion tracking.
  • Employing a prior locomotion model for gait analysis and posture estimation.
  • Incorporating camera and ground plane geometric constraints.

Related Experiment Videos

Main Results:

  • Successful segmentation and 3D tracking of multiple humans, even with occlusions and environmental challenges.
  • Accurate estimation of locomotion modes (walking, running, standing) and body postures.
  • Demonstrated robustness on difficult video sequences.

Conclusions:

  • The proposed method offers a significant advancement in multi-human tracking.
  • The approach is effective in complex scenarios involving occlusions and challenging visual conditions.
  • Accurate estimation of human motion and posture contributes to enhanced scene understanding.