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

A field model for human detection and tracking.

Ying Wu1, Ting Yu

  • 1Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL 60208, USA. yingwu@ece.northwestern.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|April 28, 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

Mesorhizobium alexandrii sp. nov., isolated from phycosphere microbiota of PSTs-producing marine dinoflagellate Alexandrium minutum amtk4.

Antonie van Leeuwenhoek·2020
Same author

KTN1 variants and risk for attention deficit hyperactivity disorder.

American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics·2020
Same author

Emergence of an NDM-5-Producing <i>Escherichia coli</i> Sequence Type 410 Clone in Infants in a Children's Hospital in China.

Infection and drug resistance·2020
Same author

A Trial of Lopinavir-Ritonavir in Adults Hospitalized with Severe Covid-19.

The New England journal of medicine·2020
Same author

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study.

Lancet (London, England)·2020
Same author

Polarization-Controlled Plasmonic Structured Illumination.

Nano letters·2020
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 introduces a novel two-layer statistical field model for robustly detecting nonrigid objects like pedestrians, even with shape variations and occlusions. The approach enhances object tracking and detection accuracy in complex environments.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Statistical Modeling

Background:

  • Object detection and tracking of nonrigid targets (e.g., pedestrians) are hindered by significant shape variability and partial occlusions.
  • Existing methods struggle to accurately model and account for complex, dynamic shape changes and environmental challenges.

Purpose of the Study:

  • To develop a novel computational approach for robust object detection and tracking of nonrigid targets.
  • To address challenges posed by large shape variations, partial occlusions, and cluttered environments.

Main Methods:

  • A two-layer statistical field model is proposed, incorporating a Boltzmann distribution for shape variations and a Markov field for image likelihood.
  • Probabilistic variational analysis yields fixed-point equations for efficient model training and image likelihood calculation.

Related Experiment Videos

  • Development of algorithms for nonrigid object detection based on the formulated statistical model.

    • Main Results:

    • The proposed method effectively captures local nonrigidity due to its intrinsic modeling capabilities.
    • The distributed likelihood enhances robustness against partial occlusions.
    • The two-layer structure improves adaptability to image observations, leading to robustness against clutters.

    Conclusions:

    • The new two-layer statistical field model provides an effective and computationally efficient solution for nonrigid object detection.
    • The approach demonstrates significant robustness to shape variations, occlusions, and clutters, outperforming existing methods in challenging scenarios.
    • This method offers a flexible and powerful framework for advanced computer vision tasks involving nonrigid object analysis.