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 Video

Updated: Apr 4, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K

Non-Rigid Object Detection with LocalInterleaved Sequential Alignment (LISA).

Karel Zimmermann, David Hurych, Tomáš Svoboda

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |September 10, 2015
    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

    PROPTIMUS LIVE: local constrained α-carbon optimization of proteins.

    Nucleic acids research·2026
    Same author

    Risk of Non-colorectal Malignancies in Sporadic <i>Versus</i> Lynch Syndrome-associated dMMR Colorectal Cancer.

    Anticancer research·2026
    Same author

    Analysis of cyclohexane, cyclopentane, and benzene conformations in ligands for PDB X-ray structures using the Hill-Reilly approach.

    Journal of cheminformatics·2026
    Same author

    Gromacs MetaDump: a tool for extracting GROMACS simulation metadata.

    Journal of cheminformatics·2025
    Same author

    Model-based scaling of preparative chromatographic separation of sucrose and glucose using bilevel parameter estimation for equilibrium dispersive model with nonlinear isotherm.

    Journal of chromatography. A·2025
    Same author

    PDBCharges: Quantum-Mechanical Partial Atomic Charges for PDB Structures.

    Nucleic acids research·2025

    Object detection features reveal deformation, enabling real-time image alignment. This method jointly learns detection and alignment, improving accuracy with less deformed training data.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Object detection models often struggle with deformed objects.
    • Existing methods may require extensive, deformation-free training data.
    • Feature evaluation in sliding window detection has not fully utilized deformation information.

    Purpose of the Study:

    • To exploit detection features for estimating and correcting object deformation.
    • To develop a method for jointly learning object detection and alignment.
    • To improve the robustness of object detection against object deformation.

    Main Methods:

    • Utilizing successively evaluated features from sliding window detection to estimate object deformation.
    • Applying estimated deformation to un-evaluated features for image data alignment.

    More Related Videos

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.9K

    Related Experiment Videos

    Last Updated: Apr 4, 2026

    Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
    05:57

    Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

    Published on: April 8, 2019

    7.3K
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.9K
  • Jointly learning alignment estimators with the object detector.
  • Proposing fast regressors to approximate non-linear functions for alignment parameter computation.

    • Main Results:

    • Detection features inherently contain information about object deformation.
    • Joint learning allows each detection stage to train on less deformed samples.
    • The proposed alignment method achieves fast computation of alignment parameters.
    • The approach effectively aligns image data by correcting for object deformation.

    Conclusions:

    • Object deformation can be effectively estimated and corrected using detection features.
    • Joint learning of detection and alignment offers a more robust object detection system.
    • The proposed method significantly enhances image alignment efficiency and accuracy.
    • This approach advances real-time object detection in the presence of significant object variability.