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: May 26, 2026

Open-source Single-particle Analysis for Super-resolution Microscopy with VirusMapper
07:38

Open-source Single-particle Analysis for Super-resolution Microscopy with VirusMapper

Published on: April 9, 2017

Multistage particle windows for fast and accurate object detection.

Giovanni Gualdi1, Andrea Prati, Rita Cucchiara

  • 1Department of Information Engineering, University of Modena and Reggio Emilia, Modena, Italy. giovanni.gualdi@unimore.it

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 21, 2011
PubMed
Summary

This study introduces a novel statistical search for object detection, outperforming traditional sliding windows. The Monte Carlo sampling method enhances accuracy and reduces computational load for real-time applications.

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

Machine learning-assisted development of a fast Mechanochemical Johnson-Corey-Chaykovsky reaction.

Nature communications·2026
Same author

A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

The aporetic dialogs of Modena on gender differences: Is it all about testosterone? Episode III: Mathematics.

Andrology·2025
Same author

VATr++: Choose Your Words Wisely for Handwritten Text Generation.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Predicting gene and protein expression levels from DNA and protein sequences with Perceiver.

Computer methods and programs in biomedicine·2023
Same author

Fashion-Oriented Image Captioning with External Knowledge Retrieval and Fully Attentive Gates.

Sensors (Basel, Switzerland)·2023

Area of Science:

  • Computer Vision
  • Machine Learning
  • Statistical Modeling

Background:

  • Object detection commonly uses sliding window (SW) search, facing a critical trade-off between computational cost and accuracy.
  • Existing methods to accelerate SW search often involve adding complementary features.

Purpose of the Study:

  • To propose a novel object detection paradigm that overcomes the limitations of sliding window search.
  • To introduce a statistical-based search using Monte Carlo sampling for improved efficiency and accuracy.

Main Methods:

  • Object detection is framed as a statistical search problem utilizing Monte Carlo sampling.
  • A multistage strategy refines the proposal distribution based on classifier feedback.
  • The method integrates with Bayesian-recursive frameworks for video object tracking.

More Related Videos

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

Related Experiment Videos

Last Updated: May 26, 2026

Open-source Single-particle Analysis for Super-resolution Microscopy with VirusMapper
07:38

Open-source Single-particle Analysis for Super-resolution Microscopy with VirusMapper

Published on: April 9, 2017

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

Main Results:

  • The proposed method demonstrates higher detection rates and accuracy compared to sliding window detection.
  • It achieves a significantly lower computational burden than traditional sliding window approaches.
  • Effective across various classifiers (boosted, soft cascades, SVM) and features (covariance matrices, Haar-like, integral channel, HOG).

Conclusions:

  • The statistical Monte Carlo sampling approach offers a superior alternative to sliding window object detection.
  • This method provides a computationally efficient and accurate solution for object detection in images and videos.