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 Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

451
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
451

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Iterative Shifting Disaggregation Algorithm for Multi-Source, Irregularly Sampled, and Overlapped Time Series.

Sensors (Basel, Switzerland)·2025
Same author

Uncertainty-Aware Gaze Tracking for Assisted Living Environments.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

The Influence of Marking Methods on Mobility, Survivorship, and Field Recovery of Halyomorpha halys (Hemiptera: Pentatomidae) Adults and Nymphs.

Environmental entomology·2020
Same author

An autoencoder and artificial neural network-based method to estimate parity status of wild mosquitoes from near-infrared spectra.

PloS one·2020
Same author

Age grading An. gambiae and An. arabiensis using near infrared spectra and artificial neural networks.

PloS one·2019
Same author

Do NIR spectra collected from laboratory-reared mosquitoes differ from those collected from wild mosquitoes?

PloS one·2018

Related Experiment Video

Updated: Mar 6, 2026

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies
07:34

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Published on: November 7, 2025

381

Image-Based Multi-Target Tracking through Multi-Bernoulli Filtering with Interactive Likelihoods.

Anthony Hoak1, Henry Medeiros2, Richard J Povinelli3

  • 1Department of Electrical & Computer Engineering, Marquette University, 1551 W. Wisconsin Ave., Milwaukee, WI 53233, USA. anthony.hoak@marquette.edu.

Sensors (Basel, Switzerland)
|March 10, 2017
PubMed
Summary
This summary is machine-generated.

We introduce an interactive likelihood (ILH) to enhance sequential Monte Carlo (SMC) methods for multi-target tracking. This approach improves tracking accuracy by reducing data association needs, outperforming existing methods across multiple datasets.

Keywords:
multi-Bernoulli filtermulti-target trackingsequential Monte Carlo

More Related Videos

Image-based Lagrangian Particle Tracking in Bed-load Experiments
10:32

Image-based Lagrangian Particle Tracking in Bed-load Experiments

Published on: July 20, 2017

9.5K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.3K

Related Experiment Videos

Last Updated: Mar 6, 2026

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies
07:34

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Published on: November 7, 2025

381
Image-based Lagrangian Particle Tracking in Bed-load Experiments
10:32

Image-based Lagrangian Particle Tracking in Bed-load Experiments

Published on: July 20, 2017

9.5K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.3K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • Sequential Monte Carlo (SMC) methods are crucial for multi-target tracking.
  • Data association is a significant challenge in accurate multi-target tracking.
  • Deep neural networks offer advanced capabilities for object detection.

Purpose of the Study:

  • To develop an interactive likelihood (ILH) to improve SMC-based multi-target tracking.
  • To reduce the reliance on data association in tracking algorithms.
  • To integrate a deep neural network for pedestrian detection with the ILH and multi-Bernoulli filter.

Main Methods:

  • Developed an interactive likelihood (ILH) for sequential Monte Carlo (SMC) methods.
  • Integrated a deep neural network for pedestrian detection.
  • Utilized a multi-Bernoulli filter for tracking.
  • Evaluated performance on PETS INMOVE 2003, AFL, and TUD-Stadtmitte datasets.

Main Results:

  • The interactive likelihood (ILH) term consistently improved the tracking accuracy of the multi-Bernoulli filter.
  • Performance was evaluated using standard metrics like optimal sub-pattern assignment (OSPA) and CLEAR MOT.
  • The integrated system demonstrated enhanced performance across all tested datasets.

Conclusions:

  • The interactive likelihood (ILH) is an effective enhancement for SMC-based multi-target tracking.
  • Combining ILH with deep learning pedestrian detection and multi-Bernoulli filters significantly boosts tracking accuracy.
  • The proposed method shows promise for real-world image-based multi-target tracking applications.