Search research articles

Related Concept Videos

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

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...

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

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 6, 2026

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

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

Published on: November 7, 2025

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

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 filter multi-target tracking sequential Monte Carlo

More Related Videos

Image-based Lagrangian Particle Tracking in Bed-load Experiments

Image-based Lagrangian Particle Tracking in Bed-load Experiments

Published on: July 20, 2017

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

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

Published on: January 18, 2020

Related Experiment Videos

Last Updated: Mar 6, 2026

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

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

Published on: November 7, 2025

Image-based Lagrangian Particle Tracking in Bed-load Experiments

Image-based Lagrangian Particle Tracking in Bed-load Experiments

Published on: July 20, 2017

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

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

Published on: January 18, 2020

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.