Search research articles

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: Jun 9, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Human tracking using convolutional neural networks.

Jialue Fan¹, Wei Xu, Ying Wu

¹Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL 60208 USA. jialue.fan@u.northwestern.edu

IEEE Transactions on Neural Networks

|September 1, 2010

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

What are we tracking: a unified approach of tracking and recognition.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2012

Same author

Scribble tracker: a matting-based approach for robust tracking.

IEEE transactions on pattern analysis and machine intelligence·2012

Same author

Coordinating to three histidine residues: Cu(II) promotes oligomeric and fibrillar amyloid-beta peptide to precipitate in a non-beta aggregation manner.

Journal of Alzheimer's disease : JAD·2009

Same author

[Effect of melatonin on hyperoxia-induced oxidant/antioxidant imbalance in the lung of neonatal rats with chronic lung disease].

Zhongguo dang dai er ke za zhi = Chinese journal of contemporary pediatrics·2009

Same author

Phase I/II trial of AEG35156 X-linked inhibitor of apoptosis protein antisense oligonucleotide combined with idarubicin and cytarabine in patients with relapsed or primary refractory acute myeloid leukemia.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2009

Same author

Multiplex single-nucleotide polymorphism typing by nanoparticle-coupled DNA-templated reactions.

Journal of the American Chemical Society·2009

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study presents a novel object tracking method using convolutional neural networks (CNNs) to estimate object location and scale. The approach effectively handles complex environments by learning spatial-temporal features and employing a shift-variant architecture.

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Object tracking is crucial for various applications, but challenges remain in cluttered environments and with similar distractors.
Existing methods often struggle with drift and scale estimation accuracy.

Purpose of the Study:

To develop an object-independent tracking method using deep learning.
To improve tracking accuracy and robustness in challenging scenarios.

Main Methods:

Treated object tracking as a learning problem, estimating location and scale from image frames.
Trained convolutional neural networks (CNNs) on image pairs to learn joint spatial-temporal features.
Introduced multi-path CNNs for fused local/global information and a shift-variant architecture to mitigate drift.

More Related Videos

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

Related Experiment Videos

Last Updated: Jun 9, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

Main Results:

CNNs learned both spatial and temporal features from adjacent image pairs.
A shift-variant CNN architecture was designed to reduce drift in cluttered environments.
Scale estimation was achieved through accurate key point localization.

Conclusions:

The proposed object-independent tracking method demonstrates robust performance in complex situations.
The integration of CNNs with multi-path and shift-variant architectures offers a promising direction for advanced object tracking.