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

You might also read

Related Articles

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

Sort by
Same author

Evodiamine protects against lung ischemia-reperfusion injury by attenuating SYK-associated TLR4/NLRP3 inflammasome activation and ferroptosis-related injury signatures.

Pulmonary pharmacology & therapeutics·2026
Same author

Coordination between water source partitioning and isohydric-anisohydric behavior shapes contrasting water use strategies of <i>Tamarix chinensis</i> and <i>Ulmus pumila</i> in saline-alkaline soils.

Frontiers in plant science·2025
Same author

Liquid Reservoir Weld Defect Detection Based on Improved YOLOv8s.

Sensors (Basel, Switzerland)·2025
Same author

A Visual Trajectory-Based Method for Personnel Behavior Recognition in Industrial Scenarios.

Sensors (Basel, Switzerland)·2025
Same author

Aluminum Reservoir Welding Surface Defect Detection Method Based on Three-Dimensional Vision.

Sensors (Basel, Switzerland)·2025
Same author

Six-Dimensional Pose Estimation of Molecular Sieve Drying Package Based on Red Green Blue-Depth Camera.

Sensors (Basel, Switzerland)·2025

Related Experiment Video

Updated: Aug 29, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

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

Published on: February 6, 2020

9.5K

Improved Fully Convolutional Siamese Networks for Visual Object Tracking Based on Response Behaviour Analysis.

Xianyun Huang1, Songxiao Cao2, Chenguang Dong1

  • 1Scientific Research Post, Suzhou Institute of Metrology, Suzhou 215128, China.

Sensors (Basel, Switzerland)
|September 9, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces SiamFC-RBA, an improved Siamese network tracker that enhances visual tracking accuracy by analyzing response behavior to prevent tracking drift in cluttered environments. Experiments show superior performance on benchmark datasets.

Keywords:
Siamese trackerbackground cluttertracking driftvisual tracking

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

615
Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

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

Published on: June 15, 2020

12.7K

Related Experiment Videos

Last Updated: Aug 29, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

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

Published on: February 6, 2020

9.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

615
Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

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

Published on: June 15, 2020

12.7K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Siamese networks offer a balance of accuracy and speed for visual tracking.
  • Tracking drift, caused by appearance changes and static models, is a significant challenge, especially in cluttered backgrounds.

Purpose of the Study:

  • To propose an improved fully convolutional Siamese tracker, SiamFC-RBA, that addresses tracking drift using response behavior analysis.
  • To enhance the robustness and accuracy of visual object tracking.

Main Methods:

  • Normalizing SiamFC response maps to 8-bit grayscale images.
  • Generating isohypse contours for candidate target regions via thresholding.
  • Analyzing contour dynamics to detect approaching distractors and employing a peak switching strategy for accurate localization.

Main Results:

  • The proposed SiamFC-RBA tracker demonstrated state-of-the-art performance on OTB100, GOT-10k, and LaSOT benchmarks.
  • SiamFC-RBA outperformed established trackers like DaSiamRPN, SiamRPN, and Staple.
  • Integrating the response behavior analysis module into DiMP improved its tracking performance.

Conclusions:

  • The SiamFC-RBA tracker effectively mitigates tracking drift through response behavior analysis.
  • The proposed method offers a significant advancement in robust visual object tracking, particularly in challenging scenarios.