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

Related Concept Videos

Relative Motion Analysis using Rotating Axes

Relative Motion Analysis using Rotating Axes

Consider a component AB undergoing a linear motion. Along with a linear motion, point B also rotates around point A. To comprehend this complex movement, position vectors for both points A and B are established using a stationary reference frame.
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it instrumental in...

You might also read

Related Articles

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

Sort by

Same author

Antagonistic developmental cardiotoxicity of fluroxypyr-meptyl and carfentrazone-ethyl in zebrafish embryos via oxidative stress and apoptosis.

Environmental pollution (Barking, Essex : 1987)·2026

Same author

Decoding the shared genetic liability of lower respiratory tract infections via genomic structural equation modeling.

BMC pulmonary medicine·2026

Same author

Electronic structure-driven sodiophilicity enables stable anode-free sodium batteries.

Science advances·2026

Same author

HDAC1-mediated CDK1 decrotonylation inhibits colorectal cancer proliferation by regulating cell cycle and apoptosis.

Frontiers in oncology·2026

Same author

Factors influencing postoperative pain catastrophizing in patients with lower limb trauma and development of a nomogram prediction model.

BMC surgery·2026

Same author

Clinical characteristics and temporal trends of meropenem and piperacillin/tazobactam heteroresistance in Pseudomonas aeruginosa isolates.

Annals of clinical microbiology and antimicrobials·2026

Search research articles

Related Experiment Video

Updated: May 14, 2026

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

Robust Rear-View Human Tracking for Robotic Visual Sensing: A Spatiotemporal Prediction and Multi-Modal Fusion

Xu Jia¹, Jia Xie¹, Yongguo Li¹

¹School of Engineering, Shanghai Ocean University, Shanghai 201306, China.

Sensors (Basel, Switzerland)

|May 13, 2026

Summary

This study introduces a lightweight framework for robust rear-view human tracking and re-identification in autonomous vehicles, significantly reducing tracking errors in adverse conditions.

Keywords:

Kalman filter adverse weather multimodal fusion rear-view human tracking robotic tracking spatiotemporal prediction vision sensors

More Related Videos

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

Related Experiment Videos

Last Updated: May 14, 2026

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

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

Area of Science:

Robotics
Computer Vision
Artificial Intelligence

Background:

Rear-view human tracking is crucial for autonomous vehicles but challenging due to occlusion and adverse weather.
Conventional deep learning models struggle with feature contamination and trajectory drift.

Purpose of the Study:

To develop a lightweight, robust framework for human tracking and re-identification in challenging environments.
To enhance the reliability of robotic visual sensing in unmanned vehicles.

Main Methods:

A spatiotemporal prediction and multimodal feature fusion framework.
Ego-motion-aware Kalman prediction for occlusion handling.
Multi-factor descriptor fusion with adaptive learning rates.

Main Results:

Achieved peak precision of 94.2% and tracking success rate of 93.4% on a Mecanum-wheeled robot.
Reduced average tracking error by 35% in extreme rainy night scenarios (CLE < 11 pixels).
Demonstrated rapid re-identification response (72.83 ms) during occlusions.

Conclusions:

The proposed framework offers a robust and real-time solution for autonomous navigation in complex environments.
Effective in mitigating challenges posed by occlusion, dynamic illumination, and adverse weather.