Search research articles

Search research articles

Related Experiment Video

Updated: Jul 5, 2025

Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow

Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow

Published on: February 27, 2016

Time Convolutional Network-Based Maneuvering Target Tracking with Azimuth-Doppler Measurement.

Jianjun Huang¹, Haoqiang Hu¹, Li Kang¹

¹School of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China.

Sensors (Basel, Switzerland)

|January 11, 2024

Summary

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

Synthetic Spatiotemporal Plasmonic Vortices on Chip.

Physical review letters·2026

Same author

Adaptive Multimodal Fusion in Vertical Federated Learning for Decentralized Glaucoma Screening.

Brain sciences·2025

Same author

Design, synthesis, and bioactivity evaluation of novel indole-selenide derivatives as P-glycoprotein inhibitors against multi-drug resistance in MCF-7/ADR cell.

European journal of medicinal chemistry·2024

Same author

A distribution information sharing federated learning approach for medical image data.

Complex & intelligent systems·2023

Same author

A Hybrid Approach Based on Deep CNN and Machine Learning Classifiers for the Tumor Segmentation and Classification in Brain MRI.

Computational and mathematical methods in medicine·2022

Same author

Activation of necroptosis pathway in podocyte contributes to the pathogenesis of focal segmental glomerular sclerosis.

Clinical and experimental nephrology·2022

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

This study introduces a novel deep learning algorithm, the recursive downsample-convolve-interact neural network (RDCINN), for maneuvering target tracking. RDCINN effectively handles weak or missing observations, outperforming traditional methods in complex scenarios.

Area of Science:

Signal Processing
Artificial Intelligence
Control Systems

Background:

Traditional maneuvering target tracking algorithms struggle with weak/missing azimuth and Doppler observations.
Model mismatch and measurement noise in conventional methods cause significant prediction errors.
Neural network-based algorithms like RNNs, LSTMs, and Transformers show promise for improved target tracking.

Purpose of the Study:

To develop a deep learning algorithm capable of modeling complex nonlinear and contextual relationships in time series data for target tracking.
To overcome the limitations of traditional algorithms in efficiently utilizing observation information, especially during weak or non-existent observations.
To enhance the accuracy of maneuvering target state prediction.

Main Methods:

Keywords:

azimuth and Doppler convolutional neural network deep learning algorithm maneuvering targets tracking

More Related Videos

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

A Protocol for Real-time 3D Single Particle Tracking

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

Related Experiment Videos

Last Updated: Jul 5, 2025

Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow

Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow

Published on: February 27, 2016

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

A Protocol for Real-time 3D Single Particle Tracking

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

Introduced the recursive downsample-convolve-interact neural network (RDCINN), a deep learning algorithm based on Convolutional Neural Networks (CNNs).
RDCINN downsamples time series data into subsequences and extracts multi-resolution features.
The architecture is designed to model nonlinear relationships between observation and target state time series and contextual relationships among time series points.

Main Results:

The proposed RDCINN algorithm demonstrated superior performance compared to existing algorithms in strong maneuvering target tracking scenarios.
The algorithm effectively utilizes combined azimuth and Doppler observations, even when they are weak or absent.
Experimental results validate the algorithm's capability in handling complex target motion states and improving prediction accuracy.

Conclusions:

RDCINN offers a significant advancement in maneuvering target tracking, particularly in challenging scenarios with limited or noisy observational data.
The deep learning approach effectively addresses the shortcomings of traditional algorithms, providing more robust and accurate target state predictions.
The algorithm's ability to model complex time series relationships makes it a promising solution for advanced tracking applications.