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

Acceleration Vectors01:30

Acceleration Vectors

8.1K
In everyday conversation, accelerating means speeding up. Acceleration is a vector in the same direction as the change in velocity, Δv, therefore the greater the acceleration, the greater the change in velocity over a given time. Since velocity is a vector, it can change in magnitude, direction, or both. Thus acceleration is a change in speed or direction, or both. For example, if a runner traveling at 10 km/h due east slows to a stop, reverses direction, and continues their run at 10 km/h...
8.1K
Association Areas of the Cortex01:21

Association Areas of the Cortex

5.4K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
5.4K

You might also read

Related Articles

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

Sort by
Same author

Three-Dimensional Architectures for Silicon Wafer-Based Integrated Microenergy Storage Systems.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Bright nanoparticle-labeled lateral flow immunoassay for rapid quantitative detection of tacrolimus in human plasma.

Mikrochimica acta·2025
Same author

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model.

Journal of visualized experiments : JoVE·2025
Same author

An interpretable machine learning model based on optimal feature selection for identifying CT abnormalities in patients with mild traumatic brain injury.

EClinicalMedicine·2025
Same author

Metabolomic machine learning-based model predicts efficacy of chemoimmunotherapy for advanced lung squamous cell carcinoma.

Frontiers in immunology·2025
Same author

Serum Albumin Levels and Length of Stay in Premature Infants.

Indian journal of pediatrics·2025

Related Experiment Video

Updated: Jul 13, 2025

A Protocol for Real-time 3D Single Particle Tracking
10:16

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

14.9K

FPGA-Based Feature Extraction and Tracking Accelerator for Real-Time Visual SLAM.

Jie Zhang1, Shuai Xiong2,3, Cheng Liu4

  • 1National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, China.

Sensors (Basel, Switzerland)
|October 14, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an FPGA accelerator for real-time visual odometry and V-SLAM, combining FAST features with dense optical flow for efficient image processing. The hardware solution significantly reduces latency from seconds to milliseconds, enabling practical edge-side applications.

Keywords:
FASTFPGAV-SLAMVIOhistogram equalizationpyramid processing

More Related Videos

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
10:02

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis

Published on: December 24, 2014

11.8K
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

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

Published on: April 4, 2025

356

Related Experiment Videos

Last Updated: Jul 13, 2025

A Protocol for Real-time 3D Single Particle Tracking
10:16

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

14.9K
FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
10:02

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis

Published on: December 24, 2014

11.8K
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

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

Published on: April 4, 2025

356

Area of Science:

  • Computer Vision
  • Hardware Acceleration
  • Robotics

Background:

  • FPGA-based acceleration is increasingly vital in computer vision due to low latency, power efficiency, and flexibility.
  • Real-time Visual Odometry (VO) and Visual Simultaneous Localization and Mapping (V-SLAM) demand efficient image front-end processing.

Purpose of the Study:

  • To propose and implement an FPGA-based accelerator for feature extraction and tracking.
  • To enhance feature tracking performance for VO and V-SLAM by combining FAST features with dense optical flow.
  • To address limitations of FAST features, such as scale and rotation invariance.

Main Methods:

  • Developed a hardware solution integrating Accelerated Segment Test (FAST) feature points with Gunnar Farneback (GF) dense optical flow.
  • Implemented an efficient five-layer pyramid module to achieve scale and rotation invariance.
  • Deployed the accelerator on a Xilinx Zynq FPGA.

Main Results:

  • Achieved stable feature tracking even with violently shaking images.
  • Demonstrated consistency with MATLAB simulations on PCs.
  • Reduced processing latency from seconds (PC CPUs) to the order of milliseconds.

Conclusions:

  • The proposed FPGA accelerator offers a practical and efficient solution for real-time VO and V-SLAM.
  • The combination of FAST features and GF dense optical flow provides superior feature tracking.
  • This hardware acceleration enables effective edge-side visual processing.