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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

801
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
801
Deconvolution01:20

Deconvolution

219
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
219
Relative Motion Analysis using Rotating Axes01:25

Relative Motion Analysis using Rotating Axes

504
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...
504

You might also read

Related Articles

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

Sort by
Same author

Advances in oral delivery systems for alpha-linolenic acid: mechanisms, bioavailability, and applications in functional foods.

Critical reviews in food science and nutrition·2026
Same author

Iron drives protease-independent cleavage of gasdermin D in allergic airway diseases.

Cell·2026
Same author

Association between early lactate trajectories and mortality in critically ill patients with acute kidney injury: A multicenter cohort study.

Science progress·2026
Same author

Confronting the known unknown: historical lessons and future strategies for Disease X.

Frontiers in public health·2026
Same author

Enhanced electroosmosis-induced delivery of persulfate for remediation of PAHs contaminated soil via time-modulated electric fields: A novel zoned processing concept.

Journal of hazardous materials·2026
Same author

Comfort-Oriented Pothole Traversal Using Multi-Sensor Perception and Fuzzy Control.

Sensors (Basel, Switzerland)·2026

Related Experiment Video

Updated: Aug 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

Keyframe image processing of semantic 3D point clouds based on deep learning.

Junxian Wang1, Wei Lv1, Zhouya Wang1

  • 1Alibaba Cloud Big Data Application College, Zhuhai College of Science and Technology, Zhuhai, China.

Frontiers in Neurorobotics
|February 6, 2023
PubMed
Summary

This study introduces a novel keyframe image processing method for 3D point clouds to bridge the semantic gap in image retrieval. A U-Net-based network enhances semantic segmentation for better information discovery from large image datasets.

Keywords:
3D point cloudU-Netdeep learningimage processingkeyframe

More Related Videos

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

15.7K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Related Experiment Videos

Last Updated: Aug 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

15.7K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Image Processing

Background:

  • The proliferation of digital images necessitates efficient retrieval and integration of visual data.
  • Traditional content-based image retrieval (CBIR) methods suffer from a semantic gap, failing to align machine interpretation with human understanding.
  • Bridging this gap is crucial for effective information discovery in massive image repositories.

Purpose of the Study:

  • To propose a keyframe image processing method specifically designed for 3D point clouds.
  • To develop a deep learning-based semantic segmentation network to address the semantic gap in image retrieval.
  • To improve the efficiency and accuracy of discovering relevant information within large-scale image data.

Main Methods:

  • A keyframe image processing technique is introduced for 3D point cloud data.
  • A U-Net-based binary data stream semantic segmentation network is established.
  • Deep learning techniques are integrated for advanced image analysis and interpretation.

Main Results:

  • The proposed method effectively processes keyframe images from 3D point clouds.
  • The U-Net-based network demonstrates capability in semantic segmentation of binary data streams.
  • The approach shows promise in addressing the semantic gap for improved image retrieval.

Conclusions:

  • The developed keyframe image processing and semantic segmentation network offer a viable solution for the semantic gap in image retrieval.
  • This deep learning approach enhances the ability to efficiently integrate and discover information from vast amounts of image material.
  • The method holds potential for applications requiring sophisticated image understanding and retrieval from complex 3D data.