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

1.0K
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.
1.0K
Uniform Depth Channel Flow: Problem Solving01:18

Uniform Depth Channel Flow: Problem Solving

137
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
137

You might also read

Related Articles

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

Sort by
Same author

A Unified GAN-Based Framework for Unsupervised Video Anomaly Detection Using Optical Flow and RGB Cues.

Sensors (Basel, Switzerland)·2025
Same author

Supervised and Self-Supervised Learning for Assembly Line Action Recognition.

Journal of imaging·2025
Same author

Elevating Chest X-ray Image Super-Resolution with Residual Network Enhancement.

Journal of imaging·2024
Same author

Conv3D-Based Video Violence Detection Network Using Optical Flow and RGB Data.

Sensors (Basel, Switzerland)·2024
Same author

Anomaly Detection Based on a 3D Convolutional Neural Network Combining Convolutional Block Attention Module Using Merged Frames.

Sensors (Basel, Switzerland)·2023
Same author

GANMasker: A Two-Stage Generative Adversarial Network for High-Quality Face Mask Removal.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Sep 30, 2025

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

15.8K

DTS-Depth: Real-Time Single-Image Depth Estimation Using Depth-to-Space Image Construction.

Hatem Ibrahem1, Ahmed Salem1,2, Hyun-Soo Kang1

  • 1Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Korea.

Sensors (Basel, Switzerland)
|March 10, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces an efficient, real-time convolutional neural network for depth estimation using single high-resolution images. The novel approach achieves high accuracy and fast processing speeds, outperforming existing methods.

Keywords:
convolutional neural networksdepth estimationreal-time processing

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

228
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.2K

Related Experiment Videos

Last Updated: Sep 30, 2025

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

15.8K
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

228
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.2K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Machine Learning

Background:

  • High-resolution depth estimation is computationally intensive, hindering real-time applications.
  • Existing solutions often rely on low-resolution inputs to reduce complexity.
  • There is a need for efficient algorithms capable of real-time, high-accuracy depth prediction from high-resolution data.

Purpose of the Study:

  • To develop an efficient, real-time convolutional neural network (CNN) for depth estimation using single high-resolution images.
  • To overcome the computational limitations of existing high-resolution depth estimation methods.
  • To achieve high accuracy and real-time performance without sacrificing input image resolution.

Main Methods:

  • A novel CNN architecture based on a modified MobileNetV2 is proposed.
  • The method utilizes a lightweight encoding architecture without a decoder.
  • Depth-to-space image construction, typically used in super-resolution, is adapted for depth estimation.
  • The algorithm processes single high-resolution images as input.

Main Results:

  • The proposed method achieves real-time performance: 48 FPS on GPU and 20 FPS on CPU for high-resolution images.
  • High accuracy is demonstrated on challenging datasets: KITTI (0.028 error), Cityscapes (0.167 error), and NYUV2 (0.069 error).
  • The algorithm outperforms state-of-the-art depth estimation methods in both speed and accuracy.

Conclusions:

  • The developed algorithm offers an efficient and real-time solution for high-resolution depth estimation.
  • The novel architecture provides a significant advancement over traditional encoder-decoder models.
  • This method enables practical real-time applications requiring accurate depth perception from high-resolution imagery.