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

550
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.
550

You might also read

Related Articles

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

Sort by
Same author

The Impact of the Number of Implantation-Window uNK Cells on Pregnancy Outcomes and Decidualization.

Reproductive sciences (Thousand Oaks, Calif.)·2026
Same author

Promoting Mechanisms of Sulfation on Ir/TiO<sub>2</sub>-S Catalysts in Methane Combustion.

ACS applied materials & interfaces·2026
Same author

ANXA2-mediated Phagocytosis Generates AR<sup>+</sup> Macrophages to Confer Enzalutamide Resistance in Prostate Cancer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Impact of endogenous LH and LH supplementation on clinical outcome following a long GnRH agonist protocol in younger and older patients.

Frontiers in endocrinology·2026
Same author

Mapping the immune landscape of PCa: From tumor microenvironment to therapeutics.

Biochimica et biophysica acta. Reviews on cancer·2026
Same author

Luminescence, scintillation, and energy transfer properties of sol-gel synthesized SiO<sub>2</sub>:Ce,Tb powder for gamma radiation.

Applied optics·2026

Related Experiment Video

Updated: Jun 4, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.6K

Fusing Events and Frames with Coordinate Attention Gated Recurrent Unit for Monocular Depth Estimation.

Huimei Duan1, Chenggang Guo1, Yuan Ou1

  • 1School of Computer and Software Engineering, Xihua University, Chengdu 610039, China.

Sensors (Basel, Switzerland)
|December 17, 2024
PubMed
Summary

This study introduces a novel Coordinate Attention Gated Recurrent Unit (CAGRU) to improve monocular depth estimation by fusing data from event and conventional cameras. The method enhances accuracy and robustness in challenging environments.

Keywords:
coordinate attentionevent camerasgate recurrent unitsmonocular depth estimation

More Related Videos

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

10.6K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.4K

Related Experiment Videos

Last Updated: Jun 4, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.6K
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

10.6K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.4K

Area of Science:

  • Computer Vision
  • Robotics
  • Sensor Fusion

Background:

  • Monocular depth estimation is crucial for scene understanding but struggles in extreme conditions like dynamic scenes or poor lighting.
  • Conventional cameras have limitations in extreme environments, while event cameras capture brightness changes asynchronously but lack color and absolute brightness.
  • Effective fusion of event and conventional camera data is needed to improve monocular depth estimation accuracy and robustness.

Purpose of the Study:

  • To propose a novel method for robust monocular depth estimation by effectively fusing data from event and conventional cameras.
  • To introduce the Coordinate Attention Gated Recurrent Unit (CAGRU) for enhanced feature screening and fusion.
  • To improve the accuracy and robustness of monocular depth estimation, especially in challenging environmental conditions.

Main Methods:

  • A novel Coordinate Attention Gated Recurrent Unit (CAGRU) was developed, integrating coordinate attention mechanisms into gated recurrent units.
  • The CAGRU utilizes coordinate attention gates combined with convolutional gates to model spatial, temporal, and inter-channel feature dependencies.
  • This approach enhances the information density of sparse event data within the temporal processing, facilitating effective feature fusion.

Main Results:

  • The proposed CAGRU method demonstrated significant performance improvements on various public datasets for monocular depth estimation.
  • The fusion of event and standard camera data using CAGRU led to enhanced accuracy and robustness.
  • The method effectively screens and fuses features, overcoming limitations of conventional approaches in extreme environments.

Conclusions:

  • The novel CAGRU effectively fuses complementary information from event and conventional cameras for monocular depth estimation.
  • The proposed method significantly improves accuracy and robustness, particularly in dynamic scenes and challenging lighting conditions.
  • CAGRU offers a promising solution for advancing monocular depth estimation in computer vision and robotics.