Search research articles

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

Related Concept Videos

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

You might also read

Related Articles

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

Sort by

Same author

Heterogeneous iron oxide nanoparticles anchored on carbon nanotubes for high-performance lithium-ion storage and fenton-like oxidation.

Journal of colloid and interface science·2021

Same author

Cost-effectiveness analysis of the integrated control strategy for schistosomiasis japonica in a lake region of China: a case study.

Infectious diseases of poverty·2021

Same author

Targeting Gα<sub>13</sub>-integrin interaction ameliorates systemic inflammation.

Nature communications·2021

Same author

Screening and mitigating major threats of regional development to water ecosystems using ecosystem services as endpoints.

Journal of environmental management·2021

Same author

Facile synthesis of a rod-like porous carbon framework confined magnetite nanoparticle composite for superior lithium-ion storage.

Journal of colloid and interface science·2021

Same author

Wafer-Scale and Full-Coverage Two-Dimensional Molecular Monolayers Strained by Solvent Surface Tension Balance.

ACS applied materials & interfaces·2021

Search research articles

Related Experiment Video

Updated: Nov 20, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A Manufacturing-Oriented Intelligent Vision System Based on Deep Neural Network for Object Recognition and 6D Pose

Guoyuan Liang^1,2,3,4, Fan Chen¹, Yu Liang¹

¹Center for Intelligent and Biomimetic Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.

Frontiers in Neurorobotics

|January 25, 2021

Summary

This study introduces a novel deep learning vision system for intelligent robots to accurately identify and determine the 6D pose of parts in manufacturing. The system enhances robotic grasping capabilities for real-time applications.

Keywords:

6D pose estimation deep neural network intelligent manufacturing object recognition semantic segmentation

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Nov 20, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Robotics
Computer Vision
Artificial Intelligence

Background:

Intelligent robots are crucial in manufacturing, but precise object recognition and pose estimation in complex environments remain challenging.
Accurate determination of part category and pose is vital for automated assembly lines and robotic manipulation tasks.

Purpose of the Study:

To develop a robust, two-stage intelligent vision system for object recognition and 6D pose estimation using RGB-D images.
To improve the feature extraction capabilities for enhanced pose prediction in robotic applications.

Main Methods:

A dense-connected network fusing multi-scale features for object segmentation.
A pose estimation network integrating 2D and 3D data with channel and position attention modules for feature enhancement.
Validation on YCB-Video and LineMOD benchmark datasets.

Main Results:

The proposed method demonstrated superior performance compared to state-of-the-art networks on benchmark datasets.
The system effectively segments objects and accurately estimates their 6D pose by fusing color and geometry features.
Attention modules significantly improved feature extraction for pose prediction.

Conclusions:

The developed vision system provides an effective solution for object recognition and 6D pose estimation in manufacturing.
A vision-guided robotic grasping system built upon this method successfully performed pick-and-place operations.
The system shows significant potential for real-time manufacturing applications requiring precise robotic manipulation.