Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

599
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.
599

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

All-telecentric multi-camera microscopic FPP: Scheimpflug calibration and reprojection-based multi-view fusion.

Optics express·2026
Same author

Lung Cancer Cell-Macrophage Interaction System for Signal Pathway-Based Logic Analysis and Drug Testing.

ACS nano·2026
Same author

S2AFormer: Strip Self-Attention for Efficient Vision Transformer.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

Research Progress on the Utilization of Semi-Dry Calcium-Based Desulfurization Dross in China.

Materials (Basel, Switzerland)·2025
Same author

Research Progress in High-Entropy Ceramics in Material Corrosion Resistance.

Langmuir : the ACS journal of surfaces and colloids·2025
Same author

In Situ Synthesis and Wide-Temperature Tribological Properties of Biphasic Structure High-Entropy (Mg<sub>1/6</sub>Ni<sub>1/6</sub>Co<sub>1/6</sub>Cu<sub>1/6</sub>Zn<sub>1/6</sub>Al<sub>1/6</sub>)<sub>3</sub>O<sub>4</sub> Ceramics.

Langmuir : the ACS journal of surfaces and colloids·2025

相关实验视频

Updated: Jun 8, 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

2.7K

级联轮增强全视分段用于机器人视觉感知.

Yue Xu1,2,3, Runze Liu1,2, Dongchen Zhu1,3

  • 1Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China.

Frontiers in neurorobotics
|November 5, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了CCPSNet,这是一种全光细分的新方法,可以增强机器人场景的理解. 该网络通过整合轮信息来改善对象和纹理歧视,在具有挑战性的条件下表现出色.

关键词:
一个布式的布式.功能增强 功能增强 功能增强全视界线轮检测仪全视觉细分系统的细分.机器人视觉机器人视觉机器人视觉结构结构 感知 感知视觉路径的视觉路径

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369
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

2.0K

相关实验视频

Last Updated: Jun 8, 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

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369
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

2.0K

科学领域:

  • 计算机视觉 计算机视觉
  • 机器人技术 机器人技术 机器人技术
  • 人工智能的人工智能

背景情况:

  • 泛光细分对于机器人环境理解至关重要.
  • 现有的方法难以处理薄弱的纹理和小物体.

研究的目的:

  • 为了提高机器人场景的理解,使用一种新的级联轮增强泛光细分网络 (CCPSNet).
  • 通过纳入受生物视觉启发的结构性知识来提高实例的歧视性.

主要方法:

  • 设计了一个级联轮检测流与道调节结构感知模块和粗细的战略.
  • 开发了一个以轮为导向的多尺度特征增强流,使用结构意识的特征调制和反向聚合.
  • 集成的轮信息与多尺度的上下文特征.

主要成果:

  • 在城市景观 (61.2 PQ) 和COCO (43.5 PQ) 数据集上实现了更高的准确性.
  • 在模拟具有挑战性的现实世界场景 (如脏的摄像头和雨) 中表现出强性.

结论:

  • 在复杂的环境中,CCPSNet显著提高了机器人的感知能力.
  • 未来的工作可能会探索无监督培训,以降低计算成本.