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

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

Text-guided RGB-P grasp generation.

PeerJ. Computer science·2025
Same author

SVD-Based Mind-Wandering Prediction from Facial Videos in Online Learning.

Journal of imaging·2024
Same author

Simulation-Based Designing of Suitable Stimulation Factors for Presenting Two Phosphenes Simultaneously to Lower Side of Field of View.

Bioengineering (Basel, Switzerland)·2022
Same author

Repetition-Based Approach for Task Adaptation in Imitation Learning.

Sensors (Basel, Switzerland)·2022
Same author

Novel Projection Schemes for Graph-Based Light Field Coding.

Sensors (Basel, Switzerland)·2022
Same author

Simulation-Based Clarification of Appropriate Factors for Presenting Phosphene in Two Directions Avoiding Electrical Interference.

Bioengineering (Basel, Switzerland)·2021

相关实验视频

Updated: Jul 19, 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

2.8K

IRDC-Net:基于单眼相机的轻量级语义细分网络,用于移动机器人导航.

Thai-Viet Dang1, Dinh-Manh-Cuong Tran1, Phan Xuan Tan2

  • 1Department of Mechatronics, School of Mechanical Engineering, Hanoi University of Science and Technology, Hanoi 10000, Vietnam.

Sensors (Basel, Switzerland)
|August 12, 2023
PubMed
概括
此摘要是机器生成的。

本研究提出了一个轻量级的语义细分模型,用于实时移动机器人导航. 该模型有效地提取走廊场景,允许精确避开障碍物和最佳路径规划.

关键词:
计算机视觉 计算机视觉移动机器人 移动机器人导航 导航 导航 导航 导航避免障碍 避免障碍 避免障碍语义细分 语义细分 语义细分 语义细分

更多相关视频

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

9.0K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

11.7K

相关实验视频

Last Updated: Jul 19, 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

2.8K
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

9.0K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

11.7K

科学领域:

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

背景情况:

  • 移动机器人导航在很大程度上依赖于计算机视觉来定位和寻找路径.
  • 环境的复杂性需要高计算性能的高效避障系统.
  • 目前的方法通常涉及复杂的传感器系统和大量的计算负载.

研究的目的:

  • 开发一个实时,计算高效的解决方案,从单个图像中提取走廊场景,用于移动机器人导航.
  • 通过使用轻量级语义细分模型和量化技术来降低培训参数和计算成本.
  • 增强移动机器人的避障能力.

主要方法:

  • 提出了一种轻量级的语义细分模型,将完全卷积网络 (FCN) 解码器与具有多尺度融合的MobileNetV2编码器相结合.
  • 集成量子化技术以最大限度地降低计算成本和培训参数.
  • 使用平衡交叉损失函数来解决不同数据集中的类不平衡.
  • 利用亚当优化器和高斯过器来提高细分性能.

主要成果:

  • 拟议的模型在各种数据集中表现出高于基线方法的性能.
  • 在保持高精度的同时,大大减少了计算时间.
  • 在实践实验中,模型的性能与真正的移动机器人保持一致.
  • 有效地支持最佳路径规划和障碍回避.

结论:

  • 轻量级的语义细分模型为复杂环境中的移动机器人导航提供了有效的实时解决方案.
  • 量子化和特定损失函数的集成提高了计算效率和细分精度.
  • 该模型的实际适用性得到了验证,使移动机器人能够有效避免障碍物和规划路径.