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 journal

Injecting reasoning into vision-language models via weight-decomposed merging.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Non-equilibrium thermodynamic framework for neural networks: A principled correspondence and parameter dynamics.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dual-pathway mask ranking guided selective fine-tuning for backdoor purification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Discriminative transfer feature learning for unsupervised domain adaptation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

ARetinex-Net: Low-light image enhancement with adaptive retinex model and global illumination representation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Multi-Task Learning Framework with Physics Embedded for Signal Reconstruction and State Prediction in Underground Multi-Robot Systems.

Neural networks : the official journal of the International Neural Network Society·2026

相关实验视频

Updated: Jul 10, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

409

前景细分网络使用转换卷积神经网络和多尺度特征编码的上方采样.

Vishruth B Gowda1, M T Gopalakrishna2, J Megha3

  • 1Department of Computer Science and Engineering, SJB Institute of Technology, Bengaluru, Karnataka 560060, India; Visvesavaraya Technological University, Belgavi, Karnataka 590018, India.

Neural networks : the official journal of the International Neural Network Society
|November 20, 2023
PubMed
概括

这项研究介绍了一种新的前景细分网络 (FgSegNet),使用三重 CNN 和转置卷积神经网络 (TCNN) 来改进移动物体检测. 在具有挑战性的条件下,FgSegNet显著提高了前景细分的准确性.

关键词:
在CDnet2014数据集中,功能聚合模块是一个功能聚合模块.前面的细分是主要的细分.多个尺度的特征编码.转移的卷积神经网络.

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

559
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

相关实验视频

Last Updated: Jul 10, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

409
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

559
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

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 图像处理 图像处理

背景情况:

  • 前景细分对于分离移动物体至关重要,但面临着来自黑暗,动态背景和摄像机动的挑战.
  • 现有的检测网络与复杂的环境干扰作斗争,限制了它们的有效性.

研究的目的:

  • 开发一种先进的前景细分算法,克服现有方法的局限性.
  • 在多样化和具有挑战性的环境中提高前景细分的准确性和稳定性.

主要方法:

  • 一个新的前景细分网络 (FgSegNet) 被开发出来,它结合了三重卷积神经网络 (CNN) 和转移卷积神经网络 (TCNN).
  • 集成了一个特征聚合模块 (FPM) 来提取多个尺度的特征并将它们合并,减少输入的复杂性.
  • 添加了一个上采样网络,以匹配抽象图像表示的空间维度与输入图像.

主要成果:

  • 与最先进的算法相比,FgSegNet在CDnet2014数据集上表现出卓越的性能.
  • 实现了0.9804的平均F-测量,0.9801的精度和0.9896.6的回忆.
  • 添加一个升级抽样网络进一步改善了F-测量,达到0.9804.

结论:

  • 拟议的FgSegNet有效地解决了前景细分方面的挑战,实现了高精度.
  • 三重CNN,TCNN,FPM和上样的组合显著提高了前景细分性能.
  • 在计算机视觉应用中,FgSegNet代表了强大的前景细分的重大进步.